OpenContext
A personal context store for AI agents and assistants, reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
Runssource: GitHubhomepageJavaScriptMITcommit 0649e7134346
JavaScript, MIT licensed. The project labels itself: agent, ai, ai agents, claude code, cli, codex, context and context management.
OpenContext runs. An Argusic agent installed it in 1 minute and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
OpenContext CLI installs, builds UI, runs all 59 Node.js tests (0 fail), starts MCP server via oc mcp, starts web UI via oc ui, and all folder/doc/config CLI commands work on node 18.19.1. Rust tests require cargo (not installed).
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, 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.
- npm install engine warnings: commander, vectra, react-router, undici, cheerio require node>=20 but container has node 18
- Rust tests skipped: cargo not found in container
- 4 native tests skipped: optional @aicontextlab/core-native not installed
- Install time
- 1 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run test exited 0 (44 pass, 4 skip, 0 fail); node --test tests/integration/*.test.js exited 0 (9 pass); ./bin/oc.js --help printed usage; ./bin/oc.js mcp --test printed 'OpenContext MCP server running'; ./bin/oc.js ui --no-open started web UI at http://127.0.0.1:4322
- Model tokens used
- 37,282
- Exact commit tested
- 0649e7134346
- 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.
OpenContext MCP server running (stdio) exec /bin/sh -lc 'cd /work/repo && ./bin/oc.js folder rm test-folder --force 2>&1; ./bin/oc.js folder ls… succeeded in 290ms: Removed folder "test-folder". (no folders) All tests pass, UI builds, CLI commands work, MCP server starts. The only gaps are Rust tests (no `… `test-folder` cleaned up. Here's the final report: tokens used 37,282 All tests pass, UI builds, CLI commands work, MCP server starts. The only gaps are Rust tests (no `… `test-folder` cleaned up. Here's the final report:
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 1 minute, faster than the median of the 137 comparable projects Argusic has measured.
- Recovered from all 3 errors 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 138 agent projects Argusic has installed and timed, OpenContext was the 14th fastest to reach a running state, and 92 of 138 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 1 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)
agentaiai-agentsclaude-codeclicodexcontextcontext-managementcursordesktop-appdeveloper-toolsknowledge-basemcpopencodetauri
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opencontext)Questions
- Does OpenContext run?
- Yes. OpenContext runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test OpenContext?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0649e7134346. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test OpenContext?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenContext take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does OpenContext need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenContext?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does OpenContext compare with the alternatives?
- Of the 138 agent projects Argusic has installed and timed, OpenContext was the 14th fastest to reach a running state, and 92 of 138 reached one at all.
- Where is the evidence for OpenContext?
- 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.