AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
A control plane for coding agents that you own: Codex, Claude Code, Cursor, Gemini and any ACP agent. Context, policy, history and cost in one place.
Developer toolsTypeScript · JavaScriptGitHub @HarnessDeskOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Open-source control plane for coding agents you own — run Codex, Claude Code, Gemini, Cursor and ACP agents side by side with shared history, permissions, handoffs and audit logs.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
HarnessDesk
Where your agents work — whoever made them.
A control plane for coding agents, owned by no model vendor.
Context, policy, history, tools, cost and evidence in one place — whichever agent does the work. macOS app today.
A turn, as it arrives. Reasoning, then the tool calls, then what changed.
Your machine probably already has several of these:Read the full README ↗Write, check, review, fix, land: every Run follows the Flow you set. When a check fails or a reviewer asks for a change, you watch it loop back, and you see the one step waiting on you.
Skip the tour of agent terminals. See what is working, what is in review and what is blocked on you, with the checks, the diff and the pull request on each card.
Every Team, one board See what needs your answer, what is working and what is ready, across every agent in the Team. Docs →
Follow each step Watch write, check, review and fix as they happen, and see where a Run waits for you. Docs →
Set the process once Set the steps, rules and triggers once, such as who checks, who reviews and what lands after both. Docs →
See what each skill costs Open a skill to see who loads it, where it came from and what it costs, then trim the dead weight. Docs →
Every runtime, ready or not See which agents are ready, which need attention and why, and which account each signs in with. Docs →
Ask first, pick a folder later Start a chat before you choose a project: it gets a folder of its own and waits under Chats. Docs →
Script it, or let your agent run it. Docs →
Also in the box:
Download the signed, notarized app for macOS 13+, Apple silicon or Intel, from the latest release. It updates itself. Then bring an agent you already use: getting started covers each one.
Build from source with Node 22.19+ and pnpm 10:
pnpm install
pnpm build
pnpm app
CONTRIBUTING.md is the way in; security reports go to SECURITY.md.
MIT. HarnessDesk is an independent project, not affiliated with, endorsed by, or sponsored by any of the vendors whose agents it drives; their names appear here only to identify their software. The extension kernel is DeepSeek's Cordis (MIT), and the Codex protocol types are generated from openai/codex (Apache-2.0). See THIRD_PARTY_NOTICES.md and TRADEMARKS.md.