meridian
Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily, and automatically drafts your project tickets for you.
Runssource: GitHubhomepageRustNOASSERTIONcommit a100468211b3
Rust, NOASSERTION licensed. The project labels itself: agents, ai, ai memory, chatgpt, claude, claude code, developer tools and gemini.
meridian runs. An Argusic agent installed it in 34 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Meridian daemon and smoke-test binaries compile in debug+release; daemon launches and produces structured log output via meridian logs; Next.js UI dashboard builds to static export; 1072/1073 unit tests, 68/68 integration tests, 21/21 OAuth tests, 906/906 UI tests pass. Tauri tray is Linux-unbuildable (requires macOS or Windows per README)
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 90 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.
- Flaky timing test `a_failed_process_with_an_inconclusive_verify_reports_the_process_failure` fails under concurrent load (documented race condition in source, grace/poll_interval may need widening)
- Tauri tray crate (meridian-tray) requires GTK/WebKit dev headers (libgtk-3-dev libwebkit2gtk) not available on Linux without root
- Install time
- 34 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- cargo test -p meridian --lib: 1072 stable passed, 1 known-flaky; cargo test --test '*': 68 passed; cargo test -p meridian-oauth: 21 passed; cd ui && npm run build: OK; cd ui && bun test: 906 passed; ./target/release/meridian logs: binary starts, produces OTEL log/spans
- Model tokens used
- 731,841
- Exact commit tested
- a100468211b3
- 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.
echo 'Error 1: flaky timing test (documented in source, passes in isolation)'
echo 'Error 2: Tauri tray cannot build on Linux (missing GTK dev headers, no root)'" in /work/repo
succeeded in 0ms:
Elapsed start 22:23 end ~22:57 = 34 min
Error 1: flaky timing test (documented in source, passes in isolation)
Error 2: Tauri tray cannot build on Linux (missing GTK dev headers, no root)
exec
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\": true, \"launch_succeeded\": true, \"inst…
succeeded in 0ms:
2026-10-21T22:58:12.229299Z ERROR codex_core::session: failed to record rollout items: thread 01a16…
tokens used
731,841Replay 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.
What did not, or is not known
- Took 34 minutes to install, slower than the median of the 40 comparable projects Argusic has measured.
- Hit 2 errors during setup, 1 of which were not solved.
- Its license file could not be classified automatically, so check it yourself before using it.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 41 agents projects Argusic has installed and timed, meridian was the 40th fastest to reach a running state, and 29 of 41 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)
agentsaiai-memorychatgptclaudeclaude-codedeveloper-toolsgeminijirallmlocal-firstmcpproductivityproductivity-toolsscreen-recordingtime-trackertime-trackingtimelinework-journalworklog
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/meridian)Questions
- Does meridian run?
- Yes. meridian runs. Argusic installed and launched it on a clean machine in 34 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test meridian?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a100468211b3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test meridian?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does meridian take to install?
- 34 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 meridian need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing meridian?
- 2 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does meridian compare with the alternatives?
- Of the 41 agents projects Argusic has installed and timed, meridian was the 40th fastest to reach a running state, and 29 of 41 reached one at all.
- Where is the evidence for meridian?
- 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.