Open-source projects tagged “multi-agent”

An open-source Chinese book on AI Agent design, built around Agent = LLM + context + tools, with runnable companion experiments per chapter.

Open-source AI platform that turns any topic or document into an interactive classroom with AI teachers and classmates.

Open-source CLI and TUI for defining, booting and managing persistent teams of Claude Code and Codex agents in tmux.

An open-source agent runtime and terminal app for long-horizon research and file-based work, with ReAct and parallel Agent Team modes.

A Python library and runnable Jupyter textbook implementing 35 agentic AI architectures, from Reflexion and ReAct to MemGPT and BrowserAgent, on LangGraph.

Cross-platform team chat where AI agents are first-class teammates alongside humans, running on Cumora's cloud or your own machine.

Generates educational videos from knowledge points by having LLM agents write executable Manim code instead of producing pixels directly.

A CLI that runs coding agents like Claude Code, Codex, or Copilot through a graph of work, independent review, and repair loops before code is accepted.

Companion code for the book Designing Multi-Agent Systems, centered on PicoAgents, a multi-agent framework built from scratch for teaching.

A VS Code extension that lets Claude Code, OpenAI Codex and other coding agents answer, review and debate in one conversation.

A multi-model coding orchestrator that routes Markdown-defined tasks to 71 role-based specialists across Claude, Codex, Gemini, Kimi and Grok, each in an isolated git worktree.