omnigent vs qm
Open-source meta-harness over Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and custom agents: swap harnesses without rewriting, enforce policies and sandboxes, follow sessions from any device. — versus — Multiplayer agent harness for startups: every employee gets a scoped workspace — memory, files, keychain, crons, sandbox — in Slack and web, with Pi/OpenCode/Codex/Claude Code swappable underneath.
Both are vendor-neutral layers driving Claude Code/Codex/OpenCode/Pi with policy and sandbox enforcement. Omnigent is a meta-harness for the operator's own machine; qm turns the same idea into a multi-tenant company deployment with Slack, per-person scopes and org admin.
| omnigent | qm | |
|---|---|---|
| Stars | 7.9k | 7.2k |
| Forks | 1.2k | 758 |
| Language | Python | TypeScript |
| License | Apache-2.0 | MIT |
| Last activity | 4 days ago | 2 days ago |
| Topics | agents, orchestration, coding | agents, orchestration |
| Curated connections | 6 | 3 |
omnigent — the curator's take
Use when you run several coding harnesses and want one control plane: mix agents in a session, gate risky actions with policies, run in Modal/Daytona/E2B/K8s sandboxes, and pick a session up from phone or browser. Team sharing (co-drive, fork) is a real differentiator. NOT if you live in one CLI on one laptop — it's a server + desktop app stack, and it's alpha; expect churn. Apache-2.0.
qm — the curator's take
The org-level answer to "give everyone at the company an agent": per-person and per-channel scopes keep memory, credentials and files isolated, and the harness underneath (Pi, OpenCode, Codex, Claude Code) is swappable, so the deployment isn't a bet on one vendor. Security postures (strict/auto/dangerous) plus a hard command-deny policy that survives even Dangerous mode are unusually well thought through. NOT for individuals — this is Postgres + sandbox + deployment-repo infrastructure; a solo dev should run a harness directly. Quirk: contributions are accepted as prose ADRs, not code PRs.