R

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.

3 integrations · MCP · REST · CLI

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.

discovered 2mo ago
MCP servers1
REST · OpenAPI1
CLI1
Credentials
Runloop API keybearerGet token ↗

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

Publish these signals → /publishing