milvus
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Runssource: GitHubhomepageGoApache-2.0commit 15fdc9599854
Go, Apache-2.0 licensed. The project labels itself: anns, cloud native, diskann, distributed, embedding database, embedding similarity, embedding store and faiss.
milvus runs. An Argusic agent installed it in 30 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pymilvus 3.0.2 with milvus-lite 3.2.1 runs embedded vector database operations (create, insert 1000 vectors, search, query, delete, drop) in the container. Go toolchain 1.26.6, Rust 1.84, and Conan 2.25.1 are installed. The C++ core cannot build without root for system library packages.
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.
- Go not found in container10 minutes
- PEP 668 blocks system pip for pymilvus and conan install5 minutes
- Full C++ source build (make) fails — Conan needs root-installed system packages (libaio, etc.) and 30+ min compile5 minutes
- 10 Go packages fail to build: rocksdb, rdkafka, pulsar C libs not in container
- 10 Go packages fail tests: paramtable/indexparams/tracer/interceptor/lock/nodescheduler/wp panic on mkdir /var/lib/milvus (permission denied); config flakes on etcd port conflict; pulsar needs running server
- Install time
- 30 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- /tmp/venv/bin/python /tmp/test_milvus_full.py: created collection, inserted 1000 vectors, searched top-10, queried by filter id==42, deleted 3 rows, dropped collection, all 11 assertions passed. go test -tags dynamic,test -gcflags='all=-N -l' -count=1 ./... under pkg/: 57 packages PASS, 10 build FAIL (missing C libs), 10 test FAIL (mkdir /var/lib/milvus: permission denied + etcd port race + pulsar not running)
- Model tokens used
- 589,817
- Exact commit tested
- 15fdc9599854
- 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.
This is the Milvus vector database, a Go+C++ project with Rust tantivy bindings. The container has … **Path 1 — Milvus Lite (Python SDK):** Installed `pymilvus[milvus-lite]` in a venv. Created a local… **Path 2 — Source build:** Installed Go 1.26.6, Rust 1.84, Conan 2.25.1. The full `make` build requ… **Path 3 — Go-only tests:** Ran `go test ./...` under `pkg/` (which has its own go.mod). **57 packa… tokens used 589,817 Now I have everything I need. Here's my final report. **Summary of what was done and observed:** This is the Milvus vector database, a Go+C++ project with Rust tantivy bindings. The container has … **Path 1 — Milvus Lite (Python SDK):** Installed `pymilvus[milvus-lite]` in a venv. Created a local… **Path 2 — Source build:** Installed Go 1.26.6, Rust 1.84, Conan 2.25.1. The full `make` build requ… **Path 3 — Go-only tests:** Ran `go test ./...` under `pkg/` (which has its own go.mod). **57 packa…
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 30 minutes.
- Recovered from all 5 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)
annscloud-nativediskanndistributedembedding-databaseembedding-similarityembedding-storefaissgolanghnswimage-searchllmnearest-neighbor-searchragvector-databasevector-searchvector-similarityvector-store
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/milvus)Questions
- Does milvus run?
- Yes. milvus runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test milvus?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 15fdc9599854. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test milvus?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does milvus take to install?
- 30 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 milvus need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing milvus?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for milvus?
- 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.