> ## Documentation Index
> Fetch the complete documentation index at: https://docs.proofable.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Import an agent

> Give an agent that already runs elsewhere its own Proofable identity, without running its code.

Drop a package, pick a GitHub repo, or paste a card or runtime link. Proofable inspects the source, registers identity on your profile, and asks you to reconnect apps. Secrets stay behind, and the package never runs.

Supported inputs include OpenClaw workspace files, Hermes config and skills, Agent Skills `SKILL.md` folders, A2A Agent Cards, MCP URLs, GitHub repositories, and zip or tar packages.

## From your terminal or coding agent

Run these yourself, or ask Claude Code, Cursor, Codex, or any agent with a shell to run them:

```bash theme={"system"}
npx -y @proofable/sdk auth --oauth
npx -y @proofable/sdk import <owner/name, URL, or folder>
npx -y @proofable/sdk mount <agentId> --apply <host>
```

`import` accepts a GitHub `owner/name`, a path, a directory, or a URL. Signed in, it creates the agent on your profile and mounts it into this project in one step, then prints what the agent may do and when its permissions end. Add `--dry-run` to see that first, or `--no-mount` to skip the mount. Secrets in `.env` files, keys, and token stores stay out of the preview. `mount` connects the agent to your project, where `<host>` is `hermes`, `openclaw`, `opencode`, `cursor`, `claude`, or `codex`, and VS Code uses `--apply cursor`. Host files are written by this command in your project, never by the browser.

## From the product

1. Open **Import your agent**.
2. Drop files or paste a link.
3. Review the detected label, skills, and apps that need reconnect.
4. Continue to register identity. Set spend and action limits as a separate step.
5. Connect the runtime from the project with the `mount` command above.

## HTTP

Inspect first, then map onto identity create. Retry is safe.

```bash theme={"system"}
POST https://api.proofable.me/api/v1/agents/import/preview
POST https://api.proofable.me/api/v1/agents/import/commit
```

Send JSON: `url`, `text`, `filename`, `archiveBase64`, or `files`. Commit returns `identityPrefill` and `mcpCreateArgs` for [`proofable_agent_create`](https://docs.proofable.me/mcp/agent-create).

If a Proofable identity is already on the source, Proofable links it only after this profile owns it. Otherwise it registers a new agent and leaves the source unchanged.

## What stays out

Credentials, OAuth databases, private keys, and token values are excluded. Reconnect those apps with OAuth or an existing account connection. Spend limits stay an explicit review.

## Related

* [Agent identity](https://docs.proofable.me/agents/agent-identity.md)
* [Connect agent context](https://docs.proofable.me/agents/runtime-mount.md)
* [Proofable CLI](https://docs.proofable.me/sdks/cli.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.