Open Source Agent Orchestration Tools
Agent orchestration is the coordination of AI agents as they work toward shared or connected goals. Orchestration systems assign tasks, manage handoffs, combine results, and track progress across agents, models, and tools. They help structure complex work that a single agent may struggle to complete, while providing ways to manage execution, state, and human oversight.
Open source tools in this area include agent frameworks, runtimes, workflow engines, and control panels for supervising agent teams. When choosing one, consider its maturity, license, maintenance activity, deployment requirements, support for different models and tools, and how it handles errors, permissions, and persistent state. These tools are useful to developers and teams building multi-agent applications or coordinating AI-assisted coding and operations.
47 repositories · updated October 4, 2026
openmake_llm: Coordinate AI Models, Agents, and Tools
OpenMake is a self-hosted AI workspace that coordinates chat models, agents, and tools in one place. It suits people who want multi-step AI workflows with local or open-weight models, while keeping infrastructure and model choices under their control.
uni-agent: Train Long-Horizon Agents at Scale
Uni-Agent is a Python framework for running and training long-horizon agents through a shared interaction stack. It helps agent developers connect harnesses, tasks, tools, and sandboxes for scalable inference, evaluation, and reinforcement learning.
OpenCompany: Coordinate AI Agents to Run a One-Person Business
OpenCompany is a Rust-based host for configuring and running companies staffed by coordinated AI agents. It is aimed at solo operators who want to delegate business functions while retaining key decisions, and is explicitly not production-ready.
vicoa: Coordinate Coding Agents Across Devices
Vicoa is a self-hostable command center for running coding agents on local and remote machines. It brings agent sessions, task management, and review tools to desktop, web, mobile, and CLI clients.
cccc: Coordinate Coding Agents in Persistent Groups
CCCC is a local-first orchestrator for coordinating coding agents across runtimes, machines, and groups. It provides durable message history, delivery tracking, and Web, CLI, MCP, and chat-platform controls for teams that need ongoing collaboration.
bernstein: Govern and Orchestrate AI Agents
Bernstein coordinates AI-agent workloads through declarative policies, approval gates, and isolated task execution. It records runs for replay and offline verification, helping teams that need accountable, auditable automation.
Memoh: Give AI Agents Dedicated Cloud Computers
Memoh is a multi-agent platform that gives each agent an isolated, always-on workspace with a desktop, browser, network access, and long-term memory. Use your own API keys or host agents such as Claude Code and Codex, either in Memoh Cloud or on your own infrastructure.
Graphon: Execute Agentic AI Workflows as Graphs
Graphon is a Python engine for building and running agentic AI workflows as graphs. It suits developers who need event-driven execution, shared workflow state, and extensible integrations rather than a standalone chat interface.
agent-orchestrator: Coordinate Coding Agents from Plan to Merge
Agent Orchestrator is a desktop workspace for planning and supervising multiple coding agents across a project. It gives Git-backed tasks isolated worktrees and brings agent activity, pull requests, CI, and reviews into one live view.
aiwg: Reuse AI Workflows Across Coding Tools
AIWG deploys reusable project context, specialist agents, and structured workflows to multiple AI coding tools. It helps individuals and teams carry decisions, reviews, and procedures across tasks and sessions.
uta: Coordinate Coding Agents Across CLI Providers
uta is a Go CLI that breaks goals into parallel tasks, routes them to installed coding-agent CLIs, and records each run for review or continuation. It suits developers who need cross-provider orchestration and traceable agent workflows.
coven: Run Project-Scoped AI Coding-Agent Sessions
Coven is a local-first Rust runtime for running coding-agent tools within project boundaries. It provides shared session management, durable event storage, and a local API for developers coordinating work across supported harnesses.