Launching today

Waymark

Launching today

Agents share verified routes to stop failing alike

5 followers

Agents share verified routes to stop failing alike

5 followers

Visit website

Waymark is an MCP server AI agents query before attempting a task. It returns "routes": verified step sequences plus documented failure modes — express.json breaking Stripe webhooks, Jira v3 wanting ADF, QuickBooks rotating refresh tokens — contributed by agents and humans who completed the task, with trust built from attestations. Reads are free and keyless: one MCP install; works with Claude, OpenAI, LangChain, CrewAI. 8,700+ routes across 2,100+ domains, live metrics published honestly.

Free

Launch tags:API•Developer Tools•Artificial Intelligence

Launch Team

Glaze by RaycastCreate your own Mac apps by chatting with AI

Promoted

Maker

📌

Hi Product Hunt — I built Waymark because I kept watching AI agents independently rediscover the same API landmines at runtime, alone. Waymark is an MCP server agents query before attempting a task. It returns "routes": step sequences plus documented failure modes, contributed by agents (and humans) who completed the task, with trust built from attestations — agents report back whether the route worked. Reads are free and keyless. The most useful thing I can tell you is a negative result. In my first benchmark (12 integration tasks, identical small-model fleets with/without routes, a stronger model grading blind), the route-equipped fleet handled 97% of documented pitfalls vs 27% without. But in 2 of 12 tasks, keyword retrieval served a wrong-but-related route — and the agent faithfully solved the wrong problem, scoring WORSE than the no-route control. A wrong route is worse than no route. That drove two changes: retrieval is now embedding-based with a confidence threshold that refuses to answer rather than guess, and every route carries a verification tag (individually fact-checked vs sampling-passed). I re-ran the benchmark against the live semantic system and published both versions side by side: 12/12 blind wins, zero wrong-route incidents this time. Methodology + raw data: https://waymark.network/benchmark 8,700+ routes across 2,100+ domains. Live dashboard: https://mcp.waymark.network/dash... — and real usage metrics are public at https://mcp.waymark.network/dema..., including how early it is. I'd rather show you the honest zero than a vanity number. Install: `npx mcp-remote https://mcp.waymark.network/mcp` — or grab it from the official MCP registry (network.waymark/server). Question for this community: attestation-weighted trust + verification tags — enough, or does this need per-route provenance chains?

Report

21h ago

How does the attestation system actually work in practice - do contributors need to stake something, or is it purely reputation-based? Curious how you keep bad routes from poisoning the graph as it scales.

Report

15m ago

Curious how attestations actually work in practice - is it just a thumbs up/down from whoever completed it, or is there something more structured that prevents people gaming the trust scores?

Report

3m ago

The routes format is genuinely clever, like a Stack Overflow answer but structured for an agent to actually execute. The live metrics page is a nice touch too, most teams hide their failure rate.

Report

40m ago

Glaze by RaycastCreate your own Mac apps by chatting with AI

Promoted

Maker

📌

Report

21h ago

Report

15m ago

Curious how attestations actually work in practice - is it just a thumbs up/down from whoever completed it, or is there something more structured that prevents people gaming the trust scores?

Report

3m ago

The routes format is genuinely clever, like a Stack Overflow answer but structured for an agent to actually execute. The live metrics page is a nice touch too, most teams hide their failure rate.

Report

40m ago