waha
WAHA - WhatsApp HTTP API (REST API) that you can configure in a click! Multiple engines: WEBJS (browser based), NOWEB (websocket nodejs), GOWS (websocket go), WPP (browser)
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 55a7d78e3fea
TypeScript, Apache-2.0 licensed. The project labels itself: ai bot, bot, http api, mcp, mcp server, mcp whatsapp, python bot and whatsapp.
waha runs, with stand-ins for the services it depends on. An Argusic agent installed it in 24 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The project installs, builds with no errors, all 31 unit test suites (308 tests) pass, and the server starts and responds correctly on /api/version, /api/server/status, and /api/sessions endpoints when invoked via X-Api-Key auth.
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.
- PhoneNumbersCacheRepository Date handling broken with SQLite — date comparisons produced wrong results and NaN dates5 minutes
- @adiwajshing/baileys is ESM-only, Jest could not parse it — 4 test suites failed with SyntaxError4 minutes
- Missing media config in session.abc.test.ts buildSession() — TypeError: Cannot read properties of undefined (reading 'events')3 minutes
- Node.js v18.19.1 in container but .nvmrc requires v24.112 minutes
- Install time
- 24 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- yarn test:unit exited 0, 31 suites passed, 308 tests passed, 2 skipped; server launched and responded: GET /api/version returned 200 with version info, GET /api/server/status returned 200 with uptime, GET /api/sessions returned 200 with []
- Model tokens used
- 564,479
- Exact commit tested
- 55a7d78e3fea
- 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.
4. **Build**: `yarn build` completed silently (no errors).
**Fixes applied:**
- **session.abc.test.ts**: `buildSession()` was missing the `media` config property, causing `TypeE…
- **PhoneNumbersCacheRepository.ts**: SQLite3 stores datetime columns as epoch‑millis numbers. Pass…
- **Baileys ESM import**: `@adiwajshing/baileys` ships ESM‑only, which choked Jest. Added a minimal…
**Verification:**
- `yarn test:unit` — **31 suites passed, 308 tests passed, 2 skipped** (previously 4 failed suites).
- `yarn build` — compiles cleanly.
- Server launch: exported the required env vars and ran `node dist/main.js`. It printed `Nest appli…
- `GET /api/version` → `{"version":"2026.9.1","engine":"NOWEB","tier":"CORE",...}` (200)
- `GET /api/server/status` → `{"startTimestamp":...,"uptime":...}` (200)
- `GET /api/sessions` → `[]` (200)Replay 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 24 minutes.
- Recovered from all 4 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.
- Measured 2 times, so the result is not a one-off.
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.
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 with mocks | 92.00 | 0.13 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.29 |
Topics (from GitHub)
ai-botbothttp-apimcpmcp-servermcp-whatsapppython-botwhatsappwhatsapp-apiwhatsapp-automationwhatsapp-botwhatsapp-chatwhatsapp-mcpwhatsapp-webwhatsapp-web-api
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/waha)Questions
- Does waha run?
- waha runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 24 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test waha?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 55a7d78e3fea. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test waha?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does waha take to install?
- 24 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 waha need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing waha?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for waha?
- 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.