herdr-web-ui
Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote PCs over SSH, web push alerts
Runssource: GitHubhomepageTypeScriptMITcommit f35aeae75762
TypeScript, MIT licensed. The project labels itself: agentic coding, ai agents, bun, claude code, codex, coding agents, herdr and herdr plugin.
herdr-web-ui runs. An Argusic agent installed it in 17 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The herdr-web-ui server starts, connects to herdr 0.9.5, answers health/session/access APIs with 200, and serves the built frontend via HTTP on port 7317.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Bun not installed; install.sh requires unzip which is not available2 minutes
- herdr binary not found for integration tests1 minute
- Install time
- 17 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- bun run test:unit exited 0 (904 pass, 2 skip, 0 fail); bun run test:integration ran (167 pass, 7 fail); curl http://127.0.0.1:7317/api/health returned 200 with {"ok":true}; curl http://127.0.0.1:7317/ returned 200 with index.html
- Model tokens used
- 307,654
- Exact commit tested
- f35aeae75762
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
6. **Integration tests**: Installed herdr 0.9.5 binary from GitHub releases. `bun run test:integrat…
- 3 omo-related (omo binary not installed — expected, not part of this project)
- 1 WebSocket PTY session timeout (herdr attach timing edge case)
- 1 attach-held contract (double-error-counting race)
- 2 omo prompt binding (omo not installed)
These are all related to optional external dependencies (omo) or timing-sensitive edge cases, no…
7. **Live server verification**: Started the server connected to herdr 0.9.5, confirmed:
- `GET /api/health` → 200 `{"ok":true,"herdr":{"version":"0.9.5","protocol":22,"terminal_attach"…
- `GET /api/session` → 200 with valid snapshot
- `GET /api/access` → 200 with tailscale state report
- `GET /` → 200 text/html
- Static JS assets served at 200Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 17 minutes.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.07 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Topics (from GitHub)
agentic-codingai-agentsbunclaude-codecodexcoding-agentsherdrherdr-pluginmobileopencodeovispush-notificationspwareactremote-accessself-hostedtailscaleterminalweb-terminalxterm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/herdr-web-ui)Questions
- Does herdr-web-ui run?
- Yes. herdr-web-ui runs. Argusic installed and launched it on a clean machine in 17 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test herdr-web-ui?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f35aeae75762. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test herdr-web-ui?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does herdr-web-ui take to install?
- 17 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does herdr-web-ui need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing herdr-web-ui?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for herdr-web-ui?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.