agent-orchestration

paperclipai/paperclip

An open-source control center for coordinating AI agents at work — Paperclip is an open-source app for managing AI agents like Claude Code and Codex in daily workflows. It targets teams doing agent orchestration and multi-agent setups, offering MCP and agent-skills support, plus a cloud waitlist for broader rollout.

The open-source app everyone uses to manage agents at work

Mintplex-Labs/anything-llm

A local-first LLM workspace that turns documents into working agents — AnythingLLM bundles RAG chat, multi-user support, and configurable AI agents into one self-hosted app, aimed at people who want to run document-grounded chat and agentic workflows locally instead of relying on hosted AI services. It targets self-hosters and teams needing private, multimodal, agent-capable LLM tooling without complex setup.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

herdrdev/herdr

A background runtime that keeps coding agents alive across disconnects — herdr is a Rust terminal multiplexer built for running coding agents like Claude Code or Codex. It keeps sessions alive in a background server through SSH drops or client closes, and restores saved layouts and agent sessions after restarts, letting you manage multiple machines from one window.

the runtime your coding agents live on

tinyhumansai/openhuman

Run hundreds of AI agents cheaply on a tiny VPS — OpenHuman is an early-beta Rust agent harness that claims to run 500+ agents on a $10 VPS, with public benchmarks to back performance claims. It ships as both a local-first desktop app for everyday users and a Rust library for developers building agent orchestration or privacy-focused personal AI tools.

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

ParadevAI/Paradev

Paradev lets you run 100+ coding agents side by side on macOS — Paradev (formerly Superset) is a desktop IDE that orchestrates many CLI coding agents—Claude Code, Codex, OpenCode, and others—in parallel workspaces using your own subscriptions. Each workspace bundles terminals, diff-based code review, and a browser preview, aimed at developers juggling multiple agent-driven tasks at once.

Paradev (formerly Superset) is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

omnigent-ai/omnigent

A unified orchestration layer for Claude Code, Codex, Cursor and more — Omnigent is a meta-harness that lets you run Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, or custom YAML agents in one session, swapping harnesses without rewriting code. It adds policy enforcement, sandboxing, cloud execution via Modal/Daytona/Blaxel, and cross-device sync so sessions follow you from terminal to phone.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

HarnessMD/munder-difflin

An open-source office of coding-agent clones on your laptop — Munder Difflin is a free, local-first multi-agent harness that wraps Claude Code, Codex, Gemini CLI, Grok, OpenCode, Cursor and more, using your existing subscriptions. It visualizes agents as avatars on a shared office floor, coordinated by a 'clone' that routes messages and remembers context while you're away.

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

superplanehq/superplane

A self-hosted factory that turns backlog issues into PRs — SuperPlane coordinates coding agents, source control, CI, review and approvals in one visible system, automatically picking backlog issues agents can handle with high confidence and turning them into review-ready pull requests. Guardrails and feedback loops catch failures, while ambiguous decisions stay with engineers. Apache 2.0 licensed, for teams exploring agentic software delivery.

Open source factory for one-shot engineering

mvschwarz/openrig

Turning scattered AI coding agents into a managed team — OpenRig lets you define a persistent team of Claude Code and Codex agents in YAML, run them under one lead agent, and keep shared context and work organized instead of juggling separate terminal sessions. Aimed at developers running multi-agent coding setups who want coordination, not chaos.

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

unstablebuild/rune

a fast, GPU-accelerated, full-featured IDE and terminal multiplexer, suitable both for automatic and manual programming.

nrslib/takt

YAML-defined workflows that discipline multi-agent coding loops — TAKT is a CLI that encodes planning, implementation, review and fix loops as YAML workflows, assigning each step its own role, context and transition rules rather than relying on one agent to remember everything. It runs tasks in isolated worktrees with traceable logs and human checkpoints, aimed at teams tired of babysitting AI coding agents like Claude Code or Codex.

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

kdlbs/kandev

A kanban-style control room for orchestrating coding agents — Kandev lets you organize parallel tasks across kanban/pipeline views and assign AI agents from multiple providers, with an integrated workspace (editor, terminal, browser preview, git diff) for reviewing their output. It ships as a self-hostable Go binary with no telemetry, aimed at power users who want fine-grained control over agent workflows and review gates rather than juggling separate terminal TUIs.

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

pullboard-dev/pullboard

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.

receptron/mulmoterminal

A Browser Grid for Juggling Several Coding Agents at Once — MulmoTerminal is a local, tmux-backed browser terminal that runs multiple coding-agent CLIs (Claude Code, Codex, Grok, Copilot CLI, Cursor CLI and more) side by side, colour-coding each cell as working, done, or waiting on you. Sessions survive reloads, isolate via git worktrees, and can push phone alerts when a turn finishes — built for people juggling several agents, not just one.

Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.