Orchestrators & Multi-Agent tools for Gemini / Google

GitHub's open-source toolkit for spec-driven development: spec.md → plan.md → tasks.md artifacts convert natural-language intent into a machine-checkable plan before any code is written, with /specify, /plan, /tasks, and /implement commands that run across Claude Code, Copilot, Codex, and Gemini CLI. The clearest reference implementation of treating spec/plan/task documents — not the prompt — as t

Intelligent routing across multiple LLM providers with load balancing, intelligent fallbacks, rate limiting, and response caching. Achieves 40–60% token cost reduction through smart model routing (cheap models for simple tasks, capable models for complex reasoning). Essential infrastructure for harnesses operating under strict cost budgets where model selection is a per-turn decision

Cross-harness plugin marketplace that maintains one source-of-truth plugins/ directory and generates harness-native artifacts for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot. It is the clearest practical example of treating reusable agent capabilities as a portable distribution format rather than ad-hoc prompt files

(15.5k ⭐) - Bridge for connecting local AI coding agents to Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work, and other messaging platforms

Production-ready Java framework for distributed, enterprise-grade agents with workspace sandboxing, permission-gated tool calls, AOP-style middleware, and cross-replica session recovery. The Java complement to AgentScope Runtime for teams that need a typed, JVM-native harness stack

Compiles agentic workflows written in Markdown into GitHub Actions YAML. Read-only by default, with writes only through sanitized safe-outputs. Copilot, Claude, Codex, Gemini.

(4.5k ⭐) - Multi-agent deliberation framework for comparing perspectives on difficult decisions across coding agents

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

by Michael Denyer - Claude Code version of Lauren Tan's Poteto's pstack. Rigorous agent workflows with Cursor primitives translated to other agents. Supports multiple providers

(3.5k ⭐) - Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents

Open-source operating system for AI agents — plug in the agent CLIs you already use and run them as a team on loops and schedules, with shared memory, permissions and approvals

(2,747 ⭐) - Multi-agent development workflows with task routing across Claude Code, Codex, Gemini, and OpenCode, plus planning, review, and testing commands

A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

Official GitHub Action that seamlessly integrates Gemini into your CI/CD pipeline, enabling automated code reviews, testing, and documentation generation

Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted

Google's experimental "hypervisor for agents" (April 2026, Apache-2.0): orchestrates Claude Code, Gemini CLI, Codex, and OpenCode as isolated concurrent processes, each with its own container, git worktree, credentials, and network policy. The core harness insight is *isolation over coordination* — let agents run fully autonomous inside their containers and enforce guardrails at the infrastructure

Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Ollama, etc supported. 🎆 Code RAG

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions.

Local-first AI agent office simulator. Orchestrates CLI, OAuth, and API-connected agents as a virtual autonomous company

The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.

Deterministic scheduler for 40+ CLI coding agents running in parallel git worktrees with an HMAC-signed audit chain, signed agent cards, and per-artefact lineage. The zero-LLM coordination loop and tamper-evident audit trail make it the only open-source orchestrator designed for compliance-sensitive agent fleets

Universal agent orchestrator. Route tasks between Codex, Claude Code, and Gemini CLI based on model strengths

Terminal UI companion for CLI-based coding agents (Claude Code, Cursor, Gemini) with unified conversation history, git integration, task management, and workspace control

(974 ⭐) - Delegate tasks to Codex GPT 5.2 directly from within Claude Code

Self-hosted, open-source AI browser agent that browses, clicks, types and reads real web pages from plain-English instructions; runs locally on a patched Firefox engine and ships as an MCP server and a local web UI

Watches Linear, GitHub, GitLab, and Slack issues assigned to it, spinning up an isolated worktree per issue. Claude Code, Codex, Cursor, Gemini.

Local-first shared work-state MCP server (npx -y @concord-ai/concord-mcp) that lets coding agents coordinate on one repo through presence, file claims, messaging, handoffs and review packets. Works with Gemini CLI alongside Claude Code, Codex, Cursor and other agents. TypeScript, stdio, MIT

by aannoo - Lightweight CLI tool for real-time communication between Claude Code sub agents using hooks. Enables multi-agent collaboration with @-mention targeting, live dashboard monitoring, and a zero-dependency implementation

Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.

Workflow orchestration with Codex and other CLI backends; successor to the archived Claude Code Workflow

Run multiple coding agents (Gemini CLI, Claude Code, Codex, OpenCode) in parallel, each teleported into its own sandboxed VM — local Docker, self-hosted, or cloud (Hetzner, Daytona, Vercel, E2B, DigitalOcean). Sub-1s checkpoint startup; git credentials stay on the host. MIT

Neutral orchestration layer for Claude Code, Codex CLI, Gemini CLI, OpenCode, Qwen Code. Works from any IDE or shell

Agentic IDE and AI orchestrator for running Claude Code, Codex, OpenCode, Gemini, Cursor, GitHub Copilot, Kimi, and Hermes agents in parallel, each in its own git worktree, steered from a unified dashboard with real-time mobile sync and push notifications

TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.

Leader-worker task board with cryptographic agent identity. Claude Code, Codex, Gemini CLI.

Multi-agent development orchestration platform coordinating 22 specialized AI agents through 4-phase workflows with native parallel execution, persistent sessions, and least-privilege security tiers. Runs on Gemini CLI, Claude Code, and Codex

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

Self-improving multi-agent orchestration: 18 agents, 13 skills, TDD enforcement, quality gates

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.

AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

Desktop voice and chat assistant for Windows, macOS, and Linux that runs CLI coding agents such as Claude Code, Codex, and Gemini CLI side by side in Git worktrees, with memory, scheduled routines, and any single model key or local models via Ollama.

Open-source, ticket-driven software engineering platform that orchestrates Claude Code, Codex, and Gemini CLI agents across your machines with workflows, skills, and full traceability

Shep is an SDLC control center that enables AI coding agents to autonomously handle the complete feature lifecycle, orchestrating multi-session development using Claude Code, Cursor CLI, or Gemini with configurable approval gates and a live web dashboard github

Official source for the sandbase-mcp skill - discover, inspect, and invoke 2,000+ AI models and APIs through a local MCP bridge with explicit schema and cost checks (Apache-2.0)

Adds lit to the Antigravity CLI (agy) so a request is planned, built with tests and recorded checks, reviewed, and closed with a handoff note

Coordinates Claude Code, Codex, and Gemini CLI on one shared repo through a research-plan-delegate-adversarial-verify-deploy pipeline, with file locking, knowledge capture, and drift detection. Single Rust binary.

WhatsApp-like dashboard for managing multiple AI coding agents (including Gemini CLI) in one browser window. Live status, session resume, autopilot that routes work between agents while afk, mobile remote to check in from a phone

Local-first work inbox that triages email, chat, issue trackers, and scheduled reports into supervised Claude Code, Codex, Gemini, Cursor, or Copilot CLI runs, with conflict-aware queuing, live terminals, and approval-gated replies.

Directs agents through work cycles where a separate agent independently verifies each result. Claude Code, Codex, Gemini CLI.

Open-source AI data discovery platform that connects to warehouses (BigQuery, Redshift, Snowflake, etc.), runs autonomous agents that write and execute SQL, and surfaces validated insights. Pluggable LLM providers (Claude, OpenAI, Ollama, Vertex AI, Bedrock), industry domain packs, Helm charts, and Terraform modules for GCP/AWS

Self-hosted BYOK AI workspace with multi-provider chat (Groq, OpenRouter, NVIDIA, Hugging Face, Google AI), agents with scheduled runs, and skills like Gmail, Google Calendar, web search, and project generation. Provider keys are sealed client-side with AES-256-GCM and no middleman service is involved. Apache-2.0, Docker deployment

Cross-LLM sub-agent orchestration - routes tasks to Codex for fast refactors, Claude Code for long reasoning, Gemini for large-context analysis

MIT-licensed, local platform that runs a team of role-based agents (developer, QA, PM, orchestrator) on Gemini CLI, Claude Code, and Codex, with task delegation through agent skills, shared persistent memory, and a web dashboard of live agent terminals. Requires one of these agent CLIs installed and logged in

Self-hosted CLI that runs a team of coding agents on one Linux host: each agent is its own Linux user running claude, codex, opencode, hermes or another CLI as a systemd service, coordinating through an org chart and a shared SQLite backlog, escalating to Telegram only when a human must decide. MIT

(67 ⭐) - A multi-agent orchestration system that enables Claude Code, Codex CLI, Amazon Q Developer, and Gemini Code Assist to collaborate bidirectionally through intelligent task routing and consensus-based decision making

Telegram bridge for Gemini CLI (and 5 other agents). Send tasks by voice, stream progress, configure approval mode (read-only/edit files/full access) via inline buttons. Self-hosted, MIT licensed

Kanban-driven CLI orchestrator that runs Gemini CLI alongside Claude Code and Codex in parallel across isolated git worktrees, with a merge queue that reviews and merges verified task work. Git-native task state, per-agent worktree isolation, installable via npm. MIT

Open source CLI for AI agent coordination that organizes agents into domain-aligned squads with persistent memory, goal tracking, and Git-native state. Works with Gemini CLI

Mobile & desktop PWA command center for controlling AI coding agents (Claude, Codex, Gemini) via tmux sessions across multiple machines, secured by Tailscale. Includes a multi-terminal grid view, mobile touch UI, and Ralph — an autonomous task runner. github

Gemini CLI skill that generalises autoresearch to any measurable goal. Gemini-native: uses Google Search grounding as a live verification source inside the loop, true headless overnight mode via --yolo --prompt, and 1M token context. Also works in Antigravity IDE via .agents/skills/

The Minimal Agent Engine, enabling seamless integration with your platform. KodeAgent offers tool-calling (ReAct) and sandboxed code-executing (CodeAct) agents, supported by planning and observation

Sync AGENTS.md ↔ CLAUDE.md ↔ .cursorrules. One source, all formats

Self-hosted Kanban board that runs Gemini CLI alongside Claude Code, Codex, Cursor CLI and other coding agents, each in its own container. Moving a card starts a durable workflow with parallel steps, approval gates and per-run token and cost tracking

by Wenyu Chiou - Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate

Discipline layer for AI coding agents: 135 skills and 7 subagents that wrap Gemini CLI (and Claude Code, Codex, Cursor, OpenCode, Amp, and pi) in a measure → modify → verify → keep/revert loop with automatic rollback of failed changes. MIT

Tiny Python scaffold for running Gemini CLI, Claude Code, Codex CLI, and similar coding agents in guarded local loops. It uses repo-local specs, fresh-context iterations, hard caps, git-hook gates, CI verification, and coverage gates

Intelligent orchestration platform routing tasks to Claude, Gemini, Codex, and OpenCode via Budget→TOPSIS→LinUCB composite router. 30 MCP tools (orchestrate, consensus voting, research pipelines), 12 expert agents, 17 skills, plugin-native /agents + hooks. Install: /plugin marketplace add williamzujkowski/nexus-agents

Autonomous research agent that builds a knowledge graph during web exploration via a Perceive-Think-Act loop, then refines drafts through adversarial artifact synthesis. Multi-provider via litellm

Runs Gemini CLI, Claude Code, Codex, Aider and opencode inside a Linux micro-VM on a copy-on-write clone of your project, with a network allowlist and a pull-request-style diff review before changes are applied

Self-hosted web workspace that runs Gemini CLI alongside OpenCode, Codex, Claude Code and other coding CLIs as side-by-side panes in persistent rooms, with MCP servers and managed browser panes. Install: npx --yes run-spaceapp@latest install. Source-available (BSL 1.1)

Gemini CLI extension, MCP server and CLI over the session transcripts Gemini CLI, Claude Code, Codex, Copilot CLI, Cursor, Grok and OpenCode already write. List and read other live sessions, hand off compact state, send into a specific chat, or spawn a headless session that replies through a shared inbox. Install: gemini extensions install https://github.com/abnegate/magents. Rust, MIT

Trust-based delegation with quality ratcheting that commits improvements and reverts regressions. Chains Claude Code, Aider, Gemini CLI, Ollama.

Makes Gemini CLI (and Claude Code, Codex, Qwen Code) prepare before it builds: splits the task into areas of know-how, finds or writes a skill for each, checks the result against the original, and lets a fresh critic judge it. MIT

Skill router and context picker for coding agents: a local model (via Ollama, offline by default) routes each prompt to the right skill via hybrid BM25 + embedding retrieval, cross-encoder rerank, and an LLM judge, then assembles a minimal context bundle for the execution model. Built-in prompt-injection gate scans every retrieved document, fail-closed. Ships an MCP stdio server and an OpenAI-comp

Sync MCP server configs from Claude Code to Gemini CLI, Codex CLI, OpenCode, Kiro, Cursor. One command, all agents

Tool that picks up tickets from Jira, Linear, Trello, Asana, Azure DevOps, GitHub Issues, or markdown files and turns them into self-reviewed pull requests by driving Gemini CLI non-interactively (also supports Claude Code, Codex, and others). A feasibility gate flags vague tickets back to the tracker with questions; optional unattended mode schedules ticket pickup and turns PR review comments int

Watchdog that tails Gemini CLI session transcripts and alerts when the agent loops, oscillates, or stalls — Telegram notifications, zero dependencies

Durable build harness that drives an LLM from an idea, PRD, or spec to software gated on passing verification commands, with resumable checkpointed state; provider-neutral across OpenAI-compatible, Anthropic, Gemini, local, and command-bridge backends

Local web dashboard that lists Gemini CLI and Antigravity chats alongside Claude Code, Codex and Cursor on one board, with what needs an answer and a reply box (gemini --resume -p). Python standard library only, MIT

Runs Gemini CLI alongside your other coding agents (Claude Code, Codex, Qwen, Vibe) in parallel and read-only over your diff, then synthesizes their reviews into one ship / no-ship verdict. A cross-model review panel

Gemini CLI extension + MCP server that lets Gemini CLI, Claude Code, Codex and Cursor sessions on one machine search each other's history and message each other live (send/wait/reply, channels, file claims). Local SQLite, no daemon