# nachisama/ai-data-extractor

> A Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code, and more) into a single normalized JSONL format. Useful for backup, personal analytics, or preparing data for fine-tuning.

- Magnitude: 3.4 out of 10 — Early signal
- Stars: 93 total · +5 stars measured 2026-10-08, 17:40–19:40 UTC, ≈ 7 by evening
- Star trust: star growth looks organic
- Category: Data & analytics · Language: Python · License: MIT · Created: 2026-10-07 · Last push: 2026-10-07
- GitHub: https://github.com/nachisama/ai-data-extractor · Page: https://gitnova.dev/en/r/nachisama/ai-data-extractor

## Useful for

- Back up chat histories from Cursor and Claude Code before the local database is cleared
- Build a JSONL dataset of coding conversations for later model fine-tuning
- Analyze your AI assistant sessions by project and model

## Why it’s here

- Star-counter measurements on 2026-10-08 (UTC), 17:40–19:40: 88 → 93 stars (+5). This is the change over that interval.
- Estimated end-of-day forecast: about +7 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 93 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #188.
- About 33 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: 38
- Issues and pull requests: 0
- Watchers: 17
- Average over the last week: 20 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-04 … 2026-10-08: 0, 0, 0, 34, 5

## Spotted in now

- Top new repositories this week: #188

## More in this category

1. **IAmTomShaw/f1-race-replay** — 5.7 · Breakout · Data & analytics · Python · +24 stars measured 2026-10-08, 10:59–19:38 UTC, ≈ 36 by evening
   A Python application for visualizing Formula 1 race telemetry and replaying race events with interactive controls and a graphical interface.
   Full card: https://gitnova.dev/en/r/IAmTomShaw/f1-race-replay.md
2. **fabio-rovai/open-ontologies** — 4.9 · Early signal · Data & analytics · Rust · +45 stars measured 2026-10-08, 00:02–19:39 UTC, ≈ 56 by evening
   A Rust tool for planning, applying and rolling back changes to production OWL/RDFS ontologies, with a blast radius report and a verifiable proof certificate.
   Full card: https://gitnova.dev/en/r/fabio-rovai/open-ontologies.md
3. **bilawalsidhu/gods-eye-view** — 4.4 · Steady · Data & analytics · JavaScript · +349 stars measured 2026-10-08, 00:03–19:39 UTC, ≈ 421 by evening
   A browser-based spy-satellite simulator on a photorealistic 3D globe that unifies public feeds: aircraft, ships, satellites, earthquakes, cameras, and traffic. Runs locally, with each layer as a separate module.
   Full card: https://gitnova.dev/en/r/bilawalsidhu/gods-eye-view.md
4. **duckdb/ducklake** — 4.1 · Breakout · Data & analytics · C++ · +23 stars measured 2026-10-08, 01:27–19:39 UTC, ≈ 28 by evening
   DuckDB extension for DuckLake, an open lakehouse format built on SQL and Parquet, storing metadata in a catalog database and data in Parquet files. Lets DuckDB read and write DuckLake tables directly.
   Full card: https://gitnova.dev/en/r/duckdb/ducklake.md
5. **D4Vinci/Scrapling** — 3.6 · Steady · Data & analytics · Python · +182 stars measured 2026-10-08, 00:03–19:40 UTC, ≈ 219 by evening
   An adaptive Python web scraping framework: the parser relocates elements when site markup changes, fetchers bypass anti-bot systems like Cloudflare Turnstile, and the spider system scales to concurrent multi-session crawls.
   Full card: https://gitnova.dev/en/r/D4Vinci/Scrapling.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 2026-10-08 19:54 UTC, updated every 30 minutes.