trieve
All-in-one platform for search, recommendations, RAG, and analytics offered via API
Runs with mockssource: GitHubhomepageRustMITcommit a99b21e23f21
Rust, MIT licensed. The project labels itself: actix, actix web, ai, artificial intelligence, diesel, embedding, hacktoberfest and llm.
trieve runs, with stand-ins for the services it depends on. An Argusic agent installed it in 50 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Rust server binary builds and links, Rust lib unit test passes, 408 Python SDK model unit tests pass, MCP server and TS SDK build and produce valid JavaScript bundles, and all three frontends (search, dashboard, chat) build to static assets; full integration testing requires Docker for Postgres/Redis/Qdrant/ClickHouse/MinIO which are not available in this 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 87 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.
- Hallucination-detection tests with default NER feature fail to link due to missing libtorch_cpu.so at runtime25 minutes
- Rust server binary link failure: libpq not found system-wide10 minutes
- yarn not available in environment2 minutes
- Rust build.rs expects `.env` file and `npx tailwindcss`2 minutes
- Root package.json has `conf` dependency requiring Node >=20, but Node 18 is installed1 minute
- Python SDK tests initially fail: missing `traitlets` and `requests` modules in generated code1 minute
- Install time
- 50 minutes
- Cold machine to finish
- 63 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- cargo test --lib in server/ returned '1 passed; 0 failed'; cargo test --no-default-features in hallucination-detection/ returned '5 passed; 8 failed' (NER-dependent); python3 -m pytest test/ in clients/python-sdk/ returned '408 passed'; cargo build --bin trieve-server in server/ succeeded producing a 1.4GB binary; yarn build in all 3 frontends succeeded; node clients/mcp-server/build/index.js without credentials correctly exits with 'Error: API key is required'
- Model tokens used
- 661,003
- Exact commit tested
- a99b21e23f21
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'echo "Started at the beginning of the session. Current time:" date -u echo "Time elapsed approximately 50 minutes"' in /work/repo succeeded in 0ms: Started at the beginning of the session. Current time: Wed Nov 11 02:19:35 UTC 2026 Time elapsed approximately 50 minutes Here's the complete report: tokens used 661,003 Here's the complete report:
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
- Installed in 50 minutes.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, 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.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.32 | |
| Argusic Runner | 1/3 | Runs with mocks | 82.00 | 0.03 |
Topics (from GitHub)
actixactix-webaiartificial-intelligencedieselembeddinghacktoberfestllmpostgresqlqdrantqdrant-vector-databaseragretrieval-augmented-generationrustsearchsearch-enginesolidjstailwindcssvector-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/trieve)Questions
- Does trieve run?
- trieve runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 50 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test trieve?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a99b21e23f21. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test trieve?
- The run that produced this verdict cost $0.32: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does trieve take to install?
- 50 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 trieve need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing trieve?
- 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 trieve?
- 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.