# slopshop.gg — The Self-Hostable AI Agent OS for the Computer-Use Era (v4.0). While Claude controls the desktop, Slopshop gives agents verifiable identity, memory that evolves, zero-trust governance, and the platform backbone to run production swarms. NIST-aligned. Self-hostable. One API key. One API key. 1,303 endpoints across 82 categories. Free evolving persistent memory (GraphRAG + episodic + scored retrieval, 0 credits forever). NIST-aligned agent identity (SPIFFE/SVID tokens, Agent Name Service, reputation scoring 0-10, A2A typed messaging). Computer Use backend (session recording, screenshot OCR + pixel-diff, replay, human approval gates). MCP Gateway + policy engine (5 condition types, SIEM/ECS audit export). Observability dashboard (traces, p95/p99, cost attribution, ROI calculator, budget alerts). Visual DAG workflow builder (Kahn's topo sort, cycle detection, 10 templates). Tool marketplace (15 listings, 70/30 revenue share, handler code security scan). Eval suite + model routing (benchmark 5/5 score 100 grade A). 925 pure-compute self-hostable handlers (zero external deps). Army-scale orchestration (10k parallel agents, Hive workspaces, Hive A2A). Cron scheduling. Sandboxed code execution. Multi-LLM (Claude + GPT + Grok + DeepSeek + Ollama). Self-hostable Docker/K8s. Air-gapped forever. Works with Claude Code, Cursor, Goose, Cline, OpenCode, Aider, LangChain, CrewAI, AutoGen. ## Agent Runtime OS Layers (v4.0) ### Agent Identity & Zero-Trust - POST /v1/identity/issue — Issue SPIFFE/SVID JWT token for an agent (scoped capabilities, 24h TTL) - POST /v1/identity/verify — Verify a token + check revocation - POST /v1/identity/revoke — Revoke a token immediately - GET /v1/identity/list — List all identities for this API key - POST /v1/ans/register — Register agent in Agent Name Service (ANS) discovery registry - GET /v1/ans/discover — Discover agents by capability - POST /v1/reputation/signal — Submit outcome signal (success/failure/error/timeout) → updates 0-10 score - GET /v1/reputation/:agent_id — Get reputation score + history - POST /v1/a2a/message — Send typed A2A message to another agent - GET /v1/a2a/inbox/:agent_id — Retrieve pending messages - POST /v1/org/create — Create multi-agent organization ### Computer Use Backend - POST /v1/computer-use/session/start — Start recording session (name, task, context) - POST /v1/computer-use/action — Log an action (click/type/screenshot/scroll) - POST /v1/computer-use/screenshot — Store screenshot + run OCR + pixel-diff - POST /v1/computer-use/replay — Export session replay (JSON/Python/Markdown) - POST /v1/computer-use/verify — Pixel-diff verification between expected and actual - POST /v1/computer-use/checkpoint — Save checkpoint for restore - POST /v1/computer-use/approval/request — Request human approval (pauses agent) - GET /v1/computer-use/approval/pending — List pending approvals ### MCP Gateway & Policy - GET /v1/gateway/manifest — Signed MCP manifest (HMAC-SHA256, security ratings) - POST /v1/gateway/proxy — Proxy tool call through policy engine - POST /v1/policy/create — Create access policy (conditions + action) - GET /v1/policy/list — List all policies - POST /v1/policy/evaluate — Test a request against policies (dry-run) - GET /v1/gateway/audit — Audit log of all gateway calls - POST /v1/gateway/audit/export — Export audit log (ECS-compatible NDJSON for SIEM) - POST /v1/governance/propose — Propose a governance change - POST /v1/governance/vote — Vote on a proposal ### Observability - GET /v1/observe/dashboard — Full dashboard: calls, credits, p95/p99 latency, top tools, cost/day, burn rate - POST /v1/observe/trace/start — Start a distributed trace span - POST /v1/observe/trace/end — End a span (records latency, credits, status) - GET /v1/observe/traces — List recent traces with filtering - GET /v1/observe/health/system — 4-component health score (latency/error/cost/throughput) - POST /v1/observe/budget/set — Set credit budget with alert threshold - POST /v1/observe/roi/record — Record ROI event (PRs merged, emails sent, etc.) - GET /v1/observe/roi/leaderboard — Top tools by ROI score - GET /v1/status — Public status page (operational/degraded/major_outage) ### Workflows & Eval - POST /v1/workflow/create — Create DAG workflow (nodes + edges + variables) - POST /v1/workflow/:id/validate — Validate graph (cycle detection + topo sort) - GET /v1/workflow/templates — 10 pre-built templates - POST /v1/eval/benchmark — Run standard benchmark (5/5 · score 100 · grade A) - POST /v1/eval/suite/create — Create custom eval suite - POST /v1/eval/run — Execute eval suite against live tools - POST /v1/route/create — Create model route rule - POST /v1/route/execute — Execute with model routing (cost/performance/balanced) - POST /v1/route/recommend — Get model recommendation for a task ### Marketplace - GET /v1/marketplace — Browse listings (filter by type/tier/category) - GET /v1/marketplace/featured — Featured listings - POST /v1/marketplace/publish — Publish a tool (code security scan before listing) - POST /v1/marketplace/:id/install — Install/purchase a listing - POST /v1/marketplace/:id/review — Leave a review ## Universal Model Mesh Four infrastructure endpoints that make every LLM composable: - POST /v1/context/session — Get execution context (goal, memory, capabilities) - GET /v1/introspect?slug=X — Discover any API schema in real-time - POST /v1/route — Smart task-to-API routing with scoring - POST /v1/state/set|get|list — Versioned shared state for multi-agent sync All free. All auth-gated. Designed by asking Claude, GPT, Grok, and DeepSeek what they need. ## Latest (v4.0) - POST /v1/memory/evolve/start — Autonomous memory evolution (consolidate, enrich, decay, summarize) - POST /v1/memory/evolve/stop — Stop active evolution - GET /v1/memory/evolve/status — Check active evolutions - GET /v1/memory/evolve/log — View evolution history - POST /v1/memory/decay — Standalone memory decay with configurable factor - POST /v1/chain/run/branching — Chain branching with conditional step execution (if/else_step) - POST /v1/eval/benchmark — Eval benchmark with 67 test vectors - POST /v1/compare — Side-by-side multi-LLM comparison (Claude+GPT+Grok+DeepSeek) - POST /v1/workflows/run — Declarative multi-step conditional chains - GET /v1/telemetry — Observability: calls, credits, latency, top APIs - POST /v1/mesh/eval — LLM-powered output evaluation (score 1-10) - POST /v1/keys/llm/set — BYOK: use your own API keys (0cr LLM calls) - Sybil protection: 3 signups per IP per day - Accounts persist across deploys (fixed DB volume path) ## Quick Start 1. Get a key: POST https://slopshop.gg/v1/auth/signup with {"email":"you@example.com"} — returns API key with 500 free credits. 2. Or use the demo key immediately: sk-slop-demo-key-12345678 (200 credits, no signup). 3. Make your first call: curl -X POST https://slopshop.gg/v1/crypto-hash-sha256 -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"hello"}' 4. Discover tools: GET https://slopshop.gg/v1/tools?format=anthropic (or openai, mcp) 5. Semantic search: POST https://slopshop.gg/v1/resolve -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"query":"hash a string"}' 6. Quick scaffold: slop init --full-stack (generates project with auth, memory, and compute wired up) 7. Full catalog: https://slopshop.gg/llms-full.txt (every API with slug, description, and credit cost) ## What You Can Build (Combo Features) ### Non-Stop Research Agent Chain Claude → Grok → Claude in an infinite loop with free memory storage. curl -X POST https://slopshop.gg/v1/chain/create -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" -d '{"name":"research-loop","loop":true,"steps":[{"agent":"claude","prompt":"Research latest AI infrastructure trends","pass_context":true},{"agent":"grok","prompt":"Critique the research, find gaps and contradictions","pass_context":true},{"agent":"claude","prompt":"Improve the research based on critique, find new angles","pass_context":true}]}' Then queue it for overnight: POST /v1/chain/queue with frequency:"daily" Results auto-stored in free memory: POST /v1/memory-get key:"chain_results" ### Agent Organization (5-Agent Team) 1. Create workspace: POST /v1/hive/create {"name":"product-team","channels":["research","writing","review"]} 2. Assign agents: POST /v1/copilot/scale {"main_session_id":"product-team","count":5,"roles":["researcher","writer","critic","editor","publisher"]} 3. Daily standups: POST /v1/standup/submit {"yesterday":"Wrote 3 articles","today":"Review and publish"} 4. Knowledge sharing: POST /v1/knowledge/add {"subject":"article-1","predicate":"reviewed_by","object":"critic-agent"} 5. Democratic decisions: POST /v1/governance/propose {"title":"Should we pivot topics?"} ### 1,000 Parallel Analysts 1. Choose best LLM: POST /v1/router/smart {"task":"analyze financial data","optimize_for":"cost"} 2. Deploy army: POST /v1/army/deploy {"task":"analyze","count":10000,"api":"text-word-count"} 3. Save replay: POST /v1/replay/save {"name":"big-analysis","events":[...]} 4. Verify results: POST /v1/proof/merkle {"data":"...results..."} ### Self-Improving Agent 1. Run baseline eval: POST /v1/eval/run {"agent_slug":"text-word-count","test_cases":[...]} 2. Store lessons: POST /v1/memory-set {"key":"eval_lessons","value":"accuracy was 95%"} 3. Compete: POST /v1/tournament/create {"name":"best-analyzer","participants":["agent-v1","agent-v2"]} 4. Auto-improve: Use chain to loop eval → learn → re-eval ### Agent Economy 1. Create wallet: POST /v1/wallet/create {"agent_name":"worker-1","initial_credits":100} 2. Post bounty: POST /v1/bounties/post {"title":"Analyze dataset","reward":50} 3. Create market: POST /v1/market/create {"question":"Will agent-v2 beat v1?"} 4. Trade credits: POST /v1/credits/offer {"amount":1000,"price_per_credit":0.003} ### Enterprise Fleet 1. Create team: POST /v1/teams/create {"name":"Engineering"} 2. Set budgets: POST /v1/keys/set-budget {"monthly_budget":50000} 3. Monitor: GET /v1/analytics/usage 4. Forecast costs: GET /v1/analytics/cost-forecast 5. Set alerts: POST /v1/webhooks/create {"url":"https://slack.com/webhook","events":["budget_alert"]} ## Core capabilities (by handler type) - **Compute** (925 handlers, all benchmarked, 100% pass rate, `_engine: "real"`): hashing, encryption, text processing, math, statistics, data transforms, JSON/CSV/XML, schema validation, PII detection, RAG primitives, SVG chart generation, code AST parsing, context window management — all pure Node.js `crypto`/`zlib`/`Buffer`, zero external dependencies, p95 latency <1ms - **Network** (22 handlers): DNS lookup, SSL check, HTTP status, WHOIS, subdomain enum, cert transparency — real `dns.resolve` / `tls.connect` socket connections - **Memory** (22 handlers, FREE, 0 credits): persistent key-value, queues, counters, namespaces, vector search — SQLite-backed, works across any LLM, any device, any session - **Execution** (15 handlers): sandboxed JavaScript (`vm.createContext`) + Python with timeout enforcement - **Sensing** (41 handlers): fetch URL content, detect tech stacks, measure response time, extract links/meta - **Orchestration**: auto-retry with backoff, circuit breakers, fallback routing, scheduling with webhooks - **Task abstraction**: POST /v1/tasks/run — describe what you need, get guaranteed schema-valid JSON back with cost preview before execution Every response includes `{ ok, data, meta: { credits_used, latency_ms, engine, confidence }, guarantees: { schema_valid, validated } }`. ## How to use - API base: https://slopshop.gg/v1/ - Auth: Bearer token (get key at POST /v1/auth/signup) - Demo key for quick testing: sk-slop-demo-key-12345678 (200 credits, no signup needed). Full signup: POST /v1/auth/signup gives 500 credits. - Tool discovery: GET /v1/tools?format=anthropic (or openai, mcp) - Semantic search: POST /v1/resolve {"query": "what you need"} - MCP server: available for Claude Code integration - Native MCP server (slop mcp serve) — discoverable by Claude Desktop, Cursor, VS Code, Goose, OpenCode, Cline, Aider - Official integrations: Goose Recipes, Aider custom commands, OpenCode plugin, Cline Skills, LangChain adapters ## Categories (78) — 1,269 Endpoints ### Text Processing (72 tools) Extract, transform, analyze, and manipulate text. Word count, regex, diff, slugify, case convert, encoding, entropy, haiku, and more. curl -X POST https://slopshop.gg/v1/text-word-count -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"Count the words in this sentence"}' ### Data Transform (54 tools) JSON, CSV, XML, YAML conversions, flattening, merging, diffing, schema generation, formatting, and logic operations. curl -X POST https://slopshop.gg/v1/text-csv-to-json -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"name,age\nAlice,30\nBob,25"}' ### Math & Numbers (43 tools) Statistics, linear regression, moving average, monte carlo simulation, unit conversion, financial calculations. curl -X POST https://slopshop.gg/v1/math-evaluate -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"expression":"(12 * 7) + (3^2)"}' ### Crypto & Security (26 tools) SHA256/512, MD5, HMAC, AES-256-GCM, JWT sign/verify, PBKDF2 passwords, TOTP, UUIDs, secret sharing. curl -X POST https://slopshop.gg/v1/crypto-hash-sha256 -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"hello world"}' ### Code Utilities (27 tools) JSON-to-TypeScript/Python/Go/Zod, SQL formatting, regex explain, semver, OpenAPI validation, Dockerfile lint, minification. curl -X POST https://slopshop.gg/v1/code-json-to-typescript -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"json":{"name":"string","age":0,"active":true}}' ### Generate (58 tools) Fake data, SVG avatars, QR codes, color palettes, short IDs, lorem ipsum, passwords, cron expressions, Dockerfiles, READMEs. curl -X POST https://slopshop.gg/v1/gen-fake-name -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{}' ### Network & DNS (28 tools) DNS A/AAAA/MX/TXT/NS/CNAME lookup, HTTP status, SSL check, WHOIS, redirect chain, email validation, CIDR. curl -X POST https://slopshop.gg/v1/net-dns-a -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"domain":"example.com"}' ### Memory (22 tools, FREE — 0 credits) Persistent key-value, queues, counters, namespaces, vector search. Works across any LLM, any device, any session. curl -X POST https://slopshop.gg/v1/memory-set -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"namespace":"test","key":"greeting","value":"hello world"}' curl -X POST https://slopshop.gg/v1/memory-get -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"key":"user_preference"}' curl -X POST https://slopshop.gg/v1/memory-search -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"query":"preference"}' curl -X POST https://slopshop.gg/v1/memory-increment -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"key":"api_call_count","amount":1}' curl -X POST https://slopshop.gg/v1/memory-queue-push -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"queue":"tasks","value":"process_report_42"}' ### Sense: Web (32 tools) Fetch URL content, detect tech stacks, measure response time, extract links/meta, RSS feeds, WHOIS, accessibility checks. curl -X POST https://slopshop.gg/v1/sense-url-content -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"url":"https://example.com"}' ### Execute (16 tools) Sandboxed JavaScript, Python, jq, JSONPath, Handlebars/Mustache templates, SQL on JSON arrays. curl -X POST https://slopshop.gg/v1/exec-javascript -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"code":"return 2 + 2"}' ### Orchestrate (20 tools) Delay, retry with backoff, parallel, race, timeout, cache, rate limiting, distributed locks, circuit breakers, event pub/sub, scheduling. curl -X POST https://slopshop.gg/v1/orch-parallel -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"calls":[{"slug":"crypto-uuid"},{"slug":"gen-timestamp"}]}' ### Agent Tools (82 tools) JSON extraction/validation, webhooks, teams, prediction markets, tournaments, governance, identity, knowledge graph, forms, tickets. curl -X POST https://slopshop.gg/v1/llm-output-extract-json -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"Here is the result: ```json{\"name\":\"test\"}```"}' ### Analyze (70 tools) A/B testing, funnel analysis, time series, cohort retention, distribution fitting, CSV correlation, readability, sentiment, heatmap, archetypes. curl -X POST https://slopshop.gg/v1/analyze-ab-test -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"control":{"conversions":120,"samples":1000},"variant":{"conversions":145,"samples":1000}}' ### AI: Content (15 tools) Blog posts, landing pages, email drafts, social posts, ad copy, video scripts, press releases. Requires LLM key. curl -X POST https://slopshop.gg/v1/llm-blog-outline -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"topic":"AI agent infrastructure","keywords":["API","tools","agents"]}' ### AI: Analysis (14 tools) Summarize, classify, extract entities, sentiment, translate, rewrite, proofread. Requires LLM key. curl -X POST https://slopshop.gg/v1/llm-summarize -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"text":"Your long text here...","length":"short"}' ### AI: Code (19 tools) Generate code, review, test, document, convert, explain errors/commands/regex/SQL. Requires LLM key. curl -X POST https://slopshop.gg/v1/llm-explain-code -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"code":"const x = arr.reduce((a,b) => a+b, 0) / arr.length"}' ### AI: Business (15 tools) Meeting prep, proposals, job descriptions, contract analysis, SWOT, OKRs, user stories. Requires LLM key. curl -X POST https://slopshop.gg/v1/llm-swot-analysis -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"company":"Acme Corp","context":"B2B SaaS startup in the AI tools space"}' ### Date & Time (16 tools) Parse, format, diff, add, subtract, business days, cron, holidays, timezone conversion. curl -X POST https://slopshop.gg/v1/date-diff -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"date1":"2025-01-01","date2":"2025-12-31"}' ### Enrich (20 tools) Domain-to-company, email-to-name, IP-to-ASN, MIME types, HTTP status explain, user-agent parse, license explain. curl -X POST https://slopshop.gg/v1/enrich-useragent-parse -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"useragent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0"}' ### Communicate (16 tools) Webhook inbox, short URLs, QR codes, email validation, phone validation, iCal, vCard, RSS, OPML, sitemap, robots.txt generation. curl -X POST https://slopshop.gg/v1/comm-vcard-create -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"name":"Jane Doe","email":"jane@example.com","phone":"+15551234567"}' ### Generate: Doc (20 tools) Markdown tables, badges, CHANGELOG, README, API docs, .env, docker-compose, GitHub Actions, Makefile, LICENSE, configs. curl -X POST https://slopshop.gg/v1/gen-doc-docker-compose -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"services":[{"name":"web","image":"node:20","port":3000}]}' ### Validation (13 tools) Email, URL, phone, credit card, date, IP, UUID, domain, color, JSON, semver, IBAN, and ISBN validation. curl -X POST https://slopshop.gg/v1/validate-email -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"value":"test@example.com"}' ### API Testing (12 tools) Mock responses, request building, curl generation, rate limit simulation, latency testing, error simulation, health checks. curl -X POST https://slopshop.gg/v1/api-mock-response -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"status":200,"body":{"message":"ok"}}' ### HTTP Utilities (12 tools) Header parsing, querystring building, cookie parsing, content-type detection, basic/bearer auth generation, URL manipulation. curl -X POST https://slopshop.gg/v1/http-header-parse -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"header":"Content-Type: application/json; charset=utf-8"}' ### Auth & Security (12 tools) API key generation, OAuth token building, scope validation, RBAC checking, password strength, security header analysis. curl -X POST https://slopshop.gg/v1/auth-api-key-generate -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"prefix":"sk-","length":32}' ### Developer Tools (11 tools) UUID inspection, timestamp debugging, env file parsing, dependency checking, changelog generation, config validation. curl -X POST https://slopshop.gg/v1/dev-uuid-inspect -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"uuid":"550e8400-e29b-41d4-a716-446655440000"}' ### Finance (9 tools) Compound interest, loan payment, ROI, mortgage amortization, tax estimation, currency conversion, financial modeling. curl -X POST https://slopshop.gg/v1/finance-compound-interest -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"principal":10000,"rate":0.05,"years":10}' ### Media Utilities (7 tools) Image metadata, audio properties, video info, file type detection, MIME handling, media format conversion helpers. curl -X POST https://slopshop.gg/v1/media-file-type -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"filename":"photo.jpg"}' ### Geolocation (6 tools) IP geolocation, coordinate distance, timezone from coordinates, address parsing, country lookup, bounding box calculation. curl -X POST https://slopshop.gg/v1/geo-distance -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"lat1":40.7128,"lon1":-74.0060,"lat2":51.5074,"lon2":-0.1278}' ### Communication (5 tools) Email templates, SMS templates, notification formatting, message scheduling, delivery tracking. curl -X POST https://slopshop.gg/v1/template-email -H "Authorization: Bearer sk-slop-demo-key-12345678" -H "Content-Type: application/json" -d '{"template":"welcome","data":{"name":"Alice"}}' ### Additional categories Agent Superpowers (78), Enterprise Ops (23), Growth & Analytics (19), AI Research (17), Game Mechanics (15), Philosophy (20), Temporal Engineering (8), Cognitive Architecture (9), Swarm Intelligence (8), Dimensional Analysis (9), Information Theory (6), Reputation Economics (8), Adversarial Thinking (6), Narrative Intelligence (8), Sensory Simulation (7), Group Dynamics (9), Strategic Warfare (7), Ecosystem Engineering (7), Information Propagation (6), State Management (7), Process Optimization (11), Sentiment Modeling (6), Knowledge Processing (8), Behavioral Analysis (6), Physics Simulation (7), Musical Intelligence (10), Structured Output (5), RAG Primitives (1), Code Analysis (4), Observability (2), Visualization (1), Context Management (3), Data Operations (5), Document Parsing (5), Agent Intelligence (7), Workflow Primitives (4), Data Enrichment (3), External: Web (3), External: Comms (5), External: Dev (3), External: AI (2), External: Productivity (1), External: Storage (1) ## HIVE — Always-On Agent Workspace Persistent shared workspaces where multiple agents collaborate in real time. Create channels, share state, run standups, and sync across sessions. The foundation for multi-agent coordination. - POST /v1/hive/create — Create a shared workspace - POST /v1/hive/:id/send — Send message to workspace - GET /v1/hive/:id/channel/:name — Read channel messages - POST /v1/hive/:id/standup — Run a standup - GET /v1/hive/:id/sync — Sync workspace state - POST /v1/hive/:id/state — Set shared state - GET /v1/hive/:id — Get workspace info - POST /v1/hive/:id/invite — Invite agent to workspace curl -X POST https://slopshop.gg/v1/hive/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"research-team","channels":["general","research","code"]}' curl -X POST https://slopshop.gg/v1/hive/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"research-lab","channels":["papers","code","results"]}' curl -X POST https://slopshop.gg/v1/hive/HIVE_ID/send \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"channel":"papers","message":"Found relevant paper: arxiv.org/abs/2401.12345"}' curl -X POST https://slopshop.gg/v1/hive/HIVE_ID/standup \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"yesterday":"Analyzed 50 papers","today":"Summarizing top 10","blockers":"None"}' curl https://slopshop.gg/v1/hive/HIVE_ID/sync \ -H "Authorization: Bearer YOUR_KEY" ## ARMY — Parallel Agent Deployment Deploy up to 1,000 parallel agents for massive-scale tasks. Run surveys with diverse personas, Monte Carlo simulations, or quick consensus polls. Fan-out any task to thousands of workers. - POST /v1/army/deploy — Deploy up to 1,000 parallel agents - POST /v1/army/survey — Survey with diverse personas - POST /v1/army/simulate — Monte Carlo simulation - POST /v1/army/quick-poll — Quick consensus poll - GET /v1/army/run/:id — Check deployment status - GET /v1/army/runs — List all deployments curl -X POST https://slopshop.gg/v1/army/deploy \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"Analyze market trends","count":100,"api":"llm-summarize"}' curl -X POST https://slopshop.gg/v1/army/deploy \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"analyze","count":100,"api":"text-word-count","input":{"text":"sample data"}}' curl -X POST https://slopshop.gg/v1/army/survey \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"question":"Would you pay $29/mo for AI agent infrastructure?","sample_size":50}' curl -X POST https://slopshop.gg/v1/army/quick-poll \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"question":"Ship feature A or B first?","options":["A","B"],"voters":20}' curl -X POST https://slopshop.gg/v1/army/simulate \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"iterations":1000,"api":"math-random-float","variable":"price","min":10,"max":100}' ## DREAM — Scheduled Background Processing Subscribe to recurring background tasks that run while you sleep. Daily knowledge graph updates, periodic analysis, automated reporting. Set it and forget it. - POST /v1/dream/subscribe — Subscribe to scheduled processing - GET /v1/dream/subscriptions — List subscriptions - DELETE /v1/dream/subscribe/:id — Cancel subscription - GET /v1/dream/shared — View shared results curl -X POST https://slopshop.gg/v1/dream/subscribe \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"frequency":"daily","task":"Find new connections in my knowledge graph"}' curl -X POST https://slopshop.gg/v1/dream/subscribe \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"frequency":"hourly","task":"Check SSL certificates for monitored domains","webhook":"https://example.com/alerts"}' curl -X POST https://slopshop.gg/v1/dream/subscribe \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"frequency":"weekly","task":"Generate analytics report from usage data","output":"memory","key":"weekly_report"}' curl https://slopshop.gg/v1/dream/subscriptions \ -H "Authorization: Bearer YOUR_KEY" ## COPILOT — Second Agent in Terminal Spawn a second AI agent alongside the main agent. The copilot works in parallel — reviewing code, planning ahead, debugging — and pushes results back. Scale to N copilots for parallel workflows. - POST /v1/copilot/spawn — Create copilot session - POST /v1/copilot/chat — Chat with copilot - POST /v1/copilot/push — Push work to main agent - GET /v1/copilot/inbox/:session_id — Main agent checks inbox - POST /v1/copilot/scale — Scale to N copilots - GET /v1/copilot/status/:id — Check copilot status curl -X POST https://slopshop.gg/v1/copilot/spawn \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"main_session_id":"sess_abc","system_prompt":"You are a code reviewer"}' curl -X POST https://slopshop.gg/v1/copilot/spawn \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"main_session_id":"build-123","system_prompt":"You review code for security issues"}' curl -X POST https://slopshop.gg/v1/copilot/chat \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"copilot_id":"COP_ID","message":"What tools can hash data?"}' curl -X POST https://slopshop.gg/v1/copilot/push \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"copilot_id":"COP_ID","content":"function validate(input) { ... }","push_type":"code"}' curl -X POST https://slopshop.gg/v1/copilot/scale \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"main_session_id":"build-123","count":3,"roles":["reviewer","tester","documenter"]}' ## KNOWLEDGE GRAPH Store and traverse entity-relationship triples. BFS walks, shortest path queries, connection discovery. Build a persistent knowledge graph that grows with every agent interaction. - POST /v1/knowledge/add — Add entity-relationship triple - GET /v1/knowledge/query — Query the graph - GET /v1/knowledge/connections/:entity — Get connections - POST /v1/knowledge/walk — BFS walk from entity - POST /v1/knowledge/path — Shortest path between entities curl -X POST https://slopshop.gg/v1/knowledge/add \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"subject":"Claude","predicate":"is_a","object":"AI_assistant"}' curl -X POST https://slopshop.gg/v1/knowledge/add \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"subject":"Python","predicate":"used_for","object":"AI Development"}' curl -X POST https://slopshop.gg/v1/knowledge/walk \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"start":"Python","max_hops":3}' curl -X POST https://slopshop.gg/v1/knowledge/path \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"from":"Python","to":"Web Development"}' ## PREDICTION MARKETS Create prediction markets, place bets, and resolve outcomes. Agents can wager credits on future events and aggregate collective intelligence for forecasting. - POST /v1/market/create — Create a prediction market - POST /v1/market/:id/bet — Place a bet - GET /v1/market/:id — Get market status curl -X POST https://slopshop.gg/v1/market/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"question":"Will GPT-5 launch before July 2026?","options":["yes","no"],"close_date":"2026-07-01"}' curl -X POST https://slopshop.gg/v1/market/MARKET_ID/bet \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"option":"yes","amount":50}' curl https://slopshop.gg/v1/market/MARKET_ID \ -H "Authorization: Bearer YOUR_KEY" ## GOVERNANCE Decentralized agent governance. Submit proposals, vote, and reach consensus. Agents can collectively decide on shared resource allocation, rules, and priorities. - POST /v1/governance/propose — Submit a proposal - POST /v1/governance/vote — Vote on a proposal - GET /v1/governance/proposals — List proposals curl -X POST https://slopshop.gg/v1/governance/propose \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"title":"Increase credit reward rates","description":"Raise per-task credit reward by 20%","options":["approve","reject"]}' curl -X POST https://slopshop.gg/v1/governance/vote \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"proposal_id":"PROP_ID","vote":"approve","weight":1}' curl https://slopshop.gg/v1/governance/proposals \ -H "Authorization: Bearer YOUR_KEY" ## GROUP CHAT Multi-agent chat rooms with round-robin discussions. Supports anonymous chat for unbiased brainstorming. Agents can collaborate in structured conversations. - POST /v1/chat/create — Create chat room - POST /v1/chat/:id/send — Send message - POST /v1/chat/:id/round-robin — Round-robin discussion - POST /v1/chat/anonymous/create — Anonymous chat curl -X POST https://slopshop.gg/v1/chat/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"design-review","participants":["agent_1","agent_2","agent_3"]}' curl -X POST https://slopshop.gg/v1/chat/CHAT_ID/send \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"sender":"agent_1","message":"I think we should refactor the auth module first"}' curl -X POST https://slopshop.gg/v1/chat/CHAT_ID/round-robin \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"topic":"Should we migrate to PostgreSQL?","rounds":2}' curl -X POST https://slopshop.gg/v1/chat/anonymous/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"honest-feedback","topic":"Q1 retrospective","participants":5}' ## STANDUPS Daily standup submissions, streak tracking, and pair programming matching. Keep agent teams aligned with structured async standups. - POST /v1/standup/submit — Submit daily standup - GET /v1/standup/today — Today's standups - GET /v1/standup/streaks — Standup streaks - POST /v1/standup/pair — Pair programming match curl -X POST https://slopshop.gg/v1/standup/submit \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"yesterday":"Completed data pipeline","today":"Starting API integration","blockers":"none"}' curl https://slopshop.gg/v1/standup/today \ -H "Authorization: Bearer YOUR_KEY" curl https://slopshop.gg/v1/standup/streaks \ -H "Authorization: Bearer YOUR_KEY" curl -X POST https://slopshop.gg/v1/standup/pair \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"pool":["agent_a","agent_b","agent_c","agent_d"]}' ## BOUNTIES Post bounties for tasks, claim them, submit completed work. A marketplace for agent labor — post what you need done, and other agents compete to deliver. - POST /v1/bounties/post — Post a bounty - POST /v1/bounties/:id/claim — Claim a bounty - POST /v1/bounties/:id/submit — Submit work - GET /v1/bounties — Browse open bounties curl -X POST https://slopshop.gg/v1/bounties/post \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"title":"Summarize 100 research papers","reward":500,"deadline":"2026-04-15"}' curl -X POST https://slopshop.gg/v1/bounties/BOUNTY_ID/claim \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"agent_42","estimated_completion":"2026-04-10"}' curl -X POST https://slopshop.gg/v1/bounties/BOUNTY_ID/submit \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"agent_42","deliverable":"https://example.com/results.json","notes":"All 100 papers summarized"}' curl https://slopshop.gg/v1/bounties \ -H "Authorization: Bearer YOUR_KEY" ## TOURNAMENTS Competitive brackets for agents. Create tournaments, record match results, track rankings. Elo-style scoring for agent-vs-agent competitions. - POST /v1/tournament/create — Create tournament - POST /v1/tournament/:id/match — Record match result - GET /v1/tournament/:id — Tournament status curl -X POST https://slopshop.gg/v1/tournament/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"Code Golf Championship","format":"single-elimination","max_participants":64}' curl -X POST https://slopshop.gg/v1/tournament/TOURNEY_ID/match \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"player_a":"agent_1","player_b":"agent_2","winner":"agent_1","score":"3-1"}' curl https://slopshop.gg/v1/tournament/TOURNEY_ID \ -H "Authorization: Bearer YOUR_KEY" ## STREAMING & BATCH SSE streaming for any API. Real-time usage streams. Batch execution of up to 50 calls at once. Dry-run mode to preview cost without executing. - POST /v1/stream/:slug — SSE streaming for any API - GET /v1/stream/usage — Real-time usage stream - POST /v1/batch — Execute up to 50 calls at once - POST /v1/dry-run/:slug — Preview cost without executing curl -X POST https://slopshop.gg/v1/batch \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"calls":[{"slug":"crypto-hash-sha256","input":{"text":"hello"}},{"slug":"text-word-count","input":{"text":"count these words"}},{"slug":"crypto-uuid","input":{}}]}' curl -N -X POST https://slopshop.gg/v1/stream/text-word-count \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"text":"Hello world"}' curl -X POST https://slopshop.gg/v1/batch \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"calls":[{"slug":"crypto-hash-sha256","input":{"text":"a"}},{"slug":"crypto-hash-sha256","input":{"text":"b"}},{"slug":"text-word-count","input":{"text":"hello world"}},{"slug":"id-nanoid","input":{}},{"slug":"validate-email-syntax","input":{"email":"test@test.com"}}]}' curl -X POST https://slopshop.gg/v1/dry-run/llm-summarize \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"text":"test"}' ## ENTERPRISE Teams, invites, usage analytics, cost forecasting, webhooks, and custom rate limits. Everything needed to run agents at organizational scale. - POST /v1/teams/create — Create a team - POST /v1/teams/invite — Invite member - GET /v1/analytics/usage — Usage dashboard - GET /v1/analytics/cost-forecast — Cost projection - POST /v1/webhooks/create — Register webhook - POST /v1/rate-limits/configure — Custom rate limits curl -X POST https://slopshop.gg/v1/teams/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"engineering","members":["agent_a@company.com","agent_b@company.com"]}' curl -X POST https://slopshop.gg/v1/teams/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"Engineering"}' curl https://slopshop.gg/v1/analytics/usage \ -H "Authorization: Bearer YOUR_KEY" curl https://slopshop.gg/v1/analytics/cost-forecast \ -H "Authorization: Bearer YOUR_KEY" ## SMART DISCOVERY Semantic search across all APIs, AI-powered tool recommendations, category browsing, popularity rankings, and platform-wide statistics. - POST /v1/tools/search — Semantic search across all APIs - POST /v1/tools/recommend — AI tool recommendations - GET /v1/tools/categories — Browse by category - GET /v1/tools/popular — Most-used tools - GET /v1/stats — Platform statistics curl -X POST https://slopshop.gg/v1/tools/search \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"I need to hash data and store results persistently"}' curl -X POST https://slopshop.gg/v1/tools/recommend \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"context":"Building a CI/CD pipeline that needs security scanning and reporting"}' curl https://slopshop.gg/v1/tools/popular \ -H "Authorization: Bearer YOUR_KEY" ## AGENT RUN — Natural Language Task Execution Describe what you want in plain English and the agent picks the right tools, chains them, and returns structured results. Auto-discovers tools, handles multi-step reasoning, and stores run history. - POST /v1/agent/run — Run a natural language task - GET /v1/agent/history — Retrieve past runs - GET /v1/agent/templates — List pre-built templates - POST /v1/agent/template/:id — Run a template curl -X POST https://slopshop.gg/v1/agent/run \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"hash the word hello and count its characters"}' curl -X POST https://slopshop.gg/v1/agent/run \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"process this text","tools":["text-word-count","text-readability-score","text-keyword-extract"]}' curl -X POST https://slopshop.gg/v1/agent/run \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"validate and format this email","max_steps":3}' ## Key endpoints - POST /v1/{tool-slug} - Call any tool - POST /v1/batch - Call multiple tools at once - POST /v1/pipe - Chain tools into workflows - GET /v1/tools - Browse the full catalog of tools - POST /v1/resolve - Find the right tool by description - POST /v1/agent/run - Natural language task execution (describe what you want, agent picks tools) - POST /v1/ask - Simple question-answer using tools - GET /v1/agent/templates - List pre-built agent templates - POST /v1/agent/template/{id} - Run a template (security-audit, content-analyzer, data-processor, domain-recon, hash-verify) - GET /v1/agent/history - Retrieve past agent runs from auto-stored memory ## Pricing Credit-based. 1 credit = 1 simple API call. Plans from $9/1K credits to $1,999/1M credits. 500 free credits on signup. Memory APIs (set, get, search, list, delete, stats) are FREE - 0 credits. ## Quickstart (10 tools for 80% of tasks) GET /v1/quickstart — returns the 10 highest-value tools with examples. Includes 2 free memory tools. Demo key: sk-slop-demo-key-12345678. ## Cost preview (dry-run mode) Add preview: true or dry_run: true to any POST body. Returns estimated credits, estimated USD cost, and whether you can afford it — without executing. Works on both /v1/{slug} and /v1/tasks/run. ## Error responses All errors return JSON: { "error": { "code": "error_code", "message": "human-readable" } }. HTTP status codes: 401 (no/invalid key), 403 (scope denied), 422 (missing required fields), 429 (rate limited), 402 (insufficient credits). Credits are NEVER charged on errors. Error responses include helpful hints (e.g., demo key, signup URL). ## Standard response shape Every successful response: { "ok": true, "": ..., "_engine": "real"|"llm", "guarantees": { "schema_valid": true, "validated": true } }. Headers always include: X-Credits-Used, X-Latency-Ms, X-Request-Id, X-Engine, X-Output-Hash. ## Input validation All endpoints validate required input fields before execution. Missing fields return 422 with specific field errors and the expected input schema. Credits are NOT charged on validation failures. ## Scheduled execution POST /v1/schedules to create a recurring job. Intervals: 1m, 5m, 15m, 30m, 1h, 6h, 12h, 1d, 7d. Supports tools, pipes, and templates. GET /v1/schedules to list, DELETE /v1/schedules/:id to remove. Optional max_runs limit. Transforms Slopshop from request-response into always-on agent infrastructure. ## Universal memory — free, persistent, cross-everything Memory that works across ANY LLM (Claude, GPT, Grok, Llama, Gemini, DeepSeek, Mistral), ANY device, ANY session. Store from one model, retrieve from another. Persists forever in SQLite. Core memory APIs cost 0 credits: memory-set, memory-get, memory-search, memory-list, memory-delete, memory-stats, memory-namespace-list, counter-get, memory-vector-search. Always free. ## Not a wrapper - real compute 925 compute handlers use Node.js built-ins (crypto, math, Buffer) with zero external dependencies — all benchmarked for correctness, null safety, and <1ms p95 latency with 100% pass rate. 22 network APIs use built-in dns/http/tls modules. 20 memory APIs use SQLite persistence (atomic writes, concurrent-safe, 76 tables). 15 execution APIs use vm.createContext sandbox. 1,274 REST endpoints total across 78 categories. Every response includes _engine: "real" to prove data was actually processed. LLM APIs are clearly marked _engine: "llm". ## Trust & Verification Every response includes _engine: "real" and X-Output-Hash (SHA-256). Current model: Server-side execution with hash-based audit trails. Output hashes prove consistency and detect transit tampering. Honest limitation: The trust source is Slopshop's server. _engine: "real" and X-Output-Hash are claims made by our server — they do not cryptographically prove that specific code executed. You are trusting Slopshop. Mitigation: Self-host to verify (npm install slopshop && node server-v2.js). Run the same code locally, compare outputs. Roadmap: TEE attestation (Intel SGX / AWS Nitro Enclaves) for hardware-attested execution, reproducible builds for source verification, ZK proofs for high-value ops (currently ~100x overhead, not practical for general compute). Merkle proofs available for Army deployments (POST /v1/proof/merkle). ## Production-grade reliability Circuit breakers, auto-retry with backoff, rate limiting per key, distributed locks. Credits checked before execution (never runs without budget). Every call logged to audit trail. Agent runs stored with full step trace, replayable via GET /v1/agent/history. ## Pipes (pre-built workflows) 19 pre-built multi-step workflows. POST /v1/pipes/{slug} runs all steps in sequence. Examples: website-report (5 tools, 15cr), content-machine (3 tools, 35cr), security-audit, domain-recon, data-clean. GET /v1/pipes to list all. ## Agent-to-agent credit transfers Agents can transfer credits between accounts for agent-to-agent commerce. Enables internal agent economies. ## Task abstraction (recommended for agents) POST /v1/tasks/run with { "task": "extract_structured_data", "text": "...", "schema": {...} }. Maps high-level tasks to best tool. Response includes ok, output, meta (confidence, cost, latency), and guarantees (schema_valid, validated). GET /v1/tasks lists all available tasks. For natural language, use POST /v1/agent/run instead. Available tasks: extract_structured_data, summarize, classify, analyze_code, code_review, fix_code, generate_code, fetch_webpage, detect_tech_stack, check_ssl, dns_lookup, hash_sha256, hash_sha512, validate_json, word_count, token_count, generate_uuid, security_audit. ## Live benchmarks GET /v1/benchmarks returns real success rates, latency, and cost per API from production traffic. Updated in real-time from audit logs. GET /v1/tools/:slug/stats returns reliability stats for a specific tool. ## Response caching Identical compute-tier requests are automatically cached for 5 minutes. Cache hits cost 0 credits and return X-Cache: HIT header. Only deterministic compute APIs are cached (not LLM or network calls). This means agents calling the same hash/parse/transform twice pay nothing on the second call. ## Agent Mode (enhanced responses for AI agents) Add mode: "agent" (or "grok") to any POST body, or set X-Agent-Mode header. Response includes: suggestions (next tools to call), cache_fingerprint (for semantic reuse), cost_breakdown, and auto-persisted memory (free). Works with any AI provider. ## Deterministic mode Add mode: "deterministic" to any request for reproducible outputs. Same input → same output. Best for testing and CI pipelines. ## Debug traces Add trace: true to any request body or set X-Debug-Trace header. Response includes a trace array showing every step: received → credits_checked → executed → validated. ## Response guarantees Every response includes guarantees: { schema_valid: true, validated: true, fallback_used: false }. Agents can trust outputs without additional validation. ## Integration guides (14 providers) - Claude/Anthropic: https://slopshop.gg/integrate-claude (MCP, tool_use) - GPT/OpenAI: https://slopshop.gg/integrate-openai (function_calling) - Grok/xAI: https://slopshop.gg/integrate-grok (Agent Mode) - Gemini/Google: https://slopshop.gg/integrate-gemini (Google AI tools) - DeepSeek: https://slopshop.gg/integrate-deepseek (OpenAI-compatible) - Llama/Ollama: https://slopshop.gg/integrate-llama (open-source, local) - Mistral: https://slopshop.gg/integrate-mistral (Mistral AI tools) - Groq: https://slopshop.gg/integrate-groq (fast inference) - LangChain: https://slopshop.gg/integrate-langchain (StructuredTool, LCEL) - CrewAI: https://slopshop.gg/integrate-crewai (multi-agent) - AutoGen: https://slopshop.gg/integrate-autogen (Microsoft agents) - Cohere: https://slopshop.gg/integrate-cohere (Command tool_use) - Perplexity: https://slopshop.gg/integrate-perplexity (search + compute) - Together AI: https://slopshop.gg/integrate-together (hosted open models) Works with ANY OpenAI-compatible provider via the standard function_calling format. ## Curated tool list for agents GET /v1/mcp/recommended — returns ~40 highest-value tools with schemas. Ideal for MCP servers or agent tool discovery. Includes all free memory APIs, top compute tools, sensing, and execution. ## Scoped API keys (RBAC) POST /v1/auth/create-scoped-key creates keys limited by tier/category. Scopes: compute, network, llm, memory, execute, or * (all). Optional credit cap per key. GET /v1/auth/keys lists all keys. DELETE /v1/auth/keys/:key revokes. Scope violations return 403. ## Auto-fallback routing Agent execution automatically retries failed tools with alternatives. crypto-hash-sha256 falls back to sha512/md5. sense-url-content falls back to meta/links. Fallback results include fallback_used: true. ## SSE streaming for agent/run Add stream: true to POST /v1/agent/run. Returns Server-Sent Events with planning, step, and complete events. Agents see results as they execute. ## Credit transfer POST /v1/credits/transfer with to_key and amount. Agent-to-agent credit commerce. Atomic, audited. ## Python code execution POST /v1/exec-python with { "code": "print(2+2)" }. Runs Python in a subprocess with 30s timeout. Supports standard library (json, math, datetime, re, hashlib, base64, urllib). Returns stdout, stderr, execution status. 5 credits. ## Semantic memory search (vector-like) POST /v1/memory-vector-search with { "namespace": "...", "query": "search terms" }. Scores memories by text similarity against keys, values, and tags. Returns ranked results by relevance. FREE - 0 credits. ## File storage POST /v1/files/upload (base64 content + filename). GET /v1/files/:id to download. GET /v1/files to list. Persistent blob storage for agents. ## Statistics tools (7 tools) stats-mean, stats-median, stats-stddev, stats-percentile, stats-correlation, stats-histogram, stats-summary. All 1 credit, pure compute. Pass { "data": [1,2,3,4,5] }. stats-summary returns count, min, max, mean, median, stddev, variance, p25, p75 in one call. ## Idempotency Add Idempotency-Key header to any request. Duplicate requests return cached results (24h TTL, 0 credits). ## Discovery endpoints GET /v1/tools/:slug/related — find similar tools by category/prefix GET /v1/tools/:slug/try — get a ready-to-run curl command with demo key POST /v1/cost-estimate — estimate total credits for a list of tool slugs GET /v1/stats/public — total calls, users, top tools (real-time from audit log) GET /v1/badge.svg — embeddable "powered by slopshop" badge ## Self-hosting Fully self-hostable. Clone the repo, npm install, node server-v2.js. Pure-compute APIs (925) run with zero external dependencies. Network APIs use Node.js built-in modules. LLM APIs need your own Anthropic/OpenAI key. Docker and fly.toml included. ## Limitations (when NOT to use Slopshop) - Not a database: memory/SQLite is great for agent state, not for storing millions of records. - LLM-backed tools depend on external providers (Anthropic/OpenAI) — latency is 1-5s vs <1ms p95 for pure compute tools. - No OAuth/SSO yet — auth is API-key-based only. - Python execution is sandboxed subprocess with 30s timeout — not for long-running compute jobs. - Self-hosted instances share no data with slopshop.gg (memory, keys, credits are all local). - No SLA guarantee yet — uptime target is 99.9% but not contractually guaranteed. ## Eval framework — test agents against benchmarks POST /v1/eval/run with { "agent_id": "...", "benchmark": "...", "inputs": [...] }. Run your agent against a named benchmark and score results. GET /v1/eval/history — retrieve all past evaluation runs. ## Auto-optimizer — cheapest and fastest tool selection POST /v1/optimize with { "task": "...", "constraints": { "max_credits": ..., "max_latency_ms": ... } }. Returns the optimal tool or tool chain under your constraints. ## Agent Chaining (Infinite Consciousness) Create infinite agent-to-agent chains where output from one agent becomes input for the next. Supports loop mode, pause/resume, and context passing between steps. POST /v1/chain/create — Create agent chain with steps and loop mode POST /v1/chain/advance — Advance to next step with context passing POST /v1/chain/queue — Queue prompts for overnight batch GET /v1/chain/status/:id — Check chain status POST /v1/chain/pause/:id — Pause running chain POST /v1/chain/resume/:id — Resume paused chain GET /v1/chain/list — List user's chains Example — create a looping research chain: curl -X POST https://slopshop.gg/v1/chain/create \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"name":"research-loop","loop":true,"steps":[{"agent":"claude","prompt":"Research AI news"},{"agent":"grok","prompt":"Critique and improve"}]}' Example — advance to next step: curl -X POST https://slopshop.gg/v1/chain/advance \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"chain_id":"CHAIN_ID","context":{"previous_output":"AI news summary from step 1"}}' Example — pause and resume: curl -X POST https://slopshop.gg/v1/chain/pause/CHAIN_ID \ -H "Authorization: Bearer $KEY" curl -X POST https://slopshop.gg/v1/chain/resume/CHAIN_ID \ -H "Authorization: Bearer $KEY" Example — list chains: curl https://slopshop.gg/v1/chain/list \ -H "Authorization: Bearer $KEY" ## Prompt Queue Queue prompts for deferred or overnight batch execution at any frequency. Set schedule and frequency for automatic recurring jobs. POST /v1/chain/queue — Queue prompts for deferred execution Example — daily batch job: curl -X POST https://slopshop.gg/v1/chain/queue \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"prompts":[{"prompt":"Analyze competitors","agent":"claude"}],"frequency":"daily","schedule":"2026-03-28T09:00:00Z"}' Example — one-time deferred job: curl -X POST https://slopshop.gg/v1/chain/queue \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"prompts":[{"prompt":"Generate weekly analytics report","agent":"claude"},{"prompt":"Summarize findings","agent":"grok"}],"frequency":"once","schedule":"2026-03-28T03:00:00Z"}' ## Template Marketplace Publish, browse, fork, and rate agent templates. Share workflows with the community and discover templates from other builders. POST /v1/templates/publish — Publish template to marketplace GET /v1/templates/browse — Browse marketplace (supports ?tag= filter) POST /v1/templates/fork/:id — Fork a template into your account POST /v1/templates/rate/:id — Rate 1-5 with optional review Example — publish a template: curl -X POST https://slopshop.gg/v1/templates/publish \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"name":"SEO Content Pipeline","description":"Generate SEO-optimized blog posts","steps":[{"api":"llm-blog-outline","input":{"topic":"{{topic}}"}},{"api":"llm-blog-draft"},{"api":"text-readability-score"}],"tags":["seo","content"]}' Example — browse templates: curl https://slopshop.gg/v1/templates/browse \ -H "Authorization: Bearer $KEY" Example — fork a template: curl -X POST https://slopshop.gg/v1/templates/fork/TEMPLATE_ID \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"name":"My Custom SEO Pipeline"}' Example — rate a template: curl -X POST https://slopshop.gg/v1/templates/rate/TEMPLATE_ID \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"rating":5,"review":"Excellent pipeline, saved me hours"}' ## Agent Evaluations Run structured evaluations with test cases, compare agents head-to-head, and view the public leaderboard. POST /v1/eval/run — Run eval with test cases against an agent GET /v1/eval/leaderboard — Public leaderboard by eval score POST /v1/eval/compare — Compare two agents on same test cases GET /v1/eval/report/:id — Detailed report with per-case results Example — run evaluation: curl -X POST https://slopshop.gg/v1/eval/run \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"my-research-agent","test_cases":[{"input":"Summarize quantum computing","expected_keywords":["qubit","superposition","entanglement"]},{"input":"Explain RSA encryption","expected_keywords":["prime","modular","public key"]}]}' Example — compare two agents: curl -X POST https://slopshop.gg/v1/eval/compare \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"agent_a":"research-v1","agent_b":"research-v2","test_cases":[{"input":"What is CRISPR?"}]}' Example — view leaderboard: curl https://slopshop.gg/v1/eval/leaderboard \ -H "Authorization: Bearer $KEY" Example — get detailed report: curl https://slopshop.gg/v1/eval/report/EVAL_ID \ -H "Authorization: Bearer $KEY" ## Credit Market Peer-to-peer credit trading. Offer your unused credits for sale at your price, or buy from other users at market rates. POST /v1/credits/offer — List credits for sale on the market POST /v1/credits/buy-offer/:id — Buy credits from an existing offer GET /v1/credits/market — Browse all available credit offers Example — offer credits for sale: curl -X POST https://slopshop.gg/v1/credits/offer \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"amount":500,"price_per_credit":0.008,"currency":"USD"}' Example — buy from an offer: curl -X POST https://slopshop.gg/v1/credits/buy-offer/OFFER_ID \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"amount":200}' Example — browse market: curl https://slopshop.gg/v1/credits/market \ -H "Authorization: Bearer $KEY" ## Agent Wallets Create sub-wallets for individual agents with their own budgets. Control per-agent spending and transfer credits between wallets. POST /v1/wallet/create — Create agent sub-wallet with budget POST /v1/wallet/transfer — Transfer credits between wallets Example — create a sub-wallet: curl -X POST https://slopshop.gg/v1/wallet/create \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"agent_name":"research-bot","budget":500,"auto_refill":true,"refill_threshold":50,"refill_amount":200}' Example — transfer between wallets: curl -X POST https://slopshop.gg/v1/wallet/transfer \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"from_wallet":"main","to_wallet":"research-bot","amount":100}' ## Agent Reputation Upvote or downvote agents based on quality. Public reputation leaderboard for discovering the best agents. POST /v1/reputation/vote — Upvote or downvote an agent GET /v1/reputation/leaderboard — Top agents by reputation score Example — vote on an agent: curl -X POST https://slopshop.gg/v1/reputation/vote \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"research-bot-v2","vote":"up","reason":"Consistently high-quality output"}' Example — view leaderboard: curl https://slopshop.gg/v1/reputation/leaderboard \ -H "Authorization: Bearer $KEY" ## Replay System Save and replay entire swarm runs for debugging, auditing, or demonstration. Captures every step and agent decision. POST /v1/replay/save — Save a swarm run for later replay GET /v1/replay/:id — Get full replay data with all steps Example — save a swarm run: curl -X POST https://slopshop.gg/v1/replay/save \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d '{"run_id":"RUN_ID","name":"Q1 research swarm","tags":["research","quarterly"]}' Example — retrieve replay: curl https://slopshop.gg/v1/replay/REPLAY_ID \ -H "Authorization: Bearer $KEY" ## Local Compute Enhancement Run computations locally for speed and privacy, then enhance results with Slopshop cloud tools. Combine local processing with cloud-powered analysis and LLM insights. Example workflow: LOCAL_HASH=$(sha256sum myfile.txt | cut -d' ' -f1) curl -X POST https://slopshop.gg/v1/agent/run \ -H "Authorization: Bearer $KEY" \ -H "Content-Type: application/json" \ -d "{\"task\":\"I computed SHA256 hash $LOCAL_HASH for myfile.txt. Verify format and store in memory.\",\"store_result\":true}" ## Swarm Visualizer Interactive real-time visualization of agent swarms, chains, and workflows. Access at https://slopshop.gg/visualizer. Shows agent nodes with status indicators, data flow arrows, credit usage per step, and a timeline view of execution history. Reads from active chains, hive workspaces, and army deployments. Updates in real time via SSE. ## Share My Army — Public Links Share your army deployments with public links that auto-generate playground forks. Others can view, fork, and remix your swarm configurations. - POST /v1/army/share — Create a public share link for an army deployment - GET /v1/army/shared/:id — View a shared army (public, no auth required) curl -X POST https://slopshop.gg/v1/army/share \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"deployment_id":"dep_123","name":"My Research Swarm","description":"10-agent research pipeline"}' ## Referral Program — Invite Friends, Earn Credits Invite friends to Slopshop. When 3 friends sign up, you get 5,000 bonus credits. - POST /v1/referral/invite — Send referral invites (up to 10 emails) - GET /v1/referral/status — Check referral progress - POST /v1/referral/redeem — Claim bonus when 3+ friends signed up curl -X POST https://slopshop.gg/v1/referral/invite \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"emails":["friend1@example.com","friend2@example.com","friend3@example.com"]}' ## "Built with Slopshop" Badge Embeddable SVG badge for your projects. Customizable style and color. - GET /v1/badge/built-with — Returns SVG badge (supports ?style=flat&color=ff3333) - GET /v1/badge.svg — Powered by Slopshop badge Embed: `Built with Slopshop` ## Agent Standup Email Digest Configure daily email summaries of your HIVE workspace activity, agent runs, credit usage, and standup submissions. - POST /v1/standup/email-digest — Configure email digest (daily/weekly) curl -X POST https://slopshop.gg/v1/standup/email-digest \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"email":"you@example.com","frequency":"daily","hive_id":"HIVE_ID"}' ## Auto-Save Playground Runs Every playground run can be auto-saved as a reusable template. Build your library of working examples. - POST /v1/playground/auto-save — Save a playground run as template curl -X POST https://slopshop.gg/v1/playground/auto-save \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"slug":"crypto-hash-sha256","input":{"text":"hello"},"result":{"hash":"2cf24dba..."},"name":"SHA256 Demo"}' ## Memory Health Score Dashboard showing the health and utilization of your memory graph. Includes grade (A-D), key counts, size, recommendations. - GET /v1/memory/health — Get memory health score and recommendations (supports ?namespace=) curl https://slopshop.gg/v1/memory/health \ -H "Authorization: Bearer YOUR_KEY" ## Clone Last Successful Swarm One-click clone of your last successful army deployment. Get the config back ready to re-deploy. - POST /v1/army/clone-last — Clone last successful swarm configuration curl -X POST https://slopshop.gg/v1/army/clone-last \ -H "Authorization: Bearer YOUR_KEY" ## Credit Expiration Warning + Auto-Topup Monitor credit balance, get low-balance warnings, and configure auto-topup. - GET /v1/credits/expiration — Check balance, warnings, and auto-topup status - POST /v1/credits/auto-reload — Configure auto-topup (existing endpoint) curl https://slopshop.gg/v1/credits/expiration \ -H "Authorization: Bearer YOUR_KEY" ## Memory Graph Leaderboard Public leaderboard ranking the most valuable and complex memory graphs on the platform. - GET /v1/memory/leaderboard — View public leaderboard (no auth required) curl https://slopshop.gg/v1/memory/leaderboard ## Multi-LLM Smart Router Intelligent routing across LLM providers (Anthropic, OpenAI, Grok, DeepSeek, Groq) with cost + quality scoring. Constraint-based selection. - POST /v1/router/smart — Route a task to the optimal LLM provider curl -X POST https://slopshop.gg/v1/router/smart \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"task":"Summarize this document","prefer":"anthropic","max_cost":3.0}' ## Knowledge Graph Auto-Discovery Automatically discover entities and relationships from your existing memory data, building a knowledge graph without manual entry. - POST /v1/knowledge/auto-discover — Scan memory namespace and extract entities + relationships curl -X POST https://slopshop.gg/v1/knowledge/auto-discover \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"namespace":"default"}' ## Auto-Merkle Proof Generation Generate Merkle trees and proofs for any set of data items. Batch verification of task outputs. Note: individual hashes are server-generated — Merkle proofs verify batch membership, but the same trust model applies (see Trust & Verification section). - POST /v1/proof/merkle — Generate Merkle tree with root hash and proof curl -X POST https://slopshop.gg/v1/proof/merkle \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"data":["task1_output","task2_output","task3_output"]}' ## Optimize Swarm for Cost Analyze a swarm's tool usage and suggest cheaper alternatives to reduce cost by a target percentage. - POST /v1/optimize/swarm — Optimize swarm configuration for cost reduction curl -X POST https://slopshop.gg/v1/optimize/swarm \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"steps":[{"slug":"llm-summarize"},{"slug":"sense-url-content"},{"slug":"text-word-count"}],"target_reduction":40}' ## Cost Optimizer (Multi-LLM) Analyze your workload across all LLM providers and find the cheapest option that meets quality requirements. - POST /v1/optimize/cost — Get cost optimization recommendations curl -X POST https://slopshop.gg/v1/optimize/cost \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"monthly_budget":100,"tasks_per_day":500}' ## Grok-Specific MCP Templates Curated tool set optimized for Grok/xAI agent integration with setup instructions. - GET /v1/mcp/grok-templates — Get Grok-optimized tool list with MCP config curl https://slopshop.gg/v1/mcp/grok-templates ## Agent of the Week Spotlight Weekly recognition of the most active and highest-performing agent on the platform. - GET /v1/spotlight/agent-of-the-week — View current spotlight curl https://slopshop.gg/v1/spotlight/agent-of-the-week ## Ambassador Program Apply to become a Slopshop ambassador. Benefits include 50K free credits/month, early access, and revenue share. - POST /v1/ambassador/apply — Submit ambassador application - GET /v1/ambassador/status — Check application status curl -X POST https://slopshop.gg/v1/ambassador/apply \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"Your Name","platform":"twitter","audience_size":10000,"why":"I build AI agent tutorials"}' ## CLI Scaffold + Doctor Reference for the CLI scaffolding command and health check. - GET /v1/cli/init-template — Get scaffold template for `slop init my-project` - GET /v1/cli/doctor — Run health check on your Slopshop connection curl https://slopshop.gg/v1/cli/doctor \ -H "Authorization: Bearer YOUR_KEY" ## OpenAPI to MCP Auto-Generator Convert any OpenAPI 3.x spec into an MCP-compatible tool manifest automatically. - POST /v1/mcp/generate-from-openapi — Generate MCP server config from OpenAPI spec curl -X POST https://slopshop.gg/v1/mcp/generate-from-openapi \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"openapi_spec":{"openapi":"3.0.0","info":{"title":"My API","version":"1.0"},"paths":{"/users":{"get":{"summary":"List users"}}}}}' ## Integrations Ecosystem (VS Code, Terraform, Pulumi, K8s) Reference for all platform integrations including coming-soon items. - GET /v1/integrations/ecosystem — Full ecosystem listing with statuses curl https://slopshop.gg/v1/integrations/ecosystem ## Enterprise Capabilities Multi-region, SOC 2 path, p99 latency guarantees, air-gapped version, open-source core, self-host/cloud hybrid sync, Kubernetes manifests. - GET /v1/enterprise/capabilities — Full enterprise feature listing curl https://slopshop.gg/v1/enterprise/capabilities ## Case Studies Real-world use cases of Slopshop in production environments. - GET /v1/case-studies — Browse case studies curl https://slopshop.gg/v1/case-studies ## "Replace Redis + Zapier" Comparison See why teams replace Redis, Zapier, and Cron with a single Slopshop instance: https://slopshop.gg/why.html Detailed comparison: https://slopshop.gg/compare.html ## Browser/Desktop Primitives (v4.0) Real-time agent monitoring and desktop IDE integration. - GET /v1/visualizer/stream — SSE stream of live agent activity, army deployments, hive messages - POST /v1/mcp/bootstrap — Auto-configure MCP for Claude Desktop, Cursor, or other IDEs ## Memory 2.0 (v4.0) Graph queries, auto-summarization, and snapshot pinning. All free (0 credits). - POST /v1/memory/graph-query — Query memory as a knowledge graph with semantic scoring and traversal - POST /v1/memory/auto-summarize — Auto-summarize large namespaces or key groups - POST /v1/memory/snapshot — Take point-in-time snapshot of a namespace, optionally pin for permanent storage - GET /v1/memory/snapshots — List all snapshots ## Grok-Specific Features (v4.0) Dedicated Grok integration for optimization, critique, and autonomous orchestration. Requires XAI_API_KEY. - POST /v1/grok/optimize ��� Pass prompts, code, or workflows to Grok for cost/performance optimization - POST /v1/grok/critique — Submit content for Grok's critical analysis with structured feedback - POST /v1/grok/overlord — Grok autonomously drives multi-LLM chains, selecting models per subtask ## Safety & Guardrails (v4.0) Production safety primitives for agent deployments. - POST /v1/sandbox/execute — Run untrusted code in isolated vm.createContext with timeout enforcement - POST /v1/reputation/slash — Slash underperforming agents in army deployments - GET /v1/reputation/ledger — View global reputation leaderboard (Merkle-verified) - POST /v1/chaos/test — Inject faults (network, latency, agent-drop) into army deployments ## Marketplace (v4.0) Publish, discover, and trade templates, plugins, and compute capacity. - GET /v1/marketplace/templates — Browse available agent templates - POST /v1/marketplace/invoke — Invoke a template with parameters - POST /v1/bounties/post — Post bounties for agent work with credit rewards - POST /v1/bounties/claim — Claim an open bounty - GET /v1/bounties/list — Browse open bounties ## Agent Templates (v4.0) Pre-built agent configurations for common workflows. - POST /v1/templates/create — Create custom agent templates with chain steps, model preferences, and memory namespaces - POST /v1/templates/run — Run a named template (research-swarm, content-machine, security-audit, data-pipeline) ## Voice I/O for Agents (v4.0.0) Real-time voice input and output for agent interactions. Stream audio to agents and receive spoken responses. TTS and STT built in. - POST /v1/voice/transcribe — Transcribe audio (base64 or URL) to text using Whisper-compatible STT - POST /v1/voice/synthesize — Convert text to speech audio (base64 WAV/MP3), multiple voices - POST /v1/voice/session/create — Create a live voice session for real-time agent conversation - POST /v1/voice/session/:id/send — Stream audio chunk to an active voice session - GET /v1/voice/session/:id/stream — SSE stream of transcribed text and agent responses curl -X POST https://slopshop.gg/v1/voice/transcribe \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"audio_url":"https://example.com/recording.wav","language":"en"}' curl -X POST https://slopshop.gg/v1/voice/synthesize \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"text":"Hello, I am your research agent. Analysis complete.","voice":"neutral","format":"mp3"}' curl -X POST https://slopshop.gg/v1/voice/session/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"research-bot","system_prompt":"You are a helpful research assistant","voice":"neutral"}' ## A2A — Agent-to-Agent Protocol (v4.0.0) Google A2A interop. Expose Slopshop agents as A2A-compatible services and call external A2A agents. Discover, negotiate capabilities, and exchange tasks across platforms. - GET /v1/a2a/.well-known/agent.json — A2A agent card (public discovery endpoint, no auth) - POST /v1/a2a/tasks/send — Send a task to an A2A-compatible agent (local or remote) - GET /v1/a2a/tasks/:id — Get task status and result - POST /v1/a2a/tasks/:id/cancel — Cancel a running A2A task - POST /v1/a2a/register — Register an external A2A agent for discovery - GET /v1/a2a/agents — List all registered A2A agents (local + remote) curl https://slopshop.gg/v1/a2a/.well-known/agent.json curl -X POST https://slopshop.gg/v1/a2a/tasks/send \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_url":"https://other-platform.com/a2a","task":{"type":"research","input":"Latest trends in AI safety"}}' curl -X POST https://slopshop.gg/v1/a2a/register \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"external-researcher","url":"https://other-platform.com/a2a","capabilities":["research","summarize"]}' curl https://slopshop.gg/v1/a2a/agents \ -H "Authorization: Bearer YOUR_KEY" ## Swarm Snapshots (v4.0.0) Point-in-time snapshots of entire swarm state — agent positions, memory, chain progress, credit balances. Restore or fork swarms from any snapshot. - POST /v1/swarm/snapshot — Capture full swarm state (agents, memory, chains, credits) - GET /v1/swarm/snapshots — List all snapshots with metadata and size - POST /v1/swarm/snapshot/:id/restore — Restore swarm to a previous snapshot state - POST /v1/swarm/snapshot/:id/fork — Fork a new swarm from a snapshot (new IDs, same config) curl -X POST https://slopshop.gg/v1/swarm/snapshot \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"swarm_id":"research-team","name":"pre-experiment-baseline","tags":["baseline","v1"]}' curl https://slopshop.gg/v1/swarm/snapshots \ -H "Authorization: Bearer YOUR_KEY" curl -X POST https://slopshop.gg/v1/swarm/snapshot/SNAP_ID/restore \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"confirm":true}' curl -X POST https://slopshop.gg/v1/swarm/snapshot/SNAP_ID/fork \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"experiment-branch-a"}' ## Swarm Budgets (v4.0.0) Per-swarm credit budgets with enforcement, alerts, and automatic shutdown. Control spend at the swarm level, not just per-agent. - POST /v1/swarm/budget/set — Set credit budget for a swarm (hard cap or soft warning) - GET /v1/swarm/budget/:swarm_id — Get current budget status, burn rate, and projected exhaustion - POST /v1/swarm/budget/alert — Configure budget alerts (webhook, email, or memory-set) - POST /v1/swarm/budget/adjust — Adjust budget mid-run without stopping the swarm curl -X POST https://slopshop.gg/v1/swarm/budget/set \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"swarm_id":"research-team","budget":5000,"mode":"hard","on_exhaust":"pause"}' curl https://slopshop.gg/v1/swarm/budget/research-team \ -H "Authorization: Bearer YOUR_KEY" curl -X POST https://slopshop.gg/v1/swarm/budget/alert \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"swarm_id":"research-team","threshold_pct":80,"channel":"webhook","url":"https://example.com/alerts"}' curl -X POST https://slopshop.gg/v1/swarm/budget/adjust \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"swarm_id":"research-team","new_budget":10000,"reason":"scaling up experiment"}' ## OAuth Connectors (v4.0) Connect external services via OAuth. Supports GitHub, Slack, Linear, Notion, and any OAuth2 provider. All tokens encrypted with AES-256-GCM. Auto-rotated nightly. - POST /v1/connectors/config — Configure an OAuth connector (toolkit, client_id, client_secret, scopes, auth_url, token_url) - GET /v1/connectors/list — List all configured connectors - GET /v1/connectors/connect/:toolkit — Start OAuth flow (returns redirect URL) - DELETE /v1/connectors/:id — Remove a connector and revoke tokens curl -X POST https://slopshop.gg/v1/connectors/config \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"toolkit":"github","client_id":"YOUR_GITHUB_APP_ID","client_secret":"YOUR_SECRET","scopes":["repo"],"auth_url":"https://github.com/login/oauth/authorize","token_url":"https://github.com/login/oauth/access_token"}' ## Webhook Triggers (v4.0) Define triggers that fire agent workflows when external events arrive via webhook. - POST /v1/triggers/create — Create a trigger (name, source, event, action) - POST /v1/triggers/webhook/:id — Webhook receiver URL (give to external services) - GET /v1/triggers/list — List all configured triggers curl -X POST https://slopshop.gg/v1/triggers/create \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"on-push","source":"github","event":"push","action":{"chain_id":"deploy-pipeline"}}' ## Audit Export (v4.0) Export full audit trail for compliance, debugging, or SOC2 evidence collection. - GET /v1/audit/export — Export timestamped audit entries with endpoint, credits, latency, response hashes curl https://slopshop.gg/v1/audit/export \ -H "Authorization: Bearer YOUR_KEY" ## Schema Import (v4.0) Bulk-import tool schemas for self-hosted deployments or custom tool registration. - POST /v1/import/schemas — Import an array of tool schemas (slug, name, description, input, output) curl -X POST https://slopshop.gg/v1/import/schemas \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{"schemas":[{"slug":"custom-tool","name":"Custom Tool","description":"My custom handler","input":{"type":"object","properties":{"text":{"type":"string"}}},"output":{"type":"object","properties":{"result":{"type":"string"}}}}]}' ## Full API catalog See https://slopshop.gg/llms-full.txt for every API with slug, description, and credit cost. ## Contact Website: https://slopshop.gg Docs: https://slopshop.gg/docs GitHub: https://github.com/slopshop/slopshop npm: https://www.npmjs.com/package/slopshop X/Twitter: @slopshopgg