An open-source Elixir runtime for AI agents that live inside your application and act by writing code. A Legion agent reaches into your app to find records, run reports or file tickets against functions you explicitly allow, and the same agent can sit behind a chat window, power an MCP server for Claude or Cursor, or run as an overnight background worker.
Be the first to rate Legion. Your feedback helps other users decide.
Let an agent act on application data through functions you whitelist.
Serve the same agent to Claude or Cursor through an MCP endpoint.
Run the agent as a background worker that clears a queue while nobody is watching.
Similar tools in the same category — compare side-by-side
A public collection of skills for real engineers, published straight from the author's own .agents d...
An ultra-fast, single-binary MCP server written in Rust as a lightweight alternative to Node.js or P...
An MCP server registry, directory and gateway. MCP Harbor mirrors the official MCP Registry and keep...
Guides and comparisons about code tools
Eleven recent open-source and self-hosted projects for building, sandboxing and deploying coding agents you own outright rather than rent.
Ten Show HN projects for running several agents at once: orchestrators, subagents in isolated worktrees, shared memory trees and browser relays.
Eight Show HN projects that handle the unglamorous layer: consumer-GPU serving, remote tensors, vector-ready storage, semantic layers and agent payments.
Which AI coding assistant actually saves you time? GitHub Copilot vs Cursor vs Codium in 2026, with real comparison and recommendations by use case.
How to choose an AI coding tool in 2026: inline completion, repo chat, and local privacy, compared across Copilot, Cursor, Codeium, and more.
