active library Featured

memex

Conversation knowledge base with enrichments, provenance tracking, and MCP server

Started 2026 Python

Resources & Distribution

Personal conversation knowledge base. MCP-first architecture for managing, searching, and analyzing chat conversations from multiple AI providers.

pip install -e ".[dev]"

Import conversations:

memex import conversations.json          # auto-detects format
memex import export.json --format openai  # force format

Export:

memex export output.md --format markdown
memex export output.json --format json

Browse and search:

memex show                               # list conversations
memex show <id>                          # view a conversation

HTML export (self-contained SPA):

memex export ./site --format html        # outputs index.html + DB + assets

MCP server (for Claude Desktop, etc.):

memex mcp

Scripts:

memex run --list                         # available scripts
memex run redact --words "secret" --level word --apply
memex run enrich_trivial --apply

When running as an MCP server, memex exposes 4 tools:

execute_sql – Primary read interface: all queries via SQL (read-only by default)
get_conversation – Tree-aware retrieval + export (metadata, messages, markdown/JSON)
update_conversations – Modify properties, tags, and enrichments (bulk)
append_message – Add messages to conversation trees

pytest tests/memex/ -v             # run tests
pytest tests/memex/ --cov=memex    # with coverage

MIT