ragflow
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Runssource: GitHubhomepageGoApache-2.0commit 313ca90f6abd
Go, Apache-2.0 licensed. The project labels itself: agent harness, agent native database, agentic ai, agentic retrieval, agentic search, ai, ai agents and context engine.
ragflow runs. An Argusic agent installed it in 80 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python 3.13 venv with 697 deps installed, Go toolchain auto-resolved to go1.27, C++ librag_tokenizer_c_api.a built with clang++-20, Go binaries ragflow_server and ragflow-cli compiled successfully, Go unit tests pass (all packages), Python unit tests pass (5145/5145), frontend builds successfully, native static libs (pdfium/pdf_oxide/office_oxide/onnxruntime) linked.
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 96 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.
- Missing clang++ (required by build.sh)5 minutes
- Missing libpcre2-8.a (required by C++ tokenizer static library)3 minutes
- Missing ld.lld (required to link Chromium-built pdfium)2 minutes
- Missing cmake >= 4.0 (CMakeLists.txt requires 4.0)2 minutes
- Frontend build required node >= 20.19 (system had 18.19)2 minutes
- Frontend build OOM with default Node heap1 minute
- Install time
- 80 minutes
- Cold machine to finish
- 40 minutes
- Errors hit and fixed
- 7 hit, 7 fixed with no human help
- How the result was proved
- Go unit tests: bash build.sh --test ./internal/tokenizer/... ./internal/cli/... ./internal/dao/... ./internal/storage/... ./internal/engine/... ./internal/parser/... ./internal/entity/... ./internal/server/... ./internal/router/... ./internal/handler/... ./internal/agent/... ./internal/service/... ./internal/ingestion/... all passed. Python unit tests: PYTHONPATH=$PWD .venv/bin/python3 -m pytest test/unit_test/ --no-header -q --ignore=test/unit_test/sdk --ignore=test/unit_test/agent/component returned 5145 passed, 26 skipped. CLI binary: bin/ragflow-cli --version returned 'RAGFlow CLI version 313ca90'. Frontend: npm run build completed in 3m19s.
- Model tokens used
- 1,105,613
- Exact commit tested
- 313ca90f6abd
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
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 "Start of session: repo files dated"; ls -la /work/repo/.git/index 2>/dev/null; e… succeeded in 0ms: Start of session: repo files dated -rw-rw-r-- 1 runner runner 733524 Sep 25 07:54 /work/repo/.git/index Current time: 1790322925 Start estimate: roughly when log began 5 Now I have all the information I need. Let me construct the final report. tokens used 1,105,613 Now I have all the information I need. Let me construct the final 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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 7 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 80 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
Of the 9 agent-harness projects Argusic has installed and timed, ragflow was the 9th fastest to reach a running state, and 6 of 9 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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.32 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.20 |
Topics (from GitHub)
agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ragflow)Questions
- Does ragflow run?
- Yes. ragflow runs. Argusic installed and launched it on a clean machine in 80 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test ragflow?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 313ca90f6abd. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ragflow?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ragflow take to install?
- 80 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 ragflow need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ragflow?
- 7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ragflow compare with the alternatives?
- Of the 9 agent-harness projects Argusic has installed and timed, ragflow was the 9th fastest to reach a running state, and 6 of 9 reached one at all.
- Where is the evidence for ragflow?
- 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.