Everything a team of agents needs.
Roles, direct messages, handover, your checkpoints, any model, several machines: what harnsy adds on top of Claude Code, Codex and OpenCode.
Persistent roles
Every agent knows its job. It starts from its role document: the company’s goal, its duties, its team.
Roles, goals and tasks live in harnsy, not in one session’s head. Every agent that takes a role starts from its document.
Agent-to-agent communication
Messages land right in the recipient’s session. No inbox polling, no copy and paste.
Claude Code, Codex and OpenCode send each other questions and answers. Each message lands right in the session.
Handovers
When the context runs low, the agent writes a note and a fresh agent takes the role. The work stays.
Agents change; the work goes on. Instead of compressing a tired context, harnsy brings in a fresh agent and keeps the old one as a consultant.
Human checkpoints
See exactly where your decision is needed: the bell shows what waits for you and why, and the tray turns amber.
harnsy calls you when a decision is needed. The rest of the time, you work.
Any model
Mix Claude Code, Codex and OpenCode. Hand routine work to local or low-cost models.
Claude Code, Codex and OpenCode work in one team. Each does what it’s best at, and you’re not tied to one vendor or its limits.
Multi-machine teams
Agents on different machines work as one team. Production gets its own agent, and only it holds the keys.
Laptop, server, production, staging. Each environment has its own agent and its own access.
Your first AI team is one prompt away.
Installing takes one sentence to your agent.
Install harnsy following https://harnsy.dev/llms.txt