B
An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.
Runs with mockssource: GitHubPythonMITcommit d34943d3ea89
Python, MIT licensed. The project labels itself: ai, ai agent, ai companion, artificial intelligence, autonomous agent, computer vision, desktop assistant and llm.
B runs, with stand-ins for the services it depends on. An Argusic agent installed it in 23 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 18 modules initialize correctly: EventBus, KinematicsEngine, WindowManager, FaceRenderer, ChatBubble, InputBox, StateMachine, CognitiveEngine (Groq mode), Vision sensors (semantic + mss), WindowTracker, AutonomyEngine, and VoiceEngine all boot to 'B is alive' with the Qt event loop running at ~62fps. Windows-only features (click-through, hotkeys) gracefully disabled.
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.
- ctypes.windll not available on Linux5 minutes
- uiautomation import fails on Linux (COM only on Windows)3 minutes
- PortAudio library not found (sounddevice)3 minutes
- No module 'torch' for audio/ears.py2 minutes
- auto.uiautomation.SetGlobalSearchTimeout missing2 minutes
- OCR result has no .lines attribute2 minutes
- Install time
- 23 minutes
- Cold machine to finish
- 28 minutes
- Errors hit and fixed
- 8 hit, 8 fixed with no human help
- How the result was proved
- QT_QPA_PLATFORM=offscreen timeout 8 /work/repo/venv/bin/python main.py -- all 18 modules initialized without errors, 60fps tick timer started, event loop stayed alive for full 8s run with 'B is alive' logged. Piper TTS/DSP vocoder loaded successfully from bundled ONNX model.
- Model tokens used
- 644,591
- Exact commit tested
- d34943d3ea89
- 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.
| 2 | `No module named 'uiautomation'` + COM import error | Created mock `uiautomation.py` in site-… | 3 | `ModuleNotFoundError: No module named 'torch'` | Created mock `torch/__init__.py` | 2 min | | 4 | `OSError: PortAudio library not found` (sounddevice) | Created mock `sounddevice.py` | 3 min | | 5 | `AttributeError: module 'ctypes' has no attribute 'windll'` (Linux) | Added ctypes.windll com… | 6 | `auto.uiautomation.SetGlobalSearchTimeout(...)` AttributeError | Added missing functions to u… | 7 | `module 'winocr' has no attribute 'recognize_pil'` | Enhanced winocr mock with `recognize_pil… | 8 | `'str' object has no attribute 'lines'` (OCR result shape) | Enhanced winocr mock to return o… **Calculation:** - Venv created: 19:23 UTC (birth time of venv python binary) - Final verification run: 19:46 UTC - **Total elapsed: ~23 minutes** - Errors sum to ~19 minutes of fix time (reasonable given debugging and iteration)
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
- Recovered from all 8 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, 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.
- Took 23 minutes to install, slower than the median of the 174 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 175 ai projects Argusic has installed and timed, B was the 150th fastest to reach a running state, and 114 of 175 reached one at all.
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 | 0.09 |
Topics (from GitHub)
aiai-agentai-companionartificial-intelligenceautonomous-agentcomputer-visiondesktop-assistantllmonnxpythonspeech-to-texttext-to-speech
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/b)Questions
- Does B run?
- B runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 23 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test B?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d34943d3ea89. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test B?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does B take to install?
- 23 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 B need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing B?
- 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.
- How does B compare with the alternatives?
- Of the 175 ai projects Argusic has installed and timed, B was the 150th fastest to reach a running state, and 114 of 175 reached one at all.
- Where is the evidence for B?
- 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.