Start Here
camelRun
A hosted runtime for durable agents. Your tools stay in your code; camelRun runs the model loop, keeps history and files, and wakes agents when there is work.
View as Markdown · Docs index for coding agents
Set up with your coding agent. Paste this into Claude Code, Codex, Cursor or any coding agent. It asks you what the agent should do, installs the SDK, connects your account without pasting keys into chat, and runs your first agent.
Read https://run.camelai.com/SKILL.md and set up camelRun in this project. Ask me what the agent should do.Self-host it. The runtime is open source and runs anywhere with Docker: one container and Postgres. See Self-hosting.
camelRun is camelAI's hosted agent runtime. You define an agent's tools in your own code with the TypeScript or Python SDK, or serve them over HTTP. camelRun runs the model loop, keeps each agent's history and files, compacts long conversations, runs model-written code in a sandbox, and wakes agents when there is work. Most agents are asleep at any moment and cost nothing while they are.
import { Agents } from "@camelai/run";
const agents = new Agents(); // reads CAMELAI_API_KEY
const agent = await agents.upsert("support-triage", {
instructions: "Be concise.",
});
console.log((await agent.run("Which tickets look urgent?")).text);
await agents.close();| API | https://run.camelai.com/v1 |
| Console | run.camelai.com/console |
| OpenAPI spec | /v1/openapi.json |
| Docs for agents | /llms.txt |
| Source | github.com/qaml-ai/run |
Connect your coding agent
The hosted MCP server at https://run.camelai.com/mcp needs no API key: sign
in with GitHub or Google when your client asks, which creates your account.
GitHub accounts older than 30 days start with free credit; everyone else
verifies a card on the Billing page
(no charge).
claude mcp add --transport http camelrun https://run.camelai.com/mcp
# Then run /mcp in Claude Code to sign in. Or skip signing in with a key from your environment:
claude mcp add --scope project --transport http camelrun https://run.camelai.com/mcp \
--header 'Authorization: Bearer ${CAMELAI_API_KEY}'The single quotes keep ${CAMELAI_API_KEY} as written: the project's
.mcp.json names the variable, and Claude Code reads its value from the
environment. Never write a key's value into an MCP config; they are often
committed.
What you get
The same key is the same agent, with its history and files, from any process, until you delete it.
Tools run in your process or on your HTTPS endpoint, with your credentials. MCP servers and OpenAPI specs work too.
Approvals, questions and forms suspend a run for days, then resume it where it stopped.
React, Vue, Svelte and Solid components stream an agent into your app without exposing your API key.
Slack, Telegram, Discord, GitHub and any service that sends webhooks can start and talk to agents.
Every agent is an MCP server, so Claude, Cursor or any MCP client can message it.
Pick from the catalog, bring your own provider keys, or add a model server of your own.
Start here
An agent that calls a tool in your process, in five minutes.
A streaming chat with your users' agents, from one command.
Keyed agents, runs, events, and where tools run.
Deploy and manage agents from a terminal, or from a coding agent.
Packages
| Package | |
|---|---|
@camelai/run (npm) | TypeScript SDK: Node 22+, Bun, Deno, Cloudflare Workers |
camelai-run (PyPI) | Python SDK: Python 3.11+ |
@camelai/run-react | Chat components and hooks. Vue, Svelte and Solid bindings are @camelai/run-vue, -svelte and -solid |
@camelai/create-run-app | npm create @camelai/run-app scaffolds a Next.js chat app |
@camelai/camelrun | The camelrun CLI and local MCP server |
Licensing
The camelRun runtime is licensed under the GNU AGPL-3.0. The SDKs, frontend packages, CLI and examples are MIT, so you can use them in any application. Commercial licenses for the runtime are available: contact us through camelai.com. See Self-hosting to run the runtime yourself.