---
name: bijection-agent-ready-component
description: "Evaluate and integrate the Agent Ready component with Bijection."
---

# Agent Ready

Bijection component that makes your app readable by AI agents out of the box: serves llms.txt, agents.md, and a per-site markdown file live by default with ETag caching, RFC 8288 Link

- Package: @bijectionhq/agent-ready-component
- Category: AI & Agents
- Status: Preview
- License: Apache-2.0
- Bijection source (repository access required): https://github.com/bijectionhq/agent-ready-component/tree/a3f3152fb7a5aa4cb4ae63fa15da362f5a98a7a5
- Upstream: https://github.com/waynesutton/agent-ready-component/tree/a86238ff39cd119f0239c94cf9f6bf7e193c250c
- Documentation: https://docs.bijection.com/components/using
- Directory: https://bijection.com/components/agent-ready-component

## Get the source

Bijection repository access is required. Request access at https://bijection.com/contact.

```sh
git clone https://github.com/bijectionhq/agent-ready-component.git
cd agent-ready-component
git checkout a3f3152fb7a5aa4cb4ae63fa15da362f5a98a7a5
```

## Before using this component

Read the package README at the recorded revision for setup, dependencies, and API examples. Upstream documentation describes the original package and may differ from the Bijection adaptation. This is a source candidate for evaluation. Catalog inclusion does not establish npm availability or runtime qualification. Check compatibility with your SDK and deployment before adoption. External providers run their own compute.

## Integration workflow

1. Read the source README and package manifest at the recorded revision.
2. Confirm the required SDK, dependency availability, and runtime compatibility.
3. Follow the component's documented setup and configuration. Never invent an npm install command from a catalog package name.
4. Keep credentials in the project's existing secret store.
5. Follow the project's execution rules for verification and report what was actually checked.

## Original upstream skill

The following guidance describes @waynesutton/agent-ready. Its installation commands and APIs refer to the upstream package. Evaluate compatibility with the Bijection source separately.


> Agents: read this skill fully before writing code that uses Agent Ready. Follow the installation and configuration steps exactly.

# Agent Ready

## Instructions

A Convex component that automatically generates and serves standardized AI agent discovery files (llms.txt, agents.md, llms-full.txt) from your Convex backend. It keeps these files synchronized with your app data, caches responses with ETag support, and includes React/Svelte widgets for human visibility. The component runs in isolation with its own tables and serves files over HTTP without requiring external hosting.

### Installation

```bash
npm install @waynesutton/agent-ready
```

Current npm version: `@waynesutton/agent-ready@0.3.0`

## Use cases

- **Making your app discoverable to AI coding agents** that need to understand your API structure and available endpoints through standard discovery files
- **Automating documentation maintenance** when your Convex schema and functions change frequently and you want agent files to stay current
- **Adding agent analytics** to track which AI systems are accessing your app and how they interact with your discovery endpoints
- **Implementing agent readiness compliance** to pass isitagentready.com scans with proper headers, robots.txt, and sitemap.xml generation
- **Providing human visibility into machine-readable content** so your team can see what AI agents see when they analyze your app

## How it works

The component registers with `app.use(agentReady)` in your convex.config.ts and mounts HTTP routes through `registerRoutes()` in convex/http.ts. It maintains isolated database tables for caching generated content and uses `@convex-dev/crons` for scheduled regeneration and `@convex-dev/workpool` for durable content generation with retries.

Content generation pulls from your Convex functions and schema to build llms.txt (app overview), agents.md (API documentation), and llms-full.txt (comprehensive docs). The component serves these files with ETag headers for efficient caching and includes optional AI-assisted description generation via Claude or OpenAI.

The React and Svelte widgets connect to your deployment URL and fetch status from `/llms-status` and `/llms-readiness` endpoints. The CLI wizard at `npx agent-ready setup` handles initial configuration, creates wrapper functions in `convex/agentReady/`, and manages deployment sync. Test mode blocks public access until you run `npx agent-ready go-live`.

## When NOT to use

- When a simpler built-in solution exists for your specific use case
- If you are not using Convex as your backend
- When the functionality provided by Agent Ready is not needed

## Resources

- [npm package](https://www.npmjs.com/package/%40waynesutton%2Fagent-ready)
- [GitHub repository](https://github.com/waynesutton/agent-ready-component)
- [Live demo](https://quixotic-viper-800.convex.site/)
- [Convex Components Directory](https://www.convex.dev/components/waynesutton/agent-ready)
- [Convex documentation](https://docs.convex.dev)