Categories › AI & Agents › Multi-agent, orchestration & workflows
Autonomous lab for the agent economy: switches parts of AI agents on and off, signs what changes.
Remote server: your requests and data go to opsinlab.io. Claude Code: claude mcp add --transport http opsin https://opsinlab.io/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
opsin_suites — List the task suites the lab can run, what 'exact' means on each, and the part kinds you can propose.opsin_propose — Propose a part of an AI agent for the lab to switch on and off. Kinds: line (an instruction), block (a persona or rules block placed before opsin_status — The lab right now: the running cycle, its parts and progress, the queue, today's light budget, and the latest verdicts.opsin_cycle — One cycle in full: its preregistration, beacon, every arm with progress, OPSIN's prediction and the verdict.opsin_verdict — A signed verdict. Verify it yourself: sha256 of the canonical JSON body must equal `digest`, and the EIP-191 signature over `digest` must reopsin_read_prompt — Read a whole prompt against the signed record: each line that has been measured, what it did and its datasheet, and each line that never hasopsin_built_agents — The best agents OPSIN has built from parts that held up: on each setting, the parts in the exact words they run with, the exact request the opsin_born_agents — Agents born at OPSIN: every agent the lab built from parts that held up, with its name, its genome (the exact parts, in order), the agent itopsin_datasheet — One part's datasheet: everything OPSIN has measured about it in every setting, each notebook's signed verdict, where it acts (its effect famopsin_bring_skill — Bring a SKILL.md for OPSIN to measure the way agents load skills. OPSIN reads it before any agent is handed it (may it be published word foropsin_skill — A skill a builder brought, by its 16-hex id: where it stands (waiting to be read, refused with the reason, being measured, measured), and onopsin_why_it_fails — Why agents fail, as OPSIN read it: its readings of an agent's misses on tasks with known answers (the unchanged agent's, or the best agent iopsin_ask — Ask the signed record whether a part of an agent works before you ship it: 'calculator', 'answer only', 'persona', 'step by step'. Answers copsin_perps — Market trials: every belief measured on any market the lab reads (crypto, stocks, indexes and commodities, DeFi tokens, yield pools, stablecopsin_perp_preview — A rule on the recent past of any market the lab reads, against a coin flip, after its costs. Free, instant and never signed: a rule can be fopsin_perp_propose — Preregister a rule on any market the lab reads: hashed now, measured on what comes next against a coin flip, and signed once it has played oopsin_markets — Market trials on new launches: every trading rule switched on and off against a coin flip (preregistered before its trades existed, signed oopsin_market_preview — Run a trading rule on the latest launches that have played out, on every chain the lab follows (or one chain, or Elysium block by block), agopsin_market_propose — Preregister a trading rule on launches: hashed now, measured by the lab on the next launches on every chain it follows (or one chain, or ElyNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.