#agent-orchestration

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Multi-agent research assistant using OpenAI Agents SDK and Olostep to produce sourced Markdown research reports.

Electron desktop workspace for orchestrating 5 CLI coding agents (Claude / Codex / Gemini / Kimi / OpenCode) in isolated Git worktrees, with a built-in Sigma Assistant orchestrator that resumes Claude sessions across restarts and observes pane lifecycle events via a mailbox back-channel.

Universal multi-agent infrastructure for AI coding assistants. 26 specialist agents, 19 enforced workflow skills, and a lead orchestrator — for Claude Code, Codex CLI, Cursor, and OpenCode.

Local-first desktop control room for coding agents. Run Codex, Claude Code, Cursor, Grok, Mistral, Pi, and local models together — each with its own role, permission posture, and receipts. Multi-agent ensembles in one thread, diff review, on-device history. macOS, Windows, Linux.

🚢 A crew of IDE agnostic sub-agents, slash-command workflows and tools that drive a GitHub issue from open to a reviewed, CI-green pull request — autonomously. Flagship: /ship-issue.

Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Local AgentOps for cross-vendor CLI coding agents: route work, recover state, and accept only with evidence.

Compound AI: a vendor-neutral operating standard for AI coding agents. Hard enforcement on Claude Code, advisory on other runtimes. Co-owned by Cameron Sutcliff and Joshua Sutcliff.

Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars

🗼 An orchestrator skill for Claude Code: describe a task in plain language — Manara picks the stage, routes to the right skills, keeps guards blocking, and resumes across context clears.

Local-first mission control for your AI agent workforce — run CLI agents like employees (SquadCue)

🛠️ Awesome ADE — a curated list of open-source Agentic Development Environments: orchestrators, TUIs, tmux harnesses, sandboxes and the agents they run.

Let your coding agent drive the other AIs on your machine.

Local-first control plane for AI-agent teams — orchestrates Claude Code, Codex, Grok, agy & Hermes into gated workflows that fix their own failures, with per-run metering, an append-only audit log, and team memory. Apache-2.0.

Bedside: manners for AI agents that operate tools for smart, high-judgment non-experts. Ship and test, not only write.

Delegate work to isolated sub-agents inside the pi coding agent — proven multi-agent patterns with safety, cost caps, and tracing built in.

An MCP server for orchestrating multi-agent workflows inside herdr, enabling real-time communication, pane management, and contextual handoffs.

Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm

Reusable Interpretable Context Methodology (ICM) workspace template for filesystem-based AI agent workflows

SWARM is an open-source Codex plugin for directing a coordinated team of AI agents from one control task.

Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.

Gaia — AI Workforce Platform for orchestrating Claude Code sessions across named agent personas.

🧠 Ultimate AI Coding Agent 2026: Supercharge Your Dev Workflow for Faster, Cleaner Code

Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.

An agent control plane for governed, replayable execution.

Nightshift is an overnight AI agent harness that fixes bugs, manages TODOs, and implements features across your projects while you sleep, with a morning digest waiting when you wake up.

Standalone, repo-agnostic multi-agent orchestration daemon and AI software factory CLI in Go

The terminal for running multiple AI coding agents in parallel — Claude Code, Codex, Gemini CLI, opencode. A live status sidebar shows which session is working, done, or needs you, so you never miss the agent waiting on input. macOS, built on Tabby.

🧩 Open-source control plane for running AI agents in secure, observable sandboxes.

Boardroom: iPhone command center for an autonomous AI company — agent offices, CEO/CFO/CTO teams, board debates, approvals, builds, QA, and Demo Day via Hermes on your Mac.

An open control plane for local AI coding agents.

Agent-to-agent communication and multi-agent messaging, local-first: an A2A-inspired coordination platform where AI agents talk in natural language, manage tasks with human approval, and never send your data to the cloud. 65-command API, Python client, web UI, encrypted backups.

Agentic loop OS for Claude Code on Windows. State on disk, QA with separate memory, and a rate-limit circuit breaker that pauses at zero tokens and resumes on reset. 47 offline tests.

Local-first governed software-delivery system for agent work with policy checks, digest approvals, replayable evidence, and release gates.

Kaleidoskop — replay your baro/Mozaik agent runs visually. Audit log → hexagonal neural firing in your browser.

Multi-service agency automation: React dashboard + n8n workflows + agent bridge with idempotent job tickets.