skills.rest
acabreragnz
acabreragnzCOMMUNITY
Explore all skills by this author →
GitHub

memex-search

Search indexed Claude and Codex chat history with lexical, semantic, or hybrid modes.

Updated Aug 23, 2026
Search Tags:#codex#llm#rag#search#claude#history
One-click install
npx skills add https://github.com/acabreragnz/dotfiles --skill memex-search-acabreragnz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memex-search
Source: https://github.com/acabreragnz/dotfiles/tree/main/.claude/skills/memex-search
Command: npx skills add https://github.com/acabreragnz/dotfiles --skill memex-search-acabreragnz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill allows users to efficiently search, filter, and retrieve their indexed Claude and Codex chat history, making it easy to find past conversations and information.

Core Features & Use Cases

  • Indexing: Build and maintain a searchable index of chat history.
  • Search: Perform lexical, semantic, or hybrid searches on indexed history.
  • Retrieval: Fetch full transcripts or specific records for RAG or analysis.
  • Use Case: Quickly find all conversations where you discussed a specific bug, retrieve the exact commands used in a past session, or export LLM-friendly JSON for further processing.

Quick Start

Search your history for conversations about "optimizing database queries".

Frequently Asked Questions about memex-search

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

FAQPage Schema
How do I search my Claude and Codex chat history for past conversations?▼

You can search Claude and Codex chat history by performing lexical, semantic, or hybrid searches on an indexed history. This lets you filter conversations by project, role, tool, and time to quickly find specific past discussions and information.

What is the best way to retrieve full transcripts for RAG from LLM chat history?▼

The best way to retrieve full transcripts for RAG is to fetch specific records or entire conversations from your indexed chat history, which provides LLM-friendly JSON output tailored for retrieval-augmented generation and further processing.

Can I filter indexed chat history by specific projects or tools?▼

Yes, you can filter your indexed chat history by project, role, tool, and time. This output shaping ensures you only retrieve the exact conversations and records relevant to your current search parameters.

How does semantic search work on past Claude chat sessions?▼

Semantic search works on past Claude chat sessions by matching the meaning and context of your query against the indexed chat history rather than exact keywords, retrieving conceptually relevant conversations for review or RAG.

Does this search approach support exporting LLM-friendly JSON output?▼

Yes, this search approach supports exporting LLM-friendly JSON output. It facilitates RAG workflows by providing structured JSON data and full transcript retrieval from your indexed Claude and Codex chat history for analysis.

What are the limitations when filtering Codex chat history by time?▼

The metadata does not specify explicit limitations when filtering Codex chat history by time, but effective filtering requires that the chat history be properly indexed first to ensure accurate retrieval of records within the specified time ranges.

Related Skills

Explore More Software Engineering Skills→
nirholasnirholas
71

embeddings

Create and manage vector embeddings for semantic search across multiple providers.

Community
Advanced
ruskibeatsruskibeats

rag-evidence-contract-testing

Validate retrieved graph edge evidence structure for LLM RAG context assembly.

Community
Intermediate
hussain9491hussain9491

building-rag-systems

Automate RAG pipeline creation with semantic chunking and Qdrant vector search.

Community
Advanced
Fl2vioFl2vio
1

AgentDB Vector Search

Enable semantic vector search and hybrid retrieval with AgentDB.

Community
Advanced