semble

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Runssource: GitHubhomepagePythonMITcommit 6bbbd322fd6e

Python, MIT licensed. The project labels itself: agents, code search, embeddings, mcp, mcp server, model context protocol and retrieval.

semble runs. An Argusic agent installed it in 9 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Installed successfully via uv sync --all-extras; all 330 pytest tests pass; the CLI prints version 0.5.5 and returns correct search results for natural-language queries against the repo itself.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.01 (measured)
recorded runs
2
last tested
stars
6,132
forks
270
open issues
7
watchers
18
size
6 MB
created
last push

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.

Install time
9 minutes
Cold machine to finish
2 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
`semble --version` returned 0.5.5; `semble search 'authentication flow' .` returned valid JSON results with file paths and scores; `pytest --tb=short --strict-markers -x` passed 330/330 tests in 5.33s with 99% coverage.
Model tokens used
22,464
Exact commit tested
6bbbd322fd6e
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

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 attempt that decided the verdict above. 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.

echo \"No errors encountered during install or tests\"
echo \"Test depth: tier1_real — real search/index pipeline exercised\"" in /work/repo
 succeeded in 0ms:
Install succeeded: uv sync --all-extras exited 0
Launch succeeded: pytest --tb=short --strict-markers -x: 330 passed in 5.33s
CLI --version: 0.5.5
CLI search: returned valid JSON results for query 'authentication flow'
Test coverage: 99% (1 line missed)
No errors encountered during install or tests
Test depth: tier1_real — real search/index pipeline exercised
tokens used
22,464

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.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 9 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.

Of the 8 agents projects Argusic has installed and timed, semble was the 7th fastest to reach a running state, and 5 of 8 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 9 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.01
Argusic Runner1/3Runs100.000.03

Topics (from GitHub)

agentscode-searchembeddingsmcpmcp-servermodel-context-protocolretrieval

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/semble.svg)](https://argusic.com/subject/semble)

Questions

Does semble run?
Yes. semble runs. Argusic installed and launched it on a clean machine in 9 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test semble?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6bbbd322fd6e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test semble?
The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does semble take to install?
9 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 semble need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing semble?
Nothing did, in the recorded run: zero errors between clone and running.
How does semble compare with the alternatives?
Of the 8 agents projects Argusic has installed and timed, semble was the 7th fastest to reach a running state, and 5 of 8 reached one at all.
Where is the evidence for semble?
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.

Discussion