Claude Code multi-agent
Raven Nest
Multi-agent terminal for Claude Code, Codex & Gemini. Open-source desktop app — Electron + React. Built for developers running multiple AI agents in parallel.
Install
git clone https://github.com/GeronimoDiClemente/raven-nest.gitFrom the README
🪺 NestMux Multi-AI Terminal Workspace · v1.5.0 Run Claude, Gemini, Codex, Copilot and more — side by side in a single window. Each pane is its own AI session, with its own account, history, and environment. Website · Download · Feedback · Discussions What is NestMux? Think of it as a terminal multiplexer — but built specifically for AI agents and the way teams ship code. Instead of juggling tabs and windows, you get a flexible grid workspace where every cell is an independent AI session, on top of the things developers actually need every day: native git worktrees, a real Teams workspace with team flow & health analytics, a Hub that gathers your most-used terminals in one place, your personal My Repos dashboard, GitHub & GitLab integration, CI runs, and live terminal sharing. v1.2 builds on the v1.1 foundation with per-device repo paths, Teams crash fixes, and macOS bugfixes (credential persistence, port detection, auto-update). v1.2.5 fixed the macOS auto-updater — if you're on a version older than v1.2.5, download once manually; from v1.2.5 onwards Install and restart works automatically. v1.2.6 restored terminal sessions after Cmd+Q. v1.2.7 fixes port attribution for reparented background processes on macOS and Linux. v1.3 adds an interactive onboarding tutorial, and v1.3.1 lets you install an agent's CLI straight from the pane banner. v1.4 adds the Hub (your most-used terminals in one workspace) and Team Analytics (team flow & health, not a leaderboard). v1.4.1 brought the Layout selector back into the *More tools* menu, and v1.4.2 makes it work in the Hub too — so you can arrange your curated terminals like any workspace. v1.5.0 puts a real code editor in the grid. What's new in v1.5 A real code editor, in a pane Open an Editor pane and you get Monaco —…
Details
- Repository
- GeronimoDiClemente/raven-nest
- Language
- TypeScript
- Last updated
- 3 November 2026
- Topics
- aiclaude-codecodexdeveloper-toolselectronmulti-agentopen-sourceterminal
FAQ
What is Raven Nest?
Multi-agent terminal for Claude Code, Codex & Gemini. Open-source desktop app — Electron + React. Built for developers running multiple AI agents in parallel. It is a multi-agent for Claude Code, from GeronimoDiClemente/raven-nest on GitHub.
How do I install Raven Nest?
Clone GeronimoDiClemente/raven-nest from GitHub and follow the setup steps in its README.
Is Raven Nest popular?
GeronimoDiClemente/raven-nest has 33 GitHub stars and 6 forks. It was last updated on 3 November 2026.
More multi-agent & worktrees
Agent Tower Plugin
33BayramAnnakov/agent-tower-plugin
Multi-agent deliberation plugin for Claude Code - council, debate, and deliberation modes
Claude Code Orchestration Kit
37SirRuggie/claude-code-orchestration-kit
One expensive model orchestrates, five pinned cheaper subagents do the work. Drop-in CLAUDE.md, agents, and commands for Claude Code.
Making Gemini Useful With Claude
36ankitdotgg/making-gemini-useful-with-claude
Use Gemini (1M context, free) inside Claude Desktop and Claude Code. MCP bridge that delegates heavy tasks to Gemini CLI while Claude orchestrates.
TokenCode
34yzfly/TokenCode
为 Token 燃烧而生:token 越来越便宜,质量永远稀缺——与其省 token,不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优,用冗余换质量。Go 写的开源终端 Coding Agent,类 Claude Code,可接入任意模型,对团队友好。 | Born to burn tokens — they get cheaper, quality stays scarce. A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best. Claude Code-style, any model, team-ready.
Deep Research
40oh-rid/deep-research
Claude Code plugin: deep research with 3-way LLM triangulation (Claude + Gemini via agy + GPT-5 via codex). Worktree-isolated, primary-source verified (mechanical URL + passage check), defends against shared-corpus consensus hallucination.
LLM Autonomous Agent Plugin For Claude
28bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude
Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform.
Browse the most popular Claude Code mods, all multi-agent & worktrees, or the skills and MCP server directories.