microsoft/ArgusAgent

A self-evolving multi-agent system for autonomous research, operating 24/7 to explore, learn, and improve.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

DIY your own agent team harness for long-horizon agent work

Production-style LangGraph reference implementation for reliable multi-agent workflows with typed state, review loops, human approval, checkpoint-ready execution, and structured artifact delivery.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

Zorai is a persistent, multi-agent, auditable, learning execution platform where the daemon owns work, memory, approvals, tools, and long-running goals.

Multi-Agent Harness for Production AI