iva-agent

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

Runssource: GitHubhomepageTypeScriptMITcommit b2cabffbb147

TypeScript, MIT licensed. The project labels itself: agent, ai agent, ai assistant, knowledge graph, llm, local first, long term memory and mcp.

iva-agent runs. An Argusic agent installed it in 35 minutes and hit 10 errors on a clean machine with no GPU, and the whole session was recorded.

Iva v0.4.8 dependencies installed and CLI launches (bin/iva.mjs --help shows all commands); test suite runs at 3646/3649 passing, with three pre-existing test-environment failures: OverlayFS container metadata edge case, EPIPE on Claude subprocess mock pipe, and cross-test module cache pollution in card-store resolver

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 94 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
94 / 100
cost of the verifying run
$0.89 (measured)
recorded runs
1
last tested
stars
306
forks
68
open issues
45
watchers
2
size
56 MB
created
last push

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.

Time lost to each failure while testing iva-agent, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • repair-shell: same-mtime files confuse bash -nt (versions 0.4.1 and 0.4.2)3 minutes
  • Node.js 18.x installed, project requires 24.x2 minutes
  • memory-lock test: dash echo eats -n flag from fake flock script2 minutes
  • brain-alerts test: hardcoded /opt/homebrew/bin/uv path2 minutes
  • uv not available for Python/graph tests1 minute
  • eslint-config test: .claude/ not in expected ignores list1 minute
Install time
35 minutes
Cold machine to finish
64 minutes
Errors hit and fixed
10 hit, 7 fixed with no human help
How the result was proved
npm test ran 3646 pass / 3 fail (99.9%); node bin/iva.mjs --help exited 0 showing all CLI commands
Model tokens used
1,535,978
Exact commit tested
b2cabffbb147
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Install & launch:** `npm ci` completed with 338 packages, and `node bin/iva.mjs --help` exits 0 w…
**Test suite:** 3646 pass, 3 fail (99.9%). The 3 remaining failures are test-environment constraint…
1. **same-inode ABA** — OverlayFS container metadata timestamps (container mtime semantics differ f…
2. **Claude makeTextModel session** — EPIPE on subprocess write in a timing-dependent pipe
3. **card-store same-length rewrite** — Module-level cache leaks between test files in the same pro…
**Fixes applied during setup** (all in test files adapting to this container environment):
- Node 24 installed via nvm (project requires `^24.0`, system had 18.x)
- `uv` installed for Python test dependencies
- Added `utimesSync` to age a file for `bash -nt` in repair test
- Added `.claude/` to expected ESLint ignores in coverage test
- Replaced `echo` with `printf` in fake `flock` scripts (dash eats `-n` from `echo`)
- Resolved `uv` path via `PATH` instead of hardcoded `/opt/homebrew/bin/uv`

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.
  • 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 35 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.
  • Hit 10 errors during setup, 3 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 141 agent projects Argusic has installed and timed, iva-agent was the 133rd fastest to reach a running state, and 94 of 141 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs94.000.89

Topics (from GitHub)

agentai-agentai-assistantknowledge-graphllmlocal-firstlong-term-memorymcpobsidianollamaopen-sourcepersonal-aipersonal-assistantprivacysecond-brainself-hostedtelegramtelegram-bottypescriptvoice-assistant

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/iva-agent.svg)](https://argusic.com/subject/iva-agent)

Questions

Does iva-agent run?
Yes. iva-agent runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 10 errors on the way, and recorded the session.
How did Argusic test iva-agent?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b2cabffbb147. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test iva-agent?
The run that produced this verdict cost $0.89: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does iva-agent take to install?
35 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 iva-agent need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing iva-agent?
10 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does iva-agent compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, iva-agent was the 133rd fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for iva-agent?
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.

Discussion