lean-ctx
LeanCTX, Context Intelligence for AI systems.
Runssource: GitHubhomepageRustApache-2.0commit 1f8d2d35812d
Rust, Apache-2.0 licensed. The project labels itself: agentic coding, ai, ai agents, ai coding, claude code, context engineering, context intelligence and context layer.
lean-ctx runs. An Argusic agent installed it in 62 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
lean-ctx 3.10.1 release binary is built, installed at ~/.cargo/bin/lean-ctx, and fully functional with all CLI commands working.
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.
- Rust toolchain not pre-installed in the container2 minutes
- cargo test --lib (lib test) hits 8GB cgroup memory limit during compilation of the test binary due to all tree-sitter grammar crates being linked. The test binary with --cfg test requires ~7.5GB+, exceeding the 8GB limit.
- Install time
- 62 minutes
- Cold machine to finish
- 65 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 2,058,143
- Exact commit tested
- 1f8d2d35812d
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
Now let me prepare the final report. The story of this session: 1. **Install:** Rust wasn't in the container. Installed rustup, then built `lean-ctx` from source (… 2. **Launch:** The binary was installed and verified. `lean-ctx --version`, `lean-ctx --help`, `lea… 3. **Tests:** The `cargo test --lib` compilation keeps hitting the 8GB cgroup memory limit. The cra… Let me produce the final answer: tokens used 2,058,143 Now let me prepare the final report. The story of this session: 1. **Install:** Rust wasn't in the container. Installed rustup, then built `lean-ctx` from source (… 2. **Launch:** The binary was installed and verified. `lean-ctx --version`, `lean-ctx --help`, `lea… 3. **Tests:** The `cargo test --lib` compilation keeps hitting the 8GB cgroup memory limit. The cra… Let me produce the final answer:
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.
- Recovered from all 2 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 62 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
Of the 9 agentic-coding projects Argusic has installed and timed, lean-ctx was the 9th fastest to reach a running state, and 8 of 9 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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Ran out of time | 0.00 | 0.28 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.74 |
Topics (from GitHub)
agentic-codingaiai-agentsai-codingclaude-codecontext-engineeringcontext-intelligencecontext-layercopilotcursordeveloper-toolsgemini-clilean-contextllmmcpmcp-serverreduce-token-costsrusttoken-optimization
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/lean-ctx)Questions
- Does lean-ctx run?
- Yes. lean-ctx runs. Argusic installed and launched it on a clean machine in 62 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test lean-ctx?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1f8d2d35812d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test lean-ctx?
- The run that produced this verdict cost $0.74: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does lean-ctx take to install?
- 62 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 lean-ctx need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing lean-ctx?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does lean-ctx compare with the alternatives?
- Of the 9 agentic-coding projects Argusic has installed and timed, lean-ctx was the 9th fastest to reach a running state, and 8 of 9 reached one at all.
- Where is the evidence for lean-ctx?
- All 2 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.