abacusai-bot
100% free, open-source personal agents for your messaging apps, tools, and services
Runssource: GitHubTypeScriptMITcommit 68c307fe16b5
TypeScript, MIT licensed. The project labels itself: agent, ai, ai agents, android, cli, coding agent, developer tools and electron.
abacusai-bot runs. An Argusic agent installed it in 12 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 AbacusAI Bot desktop app builds from source, 3920 unit tests pass across all packages, and the Electron app launches to the authentication screen on the virtual display.
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. 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.
- Node.js was v18, project requires v222 minutes
- Electron binary not downloaded at install time, missing LICENSES.chromium.html2 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pnpm test:unit (turbo) passed: 331 files, 3920 tests, 3 skipped; electron --version returned v44.9.3; electron app launched on :99 and reached auth screen
- Model tokens used
- 54,516
- Exact commit tested
- 68c307fe16b5
- 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.
## Tests `pnpm test:unit` (via turbo) — all passed: - **331 test files passed** (out of 331) - **3920 tests passed**, 3 skipped - Projects tested: `@abacus-ai/desktop` (main + preload), `@abacus-ai/agent`, `@abacus-ai/test-supp… ## App Launch Electron app launched successfully with `--no-sandbox` on the virtual display (`:99`): - All 7 migrations applied without error - Update service reported `dev build, not checking for updates` - `[funnel] screen_auth` — reached the authentication screen - DBus errors (no system bus in container) are expected and non-fatal - `electron --version` confirmed **v44.9.3**
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 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.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 135 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 136 agent projects Argusic has installed and timed, abacusai-bot was the 84th fastest to reach a running state, and 88 of 136 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.
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)
agentaiai-agentsandroidclicoding-agentdeveloper-toolselectroniosllmlocal-llmmcpopenroutersandboxtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/abacusai-bot)Questions
- Does abacusai-bot run?
- Yes. abacusai-bot runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test abacusai-bot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 68c307fe16b5. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test abacusai-bot?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does abacusai-bot take to install?
- 12 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 abacusai-bot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing abacusai-bot?
- 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.
- How does abacusai-bot compare with the alternatives?
- Of the 136 agent projects Argusic has installed and timed, abacusai-bot was the 84th fastest to reach a running state, and 88 of 136 reached one at all.
- Where is the evidence for abacusai-bot?
- 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.