Collection · 44 entries
Multi-agent frameworks and orchestration
Frameworks, harnesses, and DSLs for coordinating multiple AI agents across handoffs, parallel waves, and tool use.
There are two distinct branches here: harnesses that orchestrate copies of the same agent across a workflow (oh-my-team, parallel-code, agent-flow) and frameworks for building heterogeneous multi-agent systems from primitives (AgentKit, AgentScript, ADK-JS). If you're already running Claude Code, start with the harness side. If you're building a product, the framework side gives you more structural control.
wanman - worktree-isolated multi-agent runtime for Claude Code and Codex
Multi-agent runtime that spawns each Claude Code or Codex agent in its own git worktree and home directory. JSON-RPC subprocess control, task pooling, artifact storage. Solves the share-a-directory failure mode that breaks most multi-agent harnesses.
agent-of-empires - mobile-first multi-agent control plane
TUI and web UI for managing parallel Claude Code, OpenCode, Codex, Gemini, Copilot, and Factory Droid sessions. Backed by tmux and git worktrees so each agent gets its own branch.
Orca - IDE for coding agents
Stably's next-gen IDE that's built around running coding agents in parallel. First-class support for Claude Code, Codex, Cursor agent, OpenCode, Ghostty, and worktree-based orchestration.
Foundry - foundation layer for agentic intelligence
Python agent runtime and framework aimed at production agentic systems. Early but already has 800+ stars and a clear shape around runtime primitives.
agent-hub - one chat surface for every local and remote agent
Open-source hub that connects to Claude Code, Codex, Hermes, OpenClaw, and other agent runtimes - local or on remote machines - through a single chat UI. Less workflow-tied than Conductor.
Egregore - shared memory for multiplayer Claude Code
Local MIT substrate that gives a team of Claude Code sessions a shared memory and coordination layer, spun up via npx create-egregore.
my-claude-devteam - 12-agent dev team for Claude Code
Drop-in pack of 12 specialized agents and 15 automation hooks that wires Claude Code into a structured P7/P9/P10 review and delivery workflow.
asynkor - file leasing for AI agent teams
Go MCP server that gives multiple agents (or IDEs) leases on files so concurrent edits don't trample each other - a Git-free way to avoid merge conflicts in multi-agent runs.
codex-mcp-server - call Codex from Claude Code
MCP wrapper around the OpenAI Codex CLI that lets Claude Code (or Cursor) hand specific tasks to Codex as a sub-agent over MCP.
pydantic-deepagents - Claude Code-style agents in Python
Pydantic AI library for building deep agents with tool calling, sandboxed execution, multi-agent teams, skills, and checkpoints. Same shape as Claude Code, scriptable from Python.
maestro-orchestrate - multi-agent orchestration platform
Orchestrates Gemini CLI, Claude Code, Codex, and Qwen Code with 39 specialist subagents, parallel execution, and built-in review/debug/security/SEO/accessibility passes.
sandboxed.sh - self-hosted agent sandbox orchestrator
Self-hosted Rust orchestrator that runs Claude Code and OpenCode inside isolated Linux workspaces, with skills, configs, and encrypted secrets stored in a git repo.
codexia - agent workstation for Codex and Claude Code
Desktop workstation that adds a task scheduler, git worktree management, remote control, and skills management on top of Codex CLI and Claude Code.
claude_agent_teams_ui - kanban for AI engineering teams
Kanban-style UI where agents take tickets, message each other, and review each other's work. Supports Codex, Claude, OpenCode, and 75+ LLM providers.
zeroshot - autonomous engineering team CLI
JavaScript CLI that drives Claude Code, Codex, OpenCode, and Gemini CLI as a single autonomous team, taking an issue spec and returning a finished branch. Walk-away workflow with built-in orchestration.
hcom - cross-terminal agent messaging
Rust tool that lets AI agents in separate terminals message, watch, and spawn each other. Works with Claude Code, Gemini CLI, Codex, and OpenCode for ad-hoc multi-agent workflows.
dmux - dev agent multiplexer for worktrees
CLI that fans coding agents out across git worktrees and coordinates their progress, so multiple agents can work on the same repo without stepping on each other.
herdr - terminal agent multiplexer
Rust agent multiplexer that lives in the terminal and lets you drive Claude Code, Codex, and other coding agents side by side in one TUI.
weave - entity-level git merge driver for agents
Rust merge driver that resolves false conflicts when independent agents edit the same file, claiming roughly 95% reduction versus line-based merge by working at entity granularity.
helix - private agent fleet with GPU desktops
Self-hosted platform that gives every Claude, Codex, or Gemini agent its own GPU-accelerated desktop. Ships Helm charts and a full private AI stack.
ccmanager - session manager for AI coding CLIs
TUI session manager that switches between Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, and Kimi CLI sessions in one place. Lets you run and supervise multiple agent runtimes from a single shell.
Dispatch - background workers for Claude Code
Claude Code skill that offloads subtasks to background AI workers, freeing the main session's context window. Designed to expand effective context by parallelizing dispatched work.
a2a-java - Java SDK for Agent2Agent protocol
Official Java SDK implementing the Agent2Agent (A2A) protocol for inter-agent messaging and capability discovery. Provides client and server implementations for JVM agent stacks.
awesome-agent-harness - curated harness list
Curated list of agent harnesses, orchestrators, and coding-agent runtimes. Useful index for evaluating multi-agent infrastructure projects.
cass-memory-system - shared memory across agents
Procedural memory layer that turns scattered Claude Code, Codex, and Cursor session transcripts into persistent, cross-agent memory. Every agent learns from every other agent's prior work.
supaconductor - parallel multi-agent orchestrator
Multi-agent orchestration system for Claude Code with parallel waves, automated quality gates, a Board of Directors review pattern, and a bundled Superpowers skill set. Ships as a Claude Code plugin.
RedAI - validate vulnerabilities in live targets
Security agent that runs scanner agents to surface candidate vulnerabilities, then has validator agents reproduce each one against a running instance. Outputs only confirmed exploitable findings.
opencode-workspace - multi-agent harness for OpenCode
Bundled multi-agent orchestration plugin for OpenCode with planning, agent roles, and shared workspace state. One install gets you a working harness instead of wiring it yourself.
Broccoli - cloud sandbox harness for Linear
Open-source harness that pulls coding tasks from Linear, runs them in isolated cloud sandboxes, and opens PRs for human review. Built to manage many concurrent agent jobs without local worktree juggling.
agent-order - cross-model PRD planning workflow
Hack that has Claude and Codex independently draft PRDs for the same feature, then critique each other's plans before implementation. Avoids the anchoring bias when one model sees the other's answer first.
openclaw-dashboard - command center for OpenClaw agents
Zero-dependency Go dashboard for OpenClaw AI agents covering cost tracking, token usage, and per-agent monitoring. Single-binary deploy.
awesome-autoresearch - autonomous research agent loops
Curated list of self-improvement loops, research agents, and autoresearch systems following Karpathy's framing. Useful index when designing multi-step agent harnesses.
pro-workflow - self-correcting Claude Code memory
Claude Code workflow where corrections persist as compounding memory across 50+ sessions, with parallel worktrees, agent teams, and 17 prebuilt skills.
claude-delegator - delegate to Codex and Gemini from Claude Code
MCP plugin that lets Claude Code delegate subtasks to Codex and Gemini directly inside a session. Useful for cross-model orchestration.
TAKT - agent coordination topology in YAML
Define multi-agent coordination, human-in-the-loop intervention points, and audit recordings in YAML, across Claude Code, Codex, and OpenCode.
claude_code_agent_farm - 20+ Claude Code agents in parallel
Orchestration framework that runs 20+ Claude Code agents concurrently with lock-based coordination, automated bug-fixing sweeps, and live tmux monitoring.
cccc - chat-style multi-agent orchestrator
Coordinates Claude Code, Codex, and Gemini CLIs as a group chat with read receipts, delivery tracking, and remote phone control. Single pip install.
modular-context-obsidian-plugin - Claude Code in Obsidian
Obsidian plugin that runs multiple Claude Code and Codex terminals side by side with split layouts, a skills dashboard, and session glyphs. Treats your vault as the agent control surface.
oh-my-agent - portable multi-agent harness
Portable harness that runs .agents-based skills, workflows, and standards across Antigravity, Claude Code, Codex, Cursor, and OpenCode. One config, every coding agent.
oh-my-team - 12-agent Claude Code orchestration
Multi-agent harness for Claude Code with planning, parallel execution waves, and a five-agent review gate. Hub mode lets you drive sessions from Telegram or Slack.
AgentScript - schema-driven agent orchestration language
Open language from Salesforce for declaring agent orchestration: tools, handoffs, guardrails, and stop conditions. Runtime-agnostic config.
Agentic Video Editor
Turns raw footage plus a creative brief into a polished ad using a Gemini + FFmpeg multi-agent pipeline. Useful reference for chaining vision and editing tools.
agent-flow - real-time Claude Code orchestration view
Watch your Claude Code agents think, branch, and coordinate as they run. Live visualization of subagent trees and tool calls in the browser.
AgentKit - multi-agent networks in TypeScript
Inngest's framework for multi-agent networks with deterministic routing and MCP-native tooling. Picks up where the LangGraph/CrewAI camps trail off.
Related collections
Claude Code tools, plugins, and integrations
The best tools, MCP servers, and harnesses for getting more out of Claude Code - orchestration, observability, telemetry, and remote control.
Observability for AI coding agents
Tools that show you what your coding agents are actually doing: token spend, session state, tool calls, and parallel execution.