ricoeur — a local-first archive & search engine for your LLM history

Features

Everything you need to understand your AI history

Import, search, analyze, and explore your conversations across platforms — entirely on your machine.

Local-First

Your data stays on your machine. SQLite database, no cloud required. Full ownership of your conversation archive.

Multi-Platform Coming soon

Import from ChatGPT today. Claude, Gemini, and custom JSON imports coming soon.

Full-Text Search

FTS5-powered instant search across all messages. Filter by platform, language, model, date, or role.

Topic Discovery Coming soon

BERTopic-powered topic modeling. Discover themes and patterns in your conversation history automatically.

Semantic Search

Embedding-powered similarity search using sentence-transformers or Ollama. Find conversations by meaning, not keywords.

MCP Integration Coming soon

Expose your archive as a Model Context Protocol server. Let your current AI access your past conversations.

Quick Start

Up and running in minutes

Import your data, search your history, discover patterns.

# Install ricoeur
pip install ricoeur

# Initialize database
ricoeur init
Initialized ricoeur at ~/.ricoeur

# Import your ChatGPT export
ricoeur import chatgpt ~/Downloads/export.zip
Import from ChatGPT
  Parsed:       3,756 conversations (42,618 messages)
  New:          3,756

# Check your archive stats
ricoeur stats

# Hybrid search (keyword + semantic, default)
ricoeur search "deployment strategies"
Found 18 results for "deployment strategies" (hybrid)

# Semantic search — find by meaning, not keywords
ricoeur search "how to containerize apps" --semantic

# Keyword search (FTS5)
ricoeur search "neural networks" --keyword

# Filter by platform and language
ricoeur search "API design" --platform chatgpt --lang en

# Search only in code blocks
ricoeur search "async def" --code --limit 10

# More output formats coming: json, full, ids

CLI Reference

Your CLI toolkit

A focused, composable interface for your conversation history.

ricoeur init

Initialize a new ricoeur database and config at ~/.ricoeur

ricoeur import

Import from ChatGPT exports (.json or .zip)

ricoeur search

Hybrid, semantic, or keyword search with filters for platform, language, model, and date

ricoeur show

Display a full conversation in rich, markdown, or JSON format

ricoeur stats

Analytics dashboard with counts by platform, model, and language

ricoeur topics Soon

Discover themes with BERTopic-powered topic modeling

ricoeur index

Build embeddings and summaries for semantic search

ricoeur mcp Soon

Start a Model Context Protocol server for AI-to-archive access

ricoeur tui Soon

Launch the interactive terminal UI for browsing conversations

ricoeur serve Soon

Start a FastAPI web server with REST endpoints

Archive. Search. Understand.