whatsapp-ai-agent-sdk
The open-source AI agent SDK for WhatsApp. Bring your own model, your own number, your own data. Local-first, no forced cloud, no vendor lock-in.
Runssource: GitHubhomepageTypeScriptMITcommit 9b1b02eb4ae4
TypeScript, MIT licensed. The project labels itself: agent framework, ai agent, chatbot, instinct, llm, local first, muse and opensource.
whatsapp-ai-agent-sdk runs. An Argusic agent installed it in 7 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The full npm workspace builds (tsc), passes typecheck (tsc --noEmit), and passes all 1,202 tests across 9 packages with 0 failures after upgrading to Node 22 and adding the missing rolldown optional native binding.
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 100 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.
- Container had Node.js 18 but project requires Node 22+2 minutes
- rolldown linux-x64 native binding missing after initial pnpm install under Node 182 minutes
- pnpm not available in container, and npm global installs blocked by permissions1 minute
- Install time
- 7 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pnpm test exited 0: core 182p, testkit 38p, productivity 18p, connector-google 38p, whatsapp 311p, harness 370p, connector-cognee 36p, create-agent 160p, e2e 49p = 1202 passed total, 0 failed
- Model tokens used
- 119,933
- Exact commit tested
- 9b1b02eb4ae4
- 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.
tokens used 119,933 Everything passes. Let me compile the final results. **What was done:** 1. Installed pnpm to `~/.local/bin` (no root access for global installs) 2. Ran `pnpm install` — succeeded 3. Ran `pnpm build` — all 9 packages built successfully 4. Initial test run failed with two issues: - **Node.js 18** missing `styleText` on `node:util` (project needs Node 22+). Fixed by installin… - **rolldown** native binding for `linux-x64-gnu` wasn't downloaded (pnpm install happened under… 5. Re-ran `pnpm test` — **all 17 tasks successful** across 9 packages, **1,202 tests passed, 0 fail… 6. `pnpm typecheck` — all 17 tasks successful, no type errors
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 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.
What did not, or is not known
- Took 7 minutes to install, slower than the median of the 61 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 62 agent-framework projects Argusic has installed and timed, whatsapp-ai-agent-sdk was the 41st fastest to reach a running state, and 47 of 62 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 7 minutes after the clone.
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
Topics (from GitHub)
agent-frameworkai-agentchatbotinstinctllmlocal-firstmuseopensourcepersonal-agentpersonal-assistantsdktypescriptwhatsappwhatsapp-agentwhatsapp-aiwhatsapp-apiwhatsapp-botwhatsapp-cloud-api
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/whatsapp-ai-agent-sdk)Questions
- Does whatsapp-ai-agent-sdk run?
- Yes. whatsapp-ai-agent-sdk runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test whatsapp-ai-agent-sdk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9b1b02eb4ae4. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test whatsapp-ai-agent-sdk?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does whatsapp-ai-agent-sdk take to install?
- 7 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 whatsapp-ai-agent-sdk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing whatsapp-ai-agent-sdk?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does whatsapp-ai-agent-sdk compare with the alternatives?
- Of the 62 agent-framework projects Argusic has installed and timed, whatsapp-ai-agent-sdk was the 41st fastest to reach a running state, and 47 of 62 reached one at all.
- Where is the evidence for whatsapp-ai-agent-sdk?
- 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.