vearch
Distributed vector search for AI-native applications
Runssource: GitHubhomepagePythonApache-2.0commit bae78b189ff0
Python, Apache-2.0 licensed. The project labels itself: ai native, ai native database, cloud native, document retrieval, embeddings, hybrid search, rag and retrieval augmented generation.
vearch runs. An Argusic agent installed it in 90 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Vearch v3.5.9 binary (81MB) and gamma engine (.so) built from source, server starts with master+router+PS on localhost:8817/9001, REST API responds, db/create/list works, cluster health/stats/members endpoints return valid JSON, tests pass basic cluster operations but space creation times out due to PS heartbeat instability in constrained environment
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.
- pip faiss-cpu ABI mismatch with gamma engine linking20 minutes
- Missing system C++ libs (OpenBLAS, TBB, protobuf, roaring, rocksdb, zstd)10 minutes
- Ubuntu CRoaring v0.2.66 lacks C++ namespace (roaring::Roaring64Map), headers incompatible with gamma engine10 minutes
- PS heartbeat drops causing server unavailability in tests10 minutes
- No Go compiler on system5 minutes
- Static libs (rocksdb.a, zstd.a) incompatible with -fPIC shared lib linking5 minutes
- Install time
- 90 minutes
- Cold machine to finish
- 59 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- curl -s http://127.0.0.1:9001/ returned {'code':0} with version info; curl -s http://127.0.0.1:9001/servers returned server list; python test_vearch.py 5 passed, space creation failed due to PS heartbeat timeout
- Model tokens used
- 287,013
- Exact commit tested
- bae78b189ff0
- 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.
- faiss v1.14.1 built from source as shared library with OpenBLAS - Gamma engine (C++ shared lib) built successfully - Vearch Go binary (81MB) built successfully Runtime verification: - vearch -h: prints usage (confirmed) - Server start with 'all' tag: master on :8817, router on :9001 (confirmed) - GET / and /cluster/stats and /servers return valid JSON (confirmed) - db create/list/delete works (confirmed) - Python tests: 5 passed, space creation/teardown timed out - Go SDK: compiles, tests fail as server not running tokens used 287,013
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 90 minutes.
- Recovered from all 6 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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-nativeai-native-databasecloud-nativedocument-retrievalembeddingshybrid-searchragretrieval-augmented-generationvector-databasevector-searchvectors
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/vearch)Questions
- Does vearch run?
- Yes. vearch runs. Argusic installed and launched it on a clean machine in 90 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test vearch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit bae78b189ff0. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test vearch?
- The run that produced this verdict cost $1.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does vearch take to install?
- 90 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 vearch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing vearch?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for vearch?
- 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.