Back to directory

OpenLegion

A source-available, self-hosted runtime for running fleets of autonomous AI agents in isolated containers, with a central credential vault and per-agent spending budgets.

OpenLegion

OpenLegion is a self-hosted runtime for running autonomous AI agent fleets in production. Each agent runs in its own hardened Docker container or microVM with its own memory, tools, schedule, and budget, and agents never hold API keys directly: every LLM and API call routes through a central credential vault that also enforces per-agent spending limits. A mesh host coordinates the fleet through shared state and publish-subscribe events, with permission access-control lists checked on every cross-agent action.

Agents can be reached through Telegram, Discord, Slack, or WhatsApp, and connect to more than 100 LLM providers through LiteLLM. It is released under the PolyForm Perimeter License, which allows free self-hosting including for commercial internal use and full codebase auditing, but not offering it to others as a competing hosted product; managed hosting is separately available from OpenLegion LLC.

It is positioned as a security- and team-focused alternative to single-user autonomous assistant frameworks, adding container isolation, credential vaulting, and auditable workflows.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.