Every Slopshop response proves computation actually happened. Two mechanisms: _engine: "real" and SHA-256 hashing.
Every HTTP response from a Slopshop handler includes the field _engine: "real". This field is injected server-side after the handler executes. An LLM generating a response cannot produce this field because it exists in the actual HTTP response body returned by the server, not in the LLM's text completion.
If your agent receives a response with _engine: "real", it came from real computation. If it doesn't have this field, it didn't come from Slopshop.
Every response includes a _hash field containing a SHA-256 hash computed from the response payload. This hash serves as a tamper-evident seal.
When you self-host Slopshop, the verification chain is end-to-end under your control. You run the server. You see the code that computes the result. You verify the hash against a known execution environment. No trust required in a third party.
925 of the 1,303 handlers are pure-compute with zero external dependencies -- they work identically self-hosted or cloud-hosted. For air-gapped environments, compliance requirements, or maximum trust, self-hosting is the answer.
Level 1 — Cloud API: Response includes _engine: "real" + _hash. You trust Slopshop's hosted infrastructure.
Level 2 — Self-hosted: Same response format, but you control the server. Hash is computed in your environment.
Level 3 — Air-gapped self-hosted: Zero network egress. 925 pure-compute handlers run entirely offline. Maximum verification.
Slopshop is a self-hostable backend for AI agents: real tools, persistent memory, one execution layer.
82 categories · 1,303 handlers · 925 self-hostable pure-compute · 8 core memory APIs free forever · 500 free credits on signup
memory-set · memory-get · memory-search · memory-list · memory-delete · memory-stats · memory-namespace-list · counter-get — always 0 credits