# isoshimodo/ai-data-extractor

> Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline, etc.) into a unified JSONL format. Useful for backups, analytics, or preparing fine-tuning data.

- Magnitude: 5.4 out of 10 — Early signal
- Stars: 112 total · +0 stars today, ≈ 67 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-03 · Last push: 2026-10-03
- GitHub: https://github.com/isoshimodo/ai-data-extractor · Page: https://gitnova.dev/en/r/isoshimodo/ai-data-extractor

## Useful for

- Extract chat history from Cursor and Claude Code into one JSONL backup
- Build a dataset from your assistant dialogs for fine-tuning
- Preview available sources with --list without extracting data

## Why it’s here

- 0 stars so far today, about 67 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 112 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #165.
- About 44 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 37
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 60 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 9 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-05: 0, 0, 0, 0, 0, 0, 5, 108, 0

## Spotted in now

- Top new repositories this week: #165

## More in this category

1. **Niko1221/Strata** — 7.6 · Breakout · Language models · C++ · +0 stars today, ≈ 1,637 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **StayLameBro/backburner** — 5.7 · Early signal · Language models · Python · +0 stars today, ≈ 145 by evening
   A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running…
   Full card: https://gitnova.dev/en/r/StayLameBro/backburner.md
3. **antirez/ds4** — 5.7 · Breakout · Language models · C · +0 stars today, ≈ 168 by evening
   DwarfStar (ds4) is a native C inference engine for running a few specific large LLMs (DeepSeek V4 Flash/PRO, GLM 5.x, Qwen3.8 Flash Next) on Metal, CUDA and ROCm. Targets consumer hardware like MacBooks, DGX Spark and Strix Halo, with SSD…
   Full card: https://gitnova.dev/en/r/antirez/ds4.md
4. **gotoanto/text-humanizer** — 5.5 · Early signal · Language models · Python · +0 stars today, ≈ 73 by evening
   A Python tool that rewrites AI-generated text through a pipeline of LLM and translation steps to bypass detectors like GPTZero and Turnitin. Supports 8 languages while preserving the original meaning.
   Full card: https://gitnova.dev/en/r/gotoanto/text-humanizer.md
5. **heise3/academic-deai** — 4.8 · Early signal · Language models · Python · +0 stars today, ≈ 59 by evening
   A skill for editing Chinese and English academic prose: removes formulaic AI phrasing while preserving facts, citations, terminology, and author voice.
   Full card: https://gitnova.dev/en/r/heise3/academic-deai.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-05 05:07 UTC, updated every 30 minutes.