recall

Search past Claude Code and Codex conversations using BM25 ranking.

2|Updated Nov 24, 2024

Search Tags:#recall #codex #ai #search #claude #history #conversations

Ready to run

npx skills add https://github.com/DanSnow/dotfiles --skill recall-dansnow

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: recall
Source: https://github.com/DanSnow/dotfiles/tree/main/private_dot_claude/skills/recall
Command: npx skills add https://github.com/DanSnow/dotfiles --skill recall-dansnow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you quickly find and resume past conversations with AI models like Claude Code and Codex, preventing the loss of valuable context and information.

Core Features & Use Cases

Full-Text Search: Indexes and searches through all your past AI conversation sessions.
Contextual Recall: Easily find discussions about specific topics, projects, or code snippets.
Session Resumption: Provides paths and commands to directly resume a found session.
Use Case: You remember discussing a complex bug fix with an AI a few weeks ago but can't recall the exact details. Use this Skill to search for keywords related to the bug, retrieve the relevant session, and resume the conversation to continue where you left off.

Quick Start

Search for past conversations about 'bufferStore' using the recall skill.

Frequently Asked Questions about recall

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I search past AI conversation history in Claude Code and Codex?▼

You can search past AI conversation history using full-text search with BM25 ranking and incremental indexing to retrieve relevant discussion context from Claude Code and Codex sessions. It returns matching sessions for direct resumption.

What is the best way to find a specific code discussion from previous AI sessions?▼

Finding a specific code discussion from previous AI sessions is done by indexing past conversation transcripts and searching with keywords. This contextual recall helps you locate exact project context or code snippets discussed previously.

Can I resume a previous Claude Code conversation after finding it through search?▼

Yes, you can resume a previous Claude Code conversation after finding it through search. The search results provide direct paths and commands to resume the retrieved session and continue where you left off.

Does full-text search for AI history require any external dependencies?▼

No external dependencies are required for full-text search of AI history. The indexing and retrieval process runs entirely via internal Python scripts without needing additional packages or external libraries installed.

How does incremental indexing work when searching past AI conversations?▼

Incremental indexing works by processing only new or modified past AI conversations rather than re-indexing the entire history. This ensures efficient BM25 ranking and faster retrieval of relevant session transcripts during search.