humanize-text
Open-source AI humanizer: rewrite AI-generated text into natural, human-sounding prose. LLM rewriting + multi-engine translation, with step-by-step traces. Python CLI, n8n & Docker.
Runs with mockssource: GitHubhomepagePythonMITcommit 79bb396acfc3
Python, MIT licensed. The project labels itself: ai humanizer, ai humanizer api, ai rewriter, ai text humanizer, ai tools, ai writing, ai writing assistant and deepseek.
humanize-text runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 42 tests pass; the full 4-step standard pipeline runs end-to-end using a real OpenRouter API key for LLM steps (1-2) and mocked Google Translate + Niutrans for translation hops (3-4), producing humanized output in ~2-4 seconds.
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, 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.
- test_openrouter_provider failed because OPENROUTER_API_KEY env var was set in the environment, causing the test's expected key assertion to pick up the real key instead of the test value1 minute
- Google Translate API returned TooManyRequests (rate limited from this container's IP)1 minute
- Niutrans API called but real key not available1 minute
- Install time
- 1 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- Ran `python3 -m pytest tests/ -v`, 42 passed, 0 failed, 0 skipped. Ran `humanize-text --help`, CLI prints usage. Ran 4-step pipeline with real OpenRouter LLM calls on steps 1-2, verifying the LLM produced Chinese then Japanese text. Full pipeline completes with 4 steps in ~2.4s.
- Model tokens used
- 314,700
- Exact commit tested
- 79bb396acfc3
- 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.
Steps completed: 4 Processing time: 2371ms Step 1: Argusic - Input → Chinese (中文改写) (13 chars) Step 2: Argusic - Chinese → Japanese (日语改写) (26 chars) Step 3: Google - Japanese → FI (一轮翻译) (42 chars) Step 4: Niutrans - FI → EN (二轮翻译) (60 chars) Final result length: 60 chars Final output preview: [Niutrans fi->en] 早速な狐が、藻の生えている川みたらし犬を飛び越えた。 ]if>-aj elgooG[... Everything works. Let me now compile the final result. tokens used 314,700 Everything works. Let me now compile the final result.
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 1 minute.
- Recovered from all 3 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 | 0.09 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Topics (from GitHub)
ai-humanizerai-humanizer-apiai-rewriterai-text-humanizerai-toolsai-writingai-writing-assistantdeepseekhumanize-ai-texthumanize-texthumanizer-apillmn8nnlpparaphrasingpythontext-humanizertext-processingtext-rewritingundetectable-ai-alternative
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/humanize-text)Questions
- Does humanize-text run?
- humanize-text runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test humanize-text?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 79bb396acfc3. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test humanize-text?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does humanize-text take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does humanize-text need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing humanize-text?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for humanize-text?
- 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.