claude-context
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 6fc318b4e3ce
TypeScript, MIT licensed. The project labels itself: agent, agentic rag, ai coding, claude code, code generation, code search, cursor and embedding.
claude-context runs, with stand-ins for the services it depends on. An Argusic agent installed it in 18 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Install, build, typecheck, lint config, and all 35 tests pass across the monorepo. The core indexing pipeline runs end-to-end with mock providers. The MCP server starts but requires real OpenAI API key and Milvus credentials for production use.
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.
- pnpm install blocked by ERR_PNPM_IGNORED_BUILDS (18 packages with unapproved build scripts)5 minutes
- Node.js v18 (project requires >=20)2 minutes
- pnpm not found in PATH1 minute
- MCP server and example require real OpenAI API key and Milvus/Zilliz credentials
- Install time
- 18 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm --filter @zilliz/claude-context-core test exited 0, 29 passed; pnpm typecheck passed across all packages; core dist built and loaded via node -e with mock providers indexed 109 files and performed search; MCP server started (logs show 'Fatal error: OPENAI_API_KEY is required')
- Model tokens used
- 113,955
- Exact commit tested
- 6fc318b4e3ce
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
packages/mcp typecheck: Done exec /bin/sh -lc 'cd /work/repo && git diff --stat' in /work/repo succeeded in 13ms: exec /bin/sh -lc 'cd /work/repo && date -u "+%s"' in /work/repo succeeded in 0ms: 1790127075 All good. Here's my final summary: tokens used 113,955 All good. Here's my final summary:
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
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
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.
- Took 18 minutes to install, slower than the median of the 32 comparable projects Argusic has measured.
Of the 33 agent projects Argusic has installed and timed, claude-context was the 27th fastest to reach a running state, and 25 of 33 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 | 3/3 | Runs with mocks | 92.00 | 0.10 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.06 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
agentagentic-ragai-codingclaude-codecode-generationcode-searchcursorembeddinggemini-climcpmerkle-treenodejsopenairagsemantic-searchtypescriptvector-databasevibe-codingvoyage-aivscode-extension
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-context)Questions
- Does claude-context run?
- claude-context runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 18 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test claude-context?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6fc318b4e3ce. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test claude-context?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-context take to install?
- 18 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 claude-context need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-context?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does claude-context compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, claude-context was the 27th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for claude-context?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.