ethora
SDK monorepo for the Ethora chat / messaging platform. (1) Pick an SDK for your frontend stack. (2) Integrate manually or with ethora-setup. (3) Optionally configure app settings, deploy AI agents etc. Server: ethora.com cloud (free), self-hosted (AWS, Docker, Helm, Cloudron) or a managed dedicated server with SLA. All options: ethora.com/get
Runs with mockssource: GitHubhomepageJavaScriptApache-2.0commit 0f289ba4b045
JavaScript, Apache-2.0 licensed. The project labels itself: ai chat, chat, chat engine, chat sdk, chat widget, chatbot, developer tools and ejabberd.
ethora runs, with stand-ins for the services it depends on. An Argusic agent installed it in 77 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
In this container the Ethora monorepo installs and runs: MCP CLI (stdio+HTTP), backend-integration SDK (13 tests), app-reactjs (build+serve 200), playground (build+serve 200), setup CLI (works end-to-end against a local mock), features renderer, and the React Native SDK test suite (880/881) all execute;
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 92 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.
- sdk-reactjs production build still OOM-killed by the container during vite bundle phase (peak ~1.45GB RSS vs 2GB total incl. agent) even at max-old-space-size=150030 minutes
- sdk-reactjs: npm install fails (exit 137, OOM) because the package.json 'prepare' script runs two full tsc+vite builds; container has 2GB RAM, no swap20 minutes
- setup CLI verification: initial scripted drive accidentally used the real Cloud QA API (network reachable) instead of my mock, writing a real profile18 minutes
- api/tags.js was invalid JavaScript (missing commas between exported tag objects), causing api/index.js (Swagger middleware) to throw SyntaxError and the api/ docs component to be unusable12 minutes
- sdk-reactjs build fails: Vite 7.3.1 (pinned by package.json) requires Node >=20.19, container had Node 18.19.1 and no nvm; system root unavailable6 minutes
- sdk-reactnative: hooksBundle.test.tsx 'usePendingNotification' test fails deterministically (asserts AsyncStorage cleared before the asynchronous effect completes); repo test at __tests__/hooksBundle.test.tsx:3356 minutes
- Install time
- 77 minutes
- Cold machine to finish
- 78 minutes
- Errors hit and fixed
- 8 hit, 8 fixed with no human help
- How the result was proved
- npx vitest run (sdk-reactjs) -> 194/196 files, 1274 passed; sdk-reactnative npx jest -> 880 passed/1 failed (hooksBundle race); backend-integration npm test -> 13 passed; MCP initialize handshake returned serverInfo 26.9.5; app-reactjs vite build ok + vite preview -> HTTP 200 on / and /assets/index.js; playground next build ok + next start -> HTTP 200 on / and /api/config; setup CLI driven against mock 127.0.0.1:8899 -> all 19 steps OK and profile saved; api harness /api-docs/ -> 200 and /swagger.json -> 200 (10 tags, 110 paths)
- Model tokens used
- 2,266,084
- Exact commit tested
- 0f289ba4b045
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
\"test_depth\": \"tier2_mock\",
\"notes\": \"14 submodules fetched; npm installs done for mcp-cli(setup,backend-integration,sdk-r…
\"verified_how\": \"npx vitest run (sdk-reactjs) -> 194/196 files, 1274 passed; sdk-reactnative n…
\"final_state\": \"In this container the Ethora monorepo installs and runs: MCP CLI (stdio+HTTP),…
}
print(json.dumps(result))
PY
python3 /tmp/summarize.py" in /work/repo
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 77, "errors": [{"msg": "sd…
tokens used
2,266,084Replay 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
- Installed in 77 minutes.
- Recovered from all 8 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 | 1/3 | Runs with mocks | 92.00 | 0.50 |
Topics (from GitHub)
ai-chatchatchat-enginechat-sdkchat-widgetchatbotdeveloper-toolsejabberdethoralow-codemcpmessagingmessenger-platformopen-sourceragreactreact-nativereactjswalletxmpp
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ethora)Questions
- Does ethora run?
- ethora runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 77 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test ethora?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0f289ba4b045. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ethora?
- The run that produced this verdict cost $0.50: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ethora take to install?
- 77 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 ethora need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ethora?
- 8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for ethora?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.