opencode-mem
OpenCode plugin that gives coding agents persistent memory using local vector database
Runs with mockssource: GitHubTypeScriptMITcommit a2072d75eaec
TypeScript, MIT licensed. The project labels itself: ai, libsql, memory, opencode, opencode plugin, turso and vector database.
opencode-mem runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.1 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Install, TypeScript compilation, all 767 tests, full build (TS + web UI), and the web server all succeed on Linux/amd64 with Bun 1.4.3. The package.json was patched to use bun --bun for the web:build script, because system Node 18 cannot run the project's modern Svelte/Vite toolchain.
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 92 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.
- web:build failed on system Node 18 — svelte-check/vite require Node >=20 or Bun's runtime4 minutes
- Install time
- under a minute
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- bun test: 763 pass, 4 skip, 0 fail across 109 files; bun --bun run build: builds TS + web UI; server start: GET /api/health returned 200, GET /api/stats returned 401 (as expected without token)
- Model tokens used
- 202,249
- Exact commit tested
- a2072d75eaec
- 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.
$ tsc --noEmit
--- Full build ---
../dist/web/assets/index-XAqiCeXa.js 441.20 kB │ gzip: 136.54 kB
✓ built in 1.51s
--- Server test ---
Package version: 2.31.2
GET /api/health: 200 {"success":true,"status":"ok","authEnabled":false}
GET /api/stats: 401 {"success":false,"error":"Unauthorized"}
All working perfectly. Let me compile the final ARGUSIC_RESULT.
tokens used
202,249
All working perfectly. Let me compile the final ARGUSIC_RESULT.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 0.1 minutes, faster than the median of the 151 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.
- 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 152 ai projects Argusic has installed and timed, opencode-mem was the 1st fastest to reach a running state, and 99 of 152 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.12 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opencode-mem)Questions
- Does opencode-mem run?
- opencode-mem runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test opencode-mem?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a2072d75eaec. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test opencode-mem?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does opencode-mem take to install?
- 0.1 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 opencode-mem need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing opencode-mem?
- 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 opencode-mem compare with the alternatives?
- Of the 152 ai projects Argusic has installed and timed, opencode-mem was the 1st fastest to reach a running state, and 99 of 152 reached one at all.
- Where is the evidence for opencode-mem?
- 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.