llm-ls

LSP server leveraging LLMs for code completion (and more?)

Runs with mockssource: GitHubRustApache-2.0commit 89fa8a2e89b0

Rust, Apache-2.0 licensed. The project labels itself: ai, code generation, huggingface, ide, llamacpp, llm, lsp and lsp server.

llm-ls runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

llm-ls v0.5.4 LSP server builds, passes all 13 unit tests, starts on TCP port, and returns completions from a TGI-backend mock server

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.09 (measured)
recorded runs
2
last tested
stars
887
forks
73
open issues
27
watchers
21
size
0 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.

Time lost to each failure while testing llm-ls, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • mock_server missing /generate route for TGI backend compatibility2 minutes
Install time
10 minutes
Cold machine to finish
11 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
cargo test returned 13 passed (5 in llm-ls, 8 in lsp-client); python3 LSP client connected to llm-ls on tcp://127.0.0.1:4243, performed initialize, received serverInfo {"name":"llm-ls","version":"0.5.4"}, sent textDocument/didOpen and llm-ls/getCompletions against mock_server TGI backend, received completion result with generated_text "dummy"
Model tokens used
106,127
Exact commit tested
89fa8a2e89b0
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 1, 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.

First cargo build completed around
2026-11-21 05:07:32.617190435 +0000
Let me compute: Started around 05:05 (first exec session), now 05:15. So about 10 minutes total.
Let me confirm the mock was rebuilt properly:
exec
/bin/sh -lc "stat --format='%y' /work/repo/target/debug/mock_server" in /work/repo
 succeeded in 0ms:
2026-11-21 05:15:04.344778228 +0000
Good. Now let me compile the final ARGUSIC_RESULT.
tokens used
106,127
Good. Now 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

  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 10 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.

Of the 237 ai projects Argusic has installed and timed, llm-ls was the 171st fastest to reach a running state, and 168 of 237 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.09
Argusic Runner1/3Runs with mocks92.000.31

Topics (from GitHub)

aicode-generationhuggingfaceidellamacppllmlsplsp-serveropenaiself-hosted

Embed the badge

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

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

Questions

Does llm-ls run?
llm-ls runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test llm-ls?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 89fa8a2e89b0. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test llm-ls?
The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does llm-ls take to install?
10 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 llm-ls need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing llm-ls?
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 llm-ls compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, llm-ls was the 171st fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for llm-ls?
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