runloop.ai
Runloop provides managed sandbox infrastructure for AI coding agents, including isolated Linux devboxes, blueprints, snapshots, storage objects, agent tooling, and benchmarking/evaluation features. It is used to run code, manage files and environments, and coordinate agent workflows on hosted infrastructure.
Runloop exposes a bearer-authenticated REST API at https://api.runloop.ai, a Node-based CLI (`rli`) authenticated by `RUNLOOP_API_KEY`, and documentation referencing an MCP server for AI tools whose connection/auth details are not publicly specified.
- Runloop MCP Serverdiscovered
- Runloop REST APIdiscovered
- Runloop CLIdiscovered
Sign up or log in via the Runloop Dashboard, then open Settings → API Keys to create an API key. The quickstart notes that a full-access secret key is fine for local development, and for limited-access automation you can use a restricted key. Set it in RUNLOOP_API_KEY for SDKs and the CLI, or send it as Authorization: Bearer <key> for direct API calls.
conventions · 1/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✓https://runloop.ai/llms.txt
- API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing