linkit
AI bookmark manager for desktop, local-first, offline, read-it-later and PKM tool with AI summaries, semantic search, knowledge graph, and free self-hosted sync. 100% free, no paywalls, no ads.
Runssource: GitHubJavaScriptMITcommit 9edfebb69078
JavaScript, MIT licensed. The project labels itself: ai, bookmark manager, bookmark organizer, bookmarks, bookmarks manager, desktop app, golang and knowledge management.
linkit runs. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The Homebrew cask update script's 8 unit tests pass on Node v18 after a one-line import.meta.dirname fix; the Go utility and Wails desktop app are not buildable in this environment.
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.
- Test file used import.meta.dirname which is Node 21+ only; container has Node v182 minutes
- Install time
- under a minute
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- cd /work/repo && node --test scripts/update-homebrew-cask.test.mjs exited 0, all 8 tests passed. Also confirmed cask updater CLI is idempotent.
- Model tokens used
- 40,037
- Exact commit tested
- 9edfebb69078
- 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.
- A Homebrew Cask for macOS distribution - Scripts for install, dev, and release automation (Homebrew cask updater) - A Go-based identity check utility (requires Go, which is not installed) - README, screenshots, and docs **What I verified:** 1. **Node tests pass**: The `update-homebrew-cask` script and its test suite (8 tests) all pass aft… 2. **The updater CLI works**: Invoking the cask updater with the current version/sha256 confirms it… **What couldn't be verified:** - The Go `check-identity` program cannot be built or run because Go is not installed in this enviro… - The Wails desktop app cannot be built or run because Go and the Wails toolchain are not installed. - The actual application source code is not in this repository (as stated in the README). - Homebrew is not available, so the cask can't be installed.
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.
- Installed in 0.5 minutes, faster than the median of the 231 comparable projects Argusic has measured.
- Recovered from all 1 error 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 232 ai projects Argusic has installed and timed, linkit was the 14th fastest to reach a running state, and 153 of 232 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.
- A quick evaluation: it was running 0.5 minutes after the clone.
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)
aibookmark-managerbookmark-organizerbookmarksbookmarks-managerdesktop-appgolangknowledge-managementlocal-firstoffline-firstorganizerpkmprivacyproductivityreactread-it-latersecond-brainself-hostedsemantic-searchwails
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/linkit)Questions
- Does linkit run?
- Yes. linkit runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test linkit?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9edfebb69078. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test linkit?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does linkit take to install?
- 0.5 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 linkit need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing linkit?
- 1 thing 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 linkit compare with the alternatives?
- Of the 232 ai projects Argusic has installed and timed, linkit was the 14th fastest to reach a running state, and 153 of 232 reached one at all.
- Where is the evidence for linkit?
- 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.