AgentCrew
Active·★ 224·Apache-2.0·Updated 2026-10-27
AgentCrew allows building specialized AI assistant teams that collaborate via task transfer or delegation. It supports multiple AI models, tools, and interactive/automated modes, providing flexibility and safety.
AgentCrew sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Multi-model flexibility: switch between Claude, GPT, Gemini, etc.. A representative use case is Building multi-agent teams for complex software development projects.. The listed license is Apache-2.0. GitHub stars are currently 224. Relevant tags include ai-agents, ai-assistant.
#ai-agents#ai-assistant#anthropic-claude#mcp-client#mcp-servers#model-context-protocol#multi-agent-systems#terminal-app
01
Features
01Multi-model flexibility: switch between Claude, GPT, Gemini, etc.
02Agent specialization: create focused agents with custom instructions and tools.
03Tool integration: connect to real-world capabilities via MCP, web search, code analysis, etc.
04Interactive and automated modes: GUI, console, job mode, and A2A server.
05Agent-to-agent communication via A2A protocol for cross-system collaboration.
02
Why choose it
+Multi-model flexibility: switch between Claude, GPT, Gemini, etc.
+Agent specialization: create focused agents with custom instructions and tools.
+Building multi-agent teams for complex software development projects.
+Supports 5 platforms or runtime environments.
03
Trade-offs
!The final decision should still be made through side-by-side comparison with similar tools.
04
Compatibility
Python
Python 3.12+
Verified via docs
Docker
Docker
Verified via docs
Linux
Linux
Verified via docs
macOS
macOS
Verified via docs
Windows
Windows
Verified via docs
05
Quick start
1
$ git clone https://github.com/saigontechnology/AgentCrew.git
2
$ cd AgentCrew
3
$ uv sync
4
$ uv tool install .
06
Use cases
↳Building multi-agent teams for complex software development projects.
↳Automating code review and refactoring with specialized assistants.
↳Generating structured documentation from code or specifications.
07
Alternatives
asap-protocol★ 16
Standard protocol for agent-to-agent communication with stateful orchestration, MCP-compatible and a public marketplace to discover and register agents.
mcp_agent_mail_rust★ 218
Rust MCP server for multi-agent coordination: 34 tools, Git-backed archive, SQLite indexing, advisory file locks, and an interactive TUI console
pilot-shell★ 2.1k
How real engineers run Claude Code: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make Claude Code production-ready.
awesome-mcp-hardware★ 59
Awesome list of MCP servers for interacting with hardware and the physical world.
tesseron★ 21
Expose typed web-app actions to MCP-compatible AI agents over WebSocket. TypeScript SDK + matching MCP gateway.
Orkas★ 2.2k
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sessions. Agents self-evolve via reflection and skill crystallization. BYO keys. macOS / Windows / Linux.
Comments
Log in to leave a comment
No comments yet. Be the first!