crow
Active·★ 20·MIT·Updated 2026-07-20
Modular, agentic framework and MCP platform you self-host. Build and run your own AI agents, connect Claude/ChatGPT/Cursor as a native MCP connector, self-host your apps, and share over encrypted P2P — on hardware you own, with local or cloud models. Open source.
crow is currently grouped under MCP Servers, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward agent-framework and ai-agents. The listed license is MIT, which is useful when adoption constraints matter. It also shows measurable community traction with 20 GitHub stars.
#agent-framework#ai-agents#bot-builder#home-server#llm#local-first#mcp#mcp-servers
01
Why choose it
+Ships with a public repository and a MIT license, which makes adoption and review easier.
+The latest recorded update is 2026-07-20, which suggests the project is still actively maintained.
02
Trade-offs
!This page does not list a concrete install command, so you may need to verify setup steps in the official docs before adopting it.
!The publicly described feature set is still fairly compact, so deeper evaluation may require reading the README or source repository.
!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.
03
How it compares
≈crow sits in the MCP Servers category, so it makes more sense to evaluate it alongside tools like plex-mcp-server instead of in isolation.
≈It is usually better to compare by workflow, deployment model, and team fit before comparing individual features.
≈crow uses a MIT license, and community traction are both easier to judge in category context.
04
Alternatives
openislands★ 19
Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.
FunASR★ 19.4k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
llama-cpp-agent★ 650
The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.
Related searches
Comments
Log in to leave a comment
No comments yet. Be the first!