omnigent vs tailclaude
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 — Claude Code from any browser via your Tailscale tailnet — streaming chat UI, session history, model switching and cost dashboards; no SSH, no terminal.
Covers tailclaude's use case — driving your coding agent from any browser/phone — but for many harnesses, at the cost of a much heavier stack.
| omnigent | tailclaude | |
|---|---|---|
| Stars | 7.5k | 207 |
| Forks | 1.1k | 22 |
| Language | Python | TypeScript |
| License | Apache-2.0 | — |
| Last activity | today | 4 months ago |
| Topics | agents, orchestration, coding | coding |
| Curated connections | 5 | 2 |
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.
tailclaude — the curator's take
The 'doom coding from your phone' setup without the terminal: publish Claude Code to your tailnet, scan a QR code, get a touch-optimized chat UI with streaming, full session history and cost dashboards — Tailscale handles auth and transport, so nothing new is exposed. The caveats are serious though: the repo ships NO license (all rights reserved by default — you can run it, not fork or redistribute), it's young (~200 stars) and has been quiet for months. Treat it as a clever pattern to evaluate, NOT infrastructure to depend on.