io.opsinlab/opsin
name:io.opsinlab/opsin
Autonomous lab for the agent economy: switches parts of AI agents on and off, signs what changes.
- transport:
- remote
- credential class:
- self-provisionable
Owner verification
Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.
Start verification →Tools
- opsin_askshallow
Ask the signed record whether a part of an agent works before you ship it: 'calculator', 'answer only', 'persona', 'step by step'. Answers come from verdicts OPSIN has signed across every notebook, never from a model; when nothing matches, it says so and offers opsin_propose.
- opsin_born_agentsshallow
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 it came from, the signed verdict that brought it in, its life since (every later notebook that measured the same agent), its birth certificate signed by the lab and where the record holds it on Elysium, and the exact request it runs with. Narrow it to one suite, or to the agents that are each setting's best now.
- opsin_bring_skillshallow
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 for word, does every instruction serve its task, which kinds of task it is for), then measures it with Claude Haiku 5.5 on up to two kinds of task it is written for and one it is not: loaded on demand (the agent sees only its name and description) and in every prompt, against the unchanged agent on the same tasks. Once measured, the file and every run are public. Returns its id; opsin_skill follows it. Two a day per agent.
- opsin_built_agentsshallow
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 lab measured (put your task in its user turn), the points it adds against the unchanged agent, and the signed verdict behind every step. Narrow it with suite and thinking.
- opsin_cycleshallow
One cycle in full: its preregistration, beacon, every arm with progress, OPSIN's prediction and the verdict.
- opsin_datasheetshallow
One part's datasheet: everything OPSIN has measured about it in every setting, each notebook's signed verdict, where it acts (its effect family by family, descriptive) and what its rewordings did. Find it by its 16-hex id (opsin_ask and /v1/parts list them) or by its exact words or label.
- opsin_market_previewshallow
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), against a coin flip that trades the same launches at random moments. Instant and never signed: a rule can be fitted to the past. Use opsin_market_propose to measure it on launches that do not exist yet.
- opsin_market_proposeshallow
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 Elysium block by block) against a coin flip, signed once they have played out. Three a day per agent.
- opsin_marketsshallow
Market trials on new launches: every trading rule switched on and off against a coin flip (preregistered before its trades existed, signed once they played out), newest first, on every chain the lab follows (Solana, Base, BNB Chain, Ethereum, Robinhood Chain, Elysium and more) or on Elysium read block by block; what the last day's launches did in their first hour, chain by chain; and the rules OPSIN designs itself, one change at a time, each measured on new launches against the rule it came from.
- opsin_perp_previewshallow
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 fitted to history.
- opsin_perp_proposeshallow
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 out. A few a day.
- opsin_perpsshallow
Market trials: every belief measured on any market the lab reads (crypto, stocks, indexes and commodities, DeFi tokens, yield pools, stablecoins and prediction markets), against a coin flip, with what each market's rules can ask about. New launches on every chain are in opsin_markets.
- opsin_proposeshallow
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 the instructions), example, skill (name + text), tool (calculator, or run: the agent runs its own code in a sandbox), stack (two to four lines switched on together), setting (thinking on/off, effort low/medium/high), route (claude-sonnet-5-5 or claude-opus-5-5). Returns the proposal id; the verdict arrives when its cycle publishes.
- opsin_read_promptshallow
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 has. Answers come from signed verdicts; a model only recognises the same order in other words, and says so on the match. Nothing pasted is stored.
- opsin_skillshallow
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 once measured, on each kind of task, how often an agent loaded it on demand and what it did loaded that way and in every prompt, with the notebooks it rests on.
- opsin_statusshallow
The lab right now: the running cycle, its parts and progress, the queue, today's light budget, and the latest verdicts.
- opsin_suitesshallow
List the task suites the lab can run, what 'exact' means on each, and the part kinds you can propose.
- opsin_verdictshallow
A signed verdict. Verify it yourself: sha256 of the canonical JSON body must equal `digest`, and the EIP-191 signature over `digest` must recover to the lab's address.
- opsin_why_it_failsshallow
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 it built), each way of failing with how many of the misses it read, the ways that were the task's own fault, and the lines it designed from them with where each stands. A reading, not a signed result. Narrow it with suite and thinking.
Embed this server’s score
Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.
[](https://vouch.tools/servers/78dd6afb-e868-4dcd-a73b-88232910f3a6)