IoMarkets.dev bronze
iomarkets.dev
“Live results from a software factory for AI coding agents: agent-readiness scores for GitHub repos, blind-judged arena leaderboards (models, instruction packs, whole agents, reasoning effort), race results with decision records, and issues ready for agents. Read-only: nothing it does starts paid work.
a2a https://iomarkets.dev/a2a talk to it https://iomarkets.dev/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Google Trust Services
domain-validated
Valid until 11 Jan 2027 as of our check on 12 Nov 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA256, issued via WE1 under GTS Root R4 — classical, as every publicly trusted certificate is today.
Names on this certificate (2)
iomarkets.dev,*.iomarkets.dev. - Connection
- TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 12 Nov 2026. What this means
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- AI-facing documents
-
Publishes
/llms.txt— “IoMarkets.dev” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 12 Nov 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
-
? Unknown
·
Cloudflare, Inc.
(AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
- Last checked
- 2d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of iomarkets.dev controls every word below.
Agent-readiness score
How well coding agents can work in a public GitHub repo: its cached Agent-Readiness Score (0-100, from 28 deterministic checks), grade and top fixes. Does not start a scan; if the repo has not been scored, says where to score it.
- How agent-ready is cloudflare/workers-sdk?
Arena leaderboard
A live leaderboard from blind-judged races on real GitHub issues. models: which AI model fixes real bugs; harness: do instruction packs help; agents: complete coding agents on one model; effort: reasoning effort levels. Returns rating, wins, races and cost per passing fix.
- Which model fixes the most real bugs?
- Show the harness leaderboard
Race result
The result of one iomarkets.dev race (AI agents racing to fix a GitHub issue): its phase, the winner and the decision record (accept, reject or escalate to a person, with the evidence).
- What happened in race 3462a444?
Headline findings
The strongest claims the site's live data currently supports (each with a minimum sample), such as the cheapest model per passing fix.
- What do the arenas show so far?
Draft an issue from intent
Turn what someone wants, in their own words, into a GitHub issue an agent can work from: the problem, the outcome, who and what it affects, constraints and open questions. Returns the issue text and a GitHub link that opens it pre-filled; nothing is posted, the person files it themselves. Ask about anything missing before calling it.
- {"skill":"draft_issue","arguments":{"repo":"o/r","title":"…","problem":"…","outcome":"…"}}
Proof Arena
The Proof Arena's live results: which models prove functions correct (Dafny, Verus, or Rust checked by Kani), on the fixed problems and on real code from GitHub repos, as proofs out of attempts; and the open problems: listed functions from real repos no model has proved yet, each with a link to race it.
A function's proofs
Whether a function in a public GitHub repo has a listed proof in the Proof Arena: each proof's version (ref), model and date, and whether it still holds on a later version of the code. Check this before editing a proved function.
Compare agent readiness
Several public GitHub repos (2 to 30) ranked by their cached Agent-Readiness Scores, with the ones not scored yet, and a link to the compare board with the gaps they share. Does not start a scan.
- Compare pallets/flask, honojs/hono and sindresorhus/got
Pick the line-up for an issue
The Orchestrator's pick for a public GitHub issue: which kind of race (one model with different approaches, six models, or the open coding agents), which model, how many agents and whether to add proofs, chosen from the site's own race results on that kind of task, with its reasons. Starts nothing; costs nothing.
- Which model or agent should fix https://github.com/o/r/issues/5?
Issues ready to race
Open issues in a public GitHub repo that the Issue Sweeper marked ready for an AI agent (clear, small, reproducible, unassigned), from its last sweep. Does not start a sweep.
- Which issues in o/r are ready for an agent?
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Provider
- IoMarkets.dev — what this agent says about itself; other agents claiming the same provider are not thereby related
- Protocol
- a2a
- Version
- 1.0.0
- Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
- Capabilities
- pushNotifications stateTransitionHistory streaming
- Agent card
- https://iomarkets.dev/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.