Will it slow down my API?
No. The SDK sends logs in the background, and fix lookups happen in-process, with no network call in the request path.
A bare 400 leaves an agent guessing, and its wrong guesses come back as support tickets. Restless adds the fix to the error response, so the next agent corrects the call and finishes the job. No redeploy.
Free plan, no card. Set it up with one prompt to your coding agent.
Built for small teams with a public API on Node, Python, Ruby or Go. It works alongside the docs you already have on ReadMe, Mintlify, Fern or GitBook.
An agent calls an endpoint that doesn't exist, or sends a field your API rejects. It gets back a bare error with nothing to act on, so it guesses, retries or gives up. You can't see what it was trying to do.
Your error messages were written for a developer reading logs later. An agent reads them the moment the call fails, and acts on whatever they say.
"users complaining our api is down because the chatbot hallucinated the endpoint"
The ticket says your API is down. Most agents start each session fresh, so the next one makes the same bad call. The person who asked the agent for help leaves with nothing done, and you never hear why.
One API owner found 107 of 121 agent tool chains broken for months before anyone noticed.
| What you have | What it does | Where it stops |
|---|---|---|
| llms.txt and Markdown docs | Helps agents read your docs | The call still fails |
| A hosted MCP server | Gives agents your endpoints as tools | Returns the same bare error |
| Your error tracker | Records the 400 for your team | Tells the agent nothing |
| Better error text in code | Fixes one message | Every change waits on a deploy |
Restless works alongside ReadMe, Mintlify, Fern and GitBook. Keep your docs where they are.
See the failed calls. Every request lands in Restless, so you can see which calls fail and where callers give up.
Write the fix once. Plain language, with no code change and no redeploy.
Every agent gets it. Restless adds your fix to the error response for every matching call. The agent corrects the request and retries.
Nothing reaches an agent until you approve it.
The task finishes, so nobody writes in to say your API is down.
Every call in one place. See which endpoints get hit, which fail, and where callers get stuck.
Agent feedback. Agents flag missing endpoints and confusing docs to an inbox that syncs to Linear.
Agent-ready docs. Restless builds agent-readable docs and a hosted MCP server from your OpenAPI spec.
Sign up with GitHub or Google. No card.
Paste the setup prompt into your coding agent. It works in Claude Code, Cursor, Codex and VS Code. Prefer to do it yourself? Install the SDK for Node, Python, Ruby or Go.
Set up Restless in this repo Watch the first calls arrive. Then write your first fix.
Free plan, no card. Set it up with one prompt to your coding agent.
No. The SDK sends logs in the background, and fix lookups happen in-process, with no network call in the request path.
Your API keeps serving traffic, because the SDK fails open. And we never drop your traffic for billing reasons.
The SDK strips personal data before anything leaves your server, and the SDK is open source. Logs are kept for 30 days.
You do. Nothing reaches an agent until you approve it.
Free plan
Free plan, no card. Set it up with one prompt to your coding agent.
The first 100 teams get a Slack channel with the Restless team, plus an optional setup call.
If agents already handle your API fine, the free plan will show you that too. If they don't, you'll see the failed calls as soon as traffic arrives, and you can fix the first one the same day.
Setup needs the computer where your API code lives. We'll email you the prompt, so you can paste it into your coding agent there.
Free plan, no card. The first 100 teams get a Slack channel with the Restless team.