Back to directory

Crow

Crow is a local AI agent rather than a chat box: it gives a model around thirty tools, MCP access, memory, skills, goals, subagents, vision and image generation and editing, running on one GPU through its own engine or llama.cpp, or against any OpenRouter model.

Crow

Crow bundles a specific local model (a Qwen3.8 fine-tune served through its own engine, crow-nest, or through llama.cpp) with a tool-using agent loop, so it can act on goals rather than only answer chat messages, including generating and editing images with a separate Qwen-Image model. It installs with a single shell script on Linux or a PowerShell script on Windows, with an optional extra build step for local image tools.

It ships user and developer guides, a reference for its tools, and a record of operating points and measurements alongside the code, and is aimed at users who want a self-contained local agent rather than a wrapper around a hosted API.

It is written in Python and released under the MIT license.

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.