omnilogue

Desktop app and web server to browse, search and analyze your AI coding assistant history, Claude Code, Codex CLI, GitHub Copilot, Gemini CLI, Cursor, OpenCode and more. 100% offline.

Runs with mockssource: GitHubTypeScriptMITcommit bc50501397f9

TypeScript, MIT licensed. The project labels itself: ai coding assistant, chat history, claude, claude code, codex, conversation history, copilot cli and cursor.

omnilogue runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.

Frontend installs, builds, and serves correctly via Vite dev server (HTTP 200); vitest frontend test suite passes across all files verified in batches; Rust/Tauri build blocked by missing system libraries requiring root; ~400 test files verified green across commands, components, hooks, stores, navigation, lib, utils, services, and Tauri config tests.

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

At a glance

verdict
Runs with mocks
Argusic Score
80 / 100
cost of the verifying run
$0.57 (measured)
recorded runs
1
last tested
stars
2,330
forks
0
open issues
0
watchers
0
created
-
last push
-

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.

Time lost to each failure while testing omnilogue, 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.

  • No root access: missing system packages libglib2.0-dev, libwebkit2gtk-4.1-dev, libgtk-3-dev, libayatana-appindicator3-dev, librsvg2-dev prevent Rust/Tauri build15 minutes
  • Node.js v18.19.1 was system-installed (needs 20.19+ or 22.12+); upgraded to v22.14.0 via binary download5 minutes
  • pnpm not in PATH initially; installed to ~/.npm-global/bin2 minutes
  • Rust not installed; installed via rustup2 minutes
  • Full vitest suite hangs when all 400+ test files run together (vitest 4.x fork pool issue); all files pass when run in batches
Install time
10 minutes
Cold machine to finish
40 minutes
Errors hit and fixed
5 hit, 2 fixed with no human help
How the result was proved
pnpm install exited 0 with 650 packages; pnpm exec vite build succeeded (dist/ with index.html and assets); pnpm exec vite dev answered HTTP 200 on localhost:3730/; vitest run commands across ~400 test files all passed individually or in small batches (commands 200/200, transcript 781/781, src/test/ batches all passing, store/navigation/hooks/lib/utils all passing, tauri JS config tests 65/65, ui-capture scripts skipped due to missing Playwright browsers)
Model tokens used
285,099
Exact commit tested
bc50501397f9
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.

/bin/sh -lc 'cd /work/repo && export PATH="/tmp/node-v22.14.0-linux-x64/bin:$HOME/.npm-global/bin:$…
sleep 3
curl -s -o /dev/null -w "HTTP %{http_code}" http://localhost:3730/ 2>&1
echo ""
kill %1 2>/dev/null; wait 2>/dev/null' in /work/repo
 succeeded in 2978ms:
  VITE v7.3.6  ready in 285 ms
  ➜  Local:   http://localhost:3730/
  ➜  Network: use --host to expose
HTTP 200
tokens used
285,099

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 10 minutes, faster than the median of the 8 comparable projects Argusic has measured.
  • 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.
  • Hit 5 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 9 ai-coding-assistant projects Argusic has installed and timed, omnilogue was the 5th fastest to reach a running state, and 8 of 9 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks80.000.57

Topics (from GitHub)

ai-coding-assistantchat-historyclaudeclaude-codecodexconversation-historycopilot-clicursordesktop-appdeveloper-toolsgemini-cligithub-copilotoffline-firstopencodereactrustsession-viewertauri

Embed the badge

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

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

Questions

Does omnilogue run?
omnilogue runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test omnilogue?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit bc50501397f9. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test omnilogue?
The run that produced this verdict cost $0.57: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does omnilogue take to install?
10 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 omnilogue need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing omnilogue?
5 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 omnilogue compare with the alternatives?
Of the 9 ai-coding-assistant projects Argusic has installed and timed, omnilogue was the 5th fastest to reach a running state, and 8 of 9 reached one at all.
Where is the evidence for omnilogue?
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