Orchestration

Self-hosted control center for AI software development agents that schedules multiple agents and automates routine coding and development workflow tasks.

Orchestrates multiple coding agents as managed workers toward business goals, providing task assignment, approval workflows, budget controls, and isolated workspaces for organizational oversight.

Provides an agentic development environment for running fleets of coding agents in parallel isolated workspaces, helping developers compare results and merge the best outcome across desktop, mobile, and remote runtimes.

Implements an agent meta-orchestration framework for deploying multi-agent swarms that coordinate autonomous workflows, conversational AI systems, adaptive memory, and retrieval-augmented generation integrations.

Creates a shared workspace where humans and multiple coding agents collaborate on one board, supporting task assignment, handoffs, acceptance review, multi-runtime execution, and squad-based routing for teams.

Teams-first multi-agent orchestration setup for Claude Code, providing collaborative team modes, task scheduling, and structured workflows for parallel development coordination.

Creates a self-hosted collaborative workspace where humans and AI agents share rooms and coordinate as a hive mind to complete software development tasks.

Orchestrates 20+ CLI coding agents such as OpenClaw, Claude Code, Codex and OpenCode in one 24/7 cowork app, letting developers customize assistants and coordinate them as collaborative teams.

A kanban workspace manager that plans work and orchestrates multiple coding agents across branches with diff review.

Turns project work into isolated autonomous implementation runs, letting teams manage scoped tasks and review results instead of directly supervising coding agents during development.

A workflow engine orchestrating AI coding assistants through deterministic, repeatable YAML development pipelines.

Autonomous development orchestration loop that repeatedly drives AI coding tools from a PRD, completing user stories one by one with automated acceptance checks until all requirements pass.

Multi-agent workspace manager coordinating multiple coding agents through division of labor, using hooks and letter-based messaging for persistent task tracking.

Cross-device orchestration platform for running and coordinating multiple coding agents in parallel on local machines, with mobile and desktop control plus voice-assisted collaboration.

A text-space optimizer that trains reusable natural-language skills offline for frozen LLM agents, validating multi-round trajectories through gating to produce a best_skill.md file.

A desktop app orchestrating multiple autonomous coding agents to plan, build and validate software in parallel.

Agent-based IDE for orchestrating hundreds of CLI coding agents in parallel, providing isolated workspaces, built-in terminals, diff reviews, and remote access for development teams.

Provides an IDE-style workspace for managing fleets of coding agents, with planning, dispatch, code review, CI fixes, and merge-conflict handling to support parallel development tasks.

Multiplayer collaborative IDE and cloud control plane for coding agents, orchestrating multi-agent sessions, task artifacts, and collaborative review to accelerate complex codebase delivery.

Collects practical patterns, starter templates, and CLI utilities for loop engineering with AI coding agents, helping developers prompt, orchestrate, audit, and cost-control continuous agent workflows.

Orchestrates Claude Code, Codex, Cursor, Pi, and custom coding agents through a meta-harness that allows harness swapping, policy enforcement, sandboxed execution, and real-time collaboration from any device.

Meta-skill for Claude Code that designs domain-specific agent teams, defines specialized roles, and generates reusable skills for coordinated development workflows.

Local multi-agent harness that reuses existing Claude Code and Codex subscriptions, letting users run an office of cooperating agents to complete tasks together.

Agent orchestration distribution where users talk to one agent to coordinate a crew working in parallel, managing multiple sessions and workspaces for faster delivery.

A native web workspace for Hermes agents that combines chat, terminal, memory, skills, and inspector views, enabling group-based scheduling and multi-agent coordination from one control plane.

A local-first, self-hostable agent workspace spanning multiple runtimes, plugins, skills, and multi-agent tasks, producing editable documents, sites, designs, presentations, and video.

A self-hosted control plane for AI agents that dispatches tasks, reviews runs, tracks spending, and governs sessions across OpenClaw, Claude Code, and Codex runtimes.

Provides a multi-agent orchestration engine for developers seeking reproducible coding workflows, using Socratic interviews, staged evaluation gates, and budgeted evolution loops.

Desktop source-control and orchestration tool for coding agents, running multiple agents side by side while tracking each commit, prompt, and reasoning trace.

Long-horizon control plane coordinates durable governed work across Codex, Claude Code, and other harnesses, adding goal gating, recovery, and human collaboration for teams running agents.

Multi-model collaboration workflow engine that analyzes user intent, selects execution strategies, and orchestrates Codex, Gemini, and Claude together to complete software development tasks.

A local-first desktop environment for running multiple AI coding agents in parallel, each isolated in its own Git worktree.

Collaborative multi-agent runtime and coordination layer that organizes transparent, human-in-the-loop task execution through Matrix rooms for teams needing auditable agent teamwork and oversight across projects.

Evolutionary self-improvement framework for Hermes Agent that optimizes skills, prompts, and code with DSPy and GEPA, gated by tests before submitting pull requests.

Provides an overnight looping scaffold that orchestrates multiple coding agents, iteratively applying documented code changes until a limit is reached for developers running long autonomous tasks.

Coordination tool for multi-agent development workflows, dispatching role-specific agents across isolated branch sessions for teams parallelizing coding tasks collaboratively and safely.

A cross-platform team chat where AI agents and humans collaborate as teammates with cloud or bring-your-own brains.

Provides a real-time collaborative workspace where people and multiple agents coordinate across devices, supporting shared chat, editing, scheduling, and agent sharing for teams.

A collaborative multi-agent coding workspace that aggregates sessions from Claude Code, Codex, OpenCode, and similar tools, supporting delegated subagents, isolated branches, desktop and self-hosted deployment.

Visible multi-agent CLI workspace that orchestrates Codex, Claude, Gemini, and other coding agents together, supporting cross-vendor collaboration and mobile remote control for developers.

A desktop command center for running multiple AI coding agents in parallel, combining event automation, auto-run playbooks, group chat across local and remote agents, and unattended multi-project development.

Autonomous orchestration tool based on the Ralph Wiggum looping technique, repeatedly dispatching agents until tasks complete while exposing progress on a dashboard.

Provides an open-source runtime for coordinating existing agent CLIs as teams, supporting scheduled loops, shared memory, permissions, and approval workflows for automation builders.

A collaboration and review system for coding-agent organizations that captures sessions from more than 20 CLIs with a built-in Rust harness, replaying decisions and tracing code to its source.

Runtime substrate that turns agent execution into reversible Git-like traces, enabling meta-agents to observe, fork, replay and revert runs while supervising and optimizing other agents.

An AI workforce platform for orchestrating remote agent workstations with PTY sandboxing and Git worktree isolation. It coordinates multi-agent collaboration through channels, bindings, Kanban, and MR/PR integration.

Local-first multi-agent platform for automated software development, letting AI agents build, evaluate, optimize and deploy AI applications with fully transparent processes.

Production-grade multi-agent orchestration runtime for developers building agent workflows, featuring task decomposition, budget controls, sandboxed execution, multi-strategy scheduling, and time-travel debugging.

Transforms software goals into orchestrated planner, implementer, and validator agents running in isolated environments, with independent parallel review, retry loops, and Git-based delivery after acceptance.

A multi-session coordination terminal that provides a shared blackboard for coding agents such as Claude Code, Cursor, Codex, and Gemini, letting developers schedule different models in parallel across projects.

Orchestrates parallel coding-agent tasks through tmux using a samurai-inspired shogun-karo-ashigaru hierarchy, enabling one command to coordinate multiple CLI-based agents for Claude Code users.

A programmatic orchestration framework that arranges thousands of agents and harnesses as graphs, supporting parallel fan-out, iterative loops, and multi-cloud execution for developers.

Command-line tool orchestrating AI coding agents through declarative YAML topologies that define coordination, human intervention points, permissions, and recorded artifacts for repeatable pipelines.

A local-first workbench for orchestrating multiple coding agents in parallel, each in an isolated git workspace with review, terminal, and one-click shipping.

Builds a local-first multi-agent task orchestration system that coordinates tool calls, clustered scheduling, and parallel approval workflows for developers running collaborative agent tasks.

A unified control plane for calling and managing agents across multiple runtimes, including OpenCode, Cursor, and Claude-managed agents, with shared sessions, scheduling, and memory.

Collaboration layer letting people and multiple AI coding agents work in shared rooms, with identities, inboxes, shared memory, and cross-room context for coordinated development.

Coordinates Claude Code and Codex agents inside VS Code as a collaborative coding team, organizing brainstorming, debate, and synthesis to select stronger implementation approaches for developers.

Real-time control room for agent societies that can pause, replay, interrogate, rewrite narratives, and export reproducible bundles for observers inspecting language-agent clusters.

A local-first, model-agnostic agent operations environment for building and orchestrating specialist agent teams across supported LLM hosts, with owner-scoped packages and enforced permissions.

Desktop tool that runs Claude Code, Codex, and Gemini side by side in isolated git worktrees, enabling developers to compare outputs, review, merge, and benchmark agents.

Supplies infrastructure for supervised, self-improving agent organizations, coordinating shared memory, agent factories, scheduled tasks, and messaging while operating Claude Code or Kimi Code from mobile clients.

A voice-first, local runtime for orchestrating AI agents that converts one-off conversations into auditable, replayable DAG workflows and generates interactive interfaces for them.

Spatial IDE for recursive multi-agent orchestration, organizing shared memory and self-improving workflows inside a navigable graph canvas similar to Obsidian.

Real-time web cockpit for OpenClaw that unifies voice conversations, sub-agent sessions, workspace and file management, automated kanban boards, inline charts, and usage monitoring for operators supervising multiple AI agents.

Open-source AI-native operating system for defining, organizing, and running agent teams across local and cloud devices with shared task boards and execution history.

Self-hostable AI Kanban development environment for teams orchestrating coding agents, coordinating parallel work across multiple providers, reviewing changes, and opening pull requests with no telemetry.

Provides a control-room template for managing Hermes agents, scaling from a single VPS-hosted agent to specialist teams with role separation and orchestrated multi-agent workflows.

A local collaboration hub where humans and multiple coding agents coordinate through channels, tasks, and persistent workspaces. Enables shared context and task orchestration across human-AI development teams.

Orchestrates multiple frontier models to solve tasks in parallel, fusing diverse outputs through debate while restricting writes to a single safe workspace agent.

A distributed multi-agent coordination infrastructure where agents discover peers, form teams, route tasks, and collaborate under governance for persistent organization-level deployments.

Dynamic workflow system for Pi coding agents that routes tasks to specialized subagents, providing model-based routing, git-worktree isolation, cost accounting, journaled resume, and an interactive TUI.

An open-source AI IDE that runs Claude Code, Codex, and other coding agents in parallel with shared workflows.