Back to directory

AI Coding Assistant Data Extraction

A free, open-source tool that extracts a user's own local chat history from AI coding assistants such as Claude Code, Cursor, Windsurf, Aider and Cline into one normalized JSONL format.

AI Coding Assistant Data Extraction

AI Coding Assistant Data Extraction pulls a user's own local conversation history out of ten different AI coding tools and normalizes it into a single JSONL format, for fine-tuning, personal analytics, or backing up years of conversations before a tool's local database is cleared. It auto-discovers user messages, assistant responses, code context such as file paths and snippets, code diffs where a tool records them, tool calls and their results, and whatever timestamps, session IDs and model names each source actually stores.

Supported sources include Claude Code and Codex CLI's JSONL session files, Cursor and Windsurf's SQLite storage, Trae, Continue, Gemini CLI and OpenCode's JSON formats, and Cline/Roo Code and Aider, each read from their own macOS, Linux and Windows storage locations without the user needing to specify an operating system.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.