#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.

🔁 Build reliable recurring AI-agent systems: 1025 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

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

dsh-agent-team gives DeepSeek Harness agents that don't reset: durable Members with their own memory, notes, and skills across sessions, rollovers, and restarts. You set the direction; agents coordinate through Channels and Tasks.

Ryu is the open-source layer around your agents. Bring Claude Code, Codex, OpenClaw or your own. Start without building from scratch, add tools with plugins, and turn your agents into apps. Monitor every run and control what your agents can access.

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

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.

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

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.

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.

Turn one Claude Code subscription into a crew of AI agents that research, plan, and ship code in parallel — a Slack-style HQ on your laptop where every risky action needs your approval. The HQ where AI agents work as a team, and you have the final say.

PiCode — browser-based Agent Development Environment (ADE) for Pi coding agents. Create, configure and orchestrate agents across workspaces: no terminal fear required.

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

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

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

Runtime infrastructure for AI agents — lifecycle, supervision, secrets, and deterministic time-travel replay. Built in Rust.

Run Claude Code as a service: REST API, web UI and multi-agent orchestration in one container

A crew of specialist AI agents and command workflows that drive a GitHub issue to a reviewed, CI-green pull request autonomously. Multi-harness.

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

🗼 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.

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

🐾 Your agent writes the code, a different model tries to break it, and only what survives ships. Cross-model review, gated merges, human-approved.

Agent OS for Claude Code: a desktop app to plan tasks, hand them to Claude Code agents and follow their runs across all your projects. macOS, early alpha.

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

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

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

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.

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.

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

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

Open-source enterprise AI agent platform for centrally governing agents, tools, memory, RAG, approvals, and durable workflows with FastAPI, LangGraph, LangChain, and LangSmith.

Charterion: Multi-Agent Engineering Control Plane for ChatGPT Web Agents - orchestration, task dispatch, browser control, durable state, worktrees, evidence, review, recovery, and self-hosting.

One desktop app for every coding agent. Pick the harness per session and any model it can reach.

The missing agent-to-agent messenger for OpenCode.

Talk to one agent. It runs the crew. A captain → foreman → crew harness for Pi + Herdr: parallel coding agents in isolated git worktrees, with a flat context contract.

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.

Let Hermes Agent orchestrate Claude Code on your Mac through the native Claude Agent SDK.

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

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

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