v0.1.1 — local-first CLI

Archive. Search. Understand.

A local-first archive, search, and intelligence engine
for your LLM conversation history.

part → whole → part → whole
$ pip install ricoeur

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

Import from ChatGPT, Claude, and more. One unified archive across all your LLM conversations.

Full-Text Search

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

Topic Discovery

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

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

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

# Import Claude conversations too
ricoeur import claude ~/Downloads/claude-export.json

# Check your archive stats
ricoeur stats

10 commands, one archive

A focused, composable interface for your conversation history.

ricoeur init
Initialize a new ricoeur database and config at ~/.ricoeur
ricoeur import
Import from ChatGPT or Claude exports (.json or .zip)
ricoeur search
Full-text search with filters for platform, language, model, date, and role
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
Discover themes with BERTopic-powered topic modeling
ricoeur index
Build embeddings and summaries for semantic search
ricoeur mcp
Start a Model Context Protocol server for AI-to-archive access
ricoeur tui
Launch the interactive terminal UI for browsing conversations
ricoeur serve
Start a FastAPI web server with REST endpoints
To understand oneself is to understand oneself in front of the text.
Paul Ricoeur