lancedb

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Runssource: GitHubhomepageRustApache-2.0commit 221658602312

Rust, Apache-2.0 licensed. The project labels itself: approximate nearest neighbor search, image search, nearest neighbor search, recommender system, search engine, semantic search, similarity search and vector database.

lancedb runs. An Argusic agent installed it in 22 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.

Rust core crate lancedb compiles and passes all 73 integration tests; Python bindings install, import, and pass 1368 tests; the local (in-process) embedding store works end-to-end with vector search queries returning correct results

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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.22 (measured)
recorded runs
2
last tested
stars
11,912
forks
1,165
open issues
671
watchers
55
size
70 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 lancedb, 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.

  • Rust toolchain not installed1 minute
  • protoc not found1 minute
  • No space left on device (disk full)1 minute
  • uv not found on PATH1 minute
  • TypeScript build requires Node.js >=22 but container has v18.19.1
Install time
22 minutes
Cold machine to finish
84 minutes
Errors hit and fixed
5 hit, 4 fixed with no human help
How the result was proved
Rust cargo check --features remote --tests --examples exit 0; Rust tests: 73 across 5 targets all passed; Python tests: 1368 passed, 33 skipped; Python end-to-end: connect, create_table, search, drop_table all succeeded with real local data
Model tokens used
559,325
Exact commit tested
221658602312
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.

**What was done**:
- Installed Rust toolchain via rustup (1.97.0 per the project's `rust-toolchain.toml`)
- Downloaded and extracted protoc 28.2 for the Lance crate's protobuf build
- Ran `cargo clean` once when the 40G disk filled up during Python bindings build (35G `target/`)
- Built Python bindings via `uv run maturin develop`
- Installed uv via pip for Python environment management
**What was verified**:
- Rust `cargo check --features remote --tests --examples` → exit 0
- Rust test suite: 73 tests across 5 test targets, all passed
- Python import and end-to-end: `lancedb.connect()`, `create_table`, `search`, `drop_table` all wor…
- Python test suite: 1368 passed, 33 skipped (pre-existing `slow`/`s3_test` markers), 0 real failur…
- TypeScript bindings: build blocked — requires Node.js >= 22, container has v18.19.1

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 22 minutes.
  • 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

  • Hit 5 errors during setup, 1 of which were not solved.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs96.000.22
Argusic Runner1/3Ran out of time0.000.18

Topics (from GitHub)

approximate-nearest-neighbor-searchimage-searchnearest-neighbor-searchrecommender-systemsearch-enginesemantic-searchsimilarity-searchvector-database

Embed the badge

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

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

Questions

Does lancedb run?
Yes. lancedb runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test lancedb?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 221658602312. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test lancedb?
The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does lancedb take to install?
22 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 lancedb need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing lancedb?
5 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.
Where is the evidence for lancedb?
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