Export, back up, search, analyze, and reuse ChatGPT / Claude / Codex / Cursor / DeepSeek / Qwen data + skills + attachments locally
-
Updated
Jun 12, 2026 - TypeScript
Export, back up, search, analyze, and reuse ChatGPT / Claude / Codex / Cursor / DeepSeek / Qwen data + skills + attachments locally
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.
Self-improving memory for AI agents
Make Codex smarter with persistent project memory, AGENTS.md templates, smart routing, and session continuity for AI coding agents.
OpenCode memory plugin with Markdown repo memory and read-only Codex session/history search for agents.
Repo-local Markdown memory for AI coding agents. Persistent project context without a database, vector store, or hosted memory service.
Add a description, image, and links to the codex-memory topic page so that developers can more easily learn about it.
To associate your repository with the codex-memory topic, visit your repo's landing page and select "manage topics."