Orchestrators & Multi-Agent tools for opencode

The AI orchestrator for running Codex, Claude Code, OpenCode, and Pi side-by-side in isolated git worktrees. It turns fleet-of-agents execution into a polished desktop IDE with a mobile companion, making parallel agent harness design accessible beyond shell-scripting teams

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

Claude Code plugin that externalizes multi-agent orchestration as installable skills and staged team pipelines, with cross-provider advisor routing and built-in requirement-clarification interviews. The most widely adopted example of turning a single-agent CLI into a team-ready meta-harness without rewriting the underlying loop

Self-hosted daemon running agents in parallel on your own machines, driven from desktop, iOS/Android, web, or CLI, with voice control, diff review, and no telemetry or forced log-ins. Claude Code, Codex, Copilot, OpenCode, Pi.

Practical design system for agent loops with seven production patterns, cross-tool starter kits, and CLI tools that score readiness, scaffold state, estimate cost, detect drift, and isolate worktrees. The clearest open-source resource for moving from one-off prompting to durable, observable agent loops

Databricks' open-source meta-harness (June 2026) that sits above Claude Code, Codex, Pi, and custom agents to compose, govern, and share live agent sessions from one control plane. The key harness insight is that enterprises don't need another agent framework — they need a portability and governance layer above the agents they already run, with policy-driven sandboxing and cost caps enforced outsi

by backnotprop - Interactive review UI that intercepts ExitPlanMode via hooks, letting you visually annotate plans with comments, deletions, and replacements before approving or denying with detailed feedback. Has since grown to cover code and diff review, PRs, and rendered HTML artifacts, with feedback sent straight back to the agent. Supports several coding agents alongside Claude Code

by smtg-ai - A terminal app that manages multiple Claude Code, Codex, and other local agents (including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously

Local-first multi-agent desktop application where a Commander coordinates specialist agents for research, coding, data analysis, documents, and media; MIT-licensed with bring-your-own model keys

Host agent that plans a complex task as a DAG and coordinates dependencies and parallel execution across built-in research, coding, design, and on-call agents and third-party agents over ACP, CLI, or OpenAI-compatible APIs. Presets include Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, GitHub Copilot, Qwen Code, and Kimi Code.

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

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

Bash script that loops Claude Code, Codex, OpenCode, Cursor, Qwen, or Droid until the task is done.

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

Desktop app where you give high-level commands to autonomous coding-agent teams across Claude Code, Codex, OpenCode, Cursor, Grok, GitHub Copilot, Kiro, Z.AI, MiniMax, Kimi, 200+ models, and 75+ LLM providers. Agents coordinate through inter-agent messaging, Kanban tasks, and built-in code review.

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

Long-horizon computer-use harness that runs on top of Claude Code and Codex, splitting work into Manager, Executor, and Auditor roles so only independently verified results enter persistent task state. The clearest August 2026 open-source reference for carrying desktop-and-CLI tasks through dozens of hours without state drift

Herdr mobile client for iPhone and Android. A self-hosted PWA to drive Claude Code, Pi, Codex and OpenCode in Herdr, tmux or zellij from your phone. Push alerts, no app store.

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

Automated skill discovery for coding agents: evolves reusable skills and prompts from failed trajectories against benchmarks, with support for Claude Code, Codex CLI, OpenCode, OpenHands, and Goose

PRD-to-deployed-product SDLC with 41 agents in 8 swarms, nine quality gates, and blind three-reviewer code review. Source-available under BUSL-1.1.

by avifenesh - Workflow automation system for Claude with a group of useful plugins, agents, and skills. Automates task-to-production workflows, PR management, code cleanup, performance investigation, drift detection, and multi-agent code review. Includes agnix for linting agent configurations. Built on thousands of lines of code with thousands of tests. Uses deterministic detection (regex, AST) w

Self-hosted AI company operating system where a lead agent delegates goals to workers in isolated containers, with persistent memory, schedules, and review gates. Claude Code, Codex, pi, OpenCode, Cursor, Amp, Grok, Devin, and ACP agents.

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

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

Solo Agent — an open-source, local-first workspace where humans and AI coding agents collaborate through channels, tasks, teams, and persistent memory.

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

HunterCode · Community Edition · 腾讯 WorkBuddy 金融版的开源本地替代方案 · open-source, local alternative to Tencent WorkBuddy Finance Edition · 多智能体投研终端 A股/港股/美股 · 推理在你机器上跑 · 仓位不出你硬盘 · BYOK · Apache 2.0 · docker compose 自托管

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

Build organizations of OpenClaw agents coordinating across Codex, Claude Code, Cursor, and OpenCode.

Unified framework wrapping Claude Code, Cursor, OpenCode, and Codex CLIs behind a single streaming API. Adds IM adapters (Slack, Telegram, Discord, Feishu), Skill system, fleet mode, and HTTP embedding

Desktop and web workspace where persistent teams of Claude Code, Codex CLI, OpenCode, and Pi agents collaborate through shared conversations, task delegation, and collaborative memory.

Local GUI orchestrator for AI coding agents with multi-model planning (LLM councils), iterative retry loops, and isolated git worktrees for long-running, correctness-first multi-file work

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

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

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

Self-hosted web UI for Claude Code sessions on a laptop and remote dev boxes. A daemon on each host owns the claude processes so sessions keep running when SSH drops; per-session diffs of changed files, plus tasks, notes, long-term memory, and a personal agent that starts sessions. TypeScript, MIT

Persistent workspaces for AI agent teams with inter-agent mailboxes, shared drive, and full context preservation. Supports Claude Code, OpenCode, Pi Agent and more

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

Runs project-board tasks in persistent sandboxes, with manager-agent delegation and deliverable review. Supports Claude Code, Codex, OpenCode, and other configured runtimes.

Runs unattended against a shared bead queue (SQLite, atomic claims), dispatching each bead to a headless CLI — Claude Code, Codex, OpenCode, Aider — with every outcome routed through an explicit state machine; no inter-agent channel, coordination is done at decomposition time.

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

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

Lightweight subagent pack focused on TypeScript/React projects

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

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

Self-hosted runtime for autonomous Claude Code and Codex agents that turns GitHub issues into reviewed pull requests. Per-firing git worktrees, label-driven state, role-based engine routing, Slack reports. Python, MIT, macOS/Linux

Two-file task management system for Claude Code/OpenCode: NOW.md tracks current work, NEXT.md queues future tasks with /next command