quivr
An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.
Runs with mockssource: GitHubGoMITcommit f247cb21bbec
Go, MIT licensed. The project labels itself: ai, api, chatbot, chatgpt, database, docker, framework and frontend.
quivr runs, with stand-ins for the services it depends on. An Argusic agent installed it in 14 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Go 1.27.1 installed, all 42 Go packages test OK, 219 Python tests OK, binary builds and responds correctly, all plugin SDK conformance suites pass, OpenAPI contract validation passes, docs and denylist checks pass, only Docker-dependent steps (codegen, acceptance tests) skip without Docker, which is expected
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 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- Docker not available5 minutes
- Missing Python dependencies for tests3 minutes
- Go compiler not installed2 minutes
- modal module not importable in eval tests
- Install time
- 14 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- go build ./cmd/quivr created binary; go test ./... passed all 42 packages; python3 -m unittest discover -s scripts passed 219 tests; bash scripts/plugin_sdk.sh and plugin_sdk_go.sh all OK; /tmp/quivr migrate responded with expected 'read QUIVR_CONFIG file failed' error; OpenAPI and Plugin Protocol validation passed; webhook signature check passed; docs, denylist, migrations, image-context, plugin-boundary all pass
- Model tokens used
- 115,927
- Exact commit tested
- f247cb21bbec
- 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.
changes_test.go:158: make verify
--- SKIP: TestChangeFeedConcurrentCommits (0.00s)
=== RUN TestChangeStreamResumesWithoutLoss
changes_test.go:303: make verify
--- SKIP: TestChangeStreamResumesWithoutLoss (0.00s)
=== RUN TestChangeCursorExpiry
The acceptance tests are correctly skipped without Docker (they say "make verify"). That's expected…
Here's the final assessment:
tokens used
115,927
The acceptance tests are correctly skipped without Docker (they say "make verify"). That's expected…
Here's the final assessment: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
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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.
- Took 14 minutes to install, slower than the median of the 89 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 90 ai projects Argusic has installed and timed, quivr was the 69th fastest to reach a running state, and 63 of 90 reached one at all.
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 | 1/3 | Runs with mocks | 92.00 | 0.24 |
Topics (from GitHub)
aiapichatbotchatgptdatabasedockerframeworkfrontendgroqhtmljavascriptllmopenaipostgresqlprivacyragreactsecuritytypescriptvector
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/quivr)Questions
- Does quivr run?
- quivr runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 14 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test quivr?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f247cb21bbec. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test quivr?
- The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does quivr 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 quivr need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing quivr?
- 4 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.
- How does quivr compare with the alternatives?
- Of the 90 ai projects Argusic has installed and timed, quivr was the 69th fastest to reach a running state, and 63 of 90 reached one at all.
- Where is the evidence for quivr?
- 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.