SeekStorm
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
Runssource: GitHubhomepageRustApache-2.0commit 50cb0ddffe1e
Rust, Apache-2.0 licensed. The project labels itself: ai search, bm25, dense retrieval, enterprise search, faceting, full text search, geosearch and hybrid search.
SeekStorm runs. An Argusic agent installed it in 14 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Workspace builds cleanly with Rust 1.99.0, all 45 seekstorm library integration tests and all 7 seekstorm_client E2E tests pass, and the release seekstorm_server binary serves the live endpoint (HTTP 200) and completes the API key creation, index creation, document indexing, commit, and query flow returning the indexed document.
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.
- seekstorm_client E2E tests failed 6/7 with HTTP 401 'apikey invalid or missing' and bind failure on port 80 due to stale server20 minutes
- rustc/cargo not found in container; standard install (cargo build) could not start4 minutes
- Install time
- 14 minutes
- Cold machine to finish
- 63 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- cargo test -p seekstorm --tests: 45 passed, 0 failed; cargo test -p seekstorm_client_rs --tests: 7 passed, 0 failed; curl http://127.0.0.1:18080/api/v1/live returned 200 'SeekStorm server 3.3.13 (AVX2 enabled)'; curl POST /api/v1/index/0/query after indexing returned count_total=1
- Model tokens used
- 1,988,824
- Exact commit tested
- 50cb0ddffe1e
- 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.
1,988,824 I have completed the full mission. Let me assemble the final report. **Summary of work done** The repo is the SeekStorm Rust workspace (search library + multi-tenancy HTTP server + REST client)… Errors encountered and fixed: 1. **No Rust toolchain** (`rustc/cargo: not found`) → installed via `rustup` (user-local, no root n… 2. **Client E2E tests failed with 401 `apikey invalid or missing`** → the test hardcoded `MASTER_AP… 3. **Stale orphan server / port-80 contention in an earlier run** → the test spawns a server per te… Root README of the client crate and its docs advertise the inconsistent constant in prose, but the … Final real verification (release server, `tier1_real`): - `seekstorm_server local_ip=127.0.0.1 local_port=18080 index_path=...` stayed up; `curl /api/v1/li… - Full REST flow against the release binary: created API key (200), created index (returned `0`), i…
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.
What did not, or is not known
- Took 14 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 4 ai-search projects Argusic has installed and timed, SeekStorm was the 3rd fastest to reach a running state, and 3 of 4 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
Topics (from GitHub)
ai-searchbm25dense-retrievalenterprise-searchfacetingfull-text-searchgeosearchhybrid-searchlexical-searchneural-searchrealtimesearchsearch-enginesearch-serversearch-servicesemantic-searchsparse-retrievalvector-databasevector-searchvector-search-engine
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/seekstorm)Questions
- Does SeekStorm run?
- Yes. SeekStorm runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test SeekStorm?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 50cb0ddffe1e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test SeekStorm?
- The run that produced this verdict cost $0.53: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does SeekStorm take to install?
- 14 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 SeekStorm need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing SeekStorm?
- 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 SeekStorm compare with the alternatives?
- Of the 4 ai-search projects Argusic has installed and timed, SeekStorm was the 3rd fastest to reach a running state, and 3 of 4 reached one at all.
- Where is the evidence for SeekStorm?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.