whereismyai
AI Data Extractor
AI Data Extractor: Free open-source utility extracts local chat histories from multiple AI coding assistants into normalized JSONL files.
This utility extracts local chat history from AI coding assistants into a single normalized JSONL format. It automatically discovers and reads data from tools such as Claude Code, Codex CLI, Cursor, Windsurf, Trae, Continue, Gemini CLI, OpenCode, Cline, Roo Code, and Aider. The software scans standard operating system directories across macOS, Linux, and Windows without manual path configuration. It supports multiple storage backends including JSON, JSONL, SQLite databases, and Markdown files using read-only connections and heuristics. Developers can use the extracted data for fine-tuning machine learning models, personal analytics, or local backups.
AI Data Extractor at a glance
Key features
- Auto-discovers chat history across multiple tools
- Reads SQLite databases using read-only connections
- Parses JSON and JSONL session files
- Scans Markdown transcripts from project directories
- Normalizes conversations into a single JSONL format
- Searches macOS, Linux, and Windows default paths
- Runs standalone scripts for individual data sources
Use it for
- Backing up local AI coding assistant conversation histories
- Preparing chat datasets for fine-tuning machine learning models
- Running personal analytics on coding assistant usage
Alternatives to AI Data Extractor
- Code Review Graph — Provides a median 63x context reduction while keeping all code processing local.
- Entelligence AI — Inspect agent sessions locally without digging through logs or sharing data.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Wy — Links file changes directly to agent chat transcripts.
- AI Engineer Tools — Capture agent activity as structured local events without conversations.
- CodeSight — Reduces AI token usage significantly and maps projects instantly.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
- AgentsView — It keeps your AI coding session archive local by default while tracking costs and activity.
- README AI — Automates documentation creation from codebases with custom styles.
- ThreadShelf — It keeps conversation archives and search completely local using LanceDB and embeddings.
All AI Data Extractor alternatives