SVerITG/Metis
by Various
A Research Cortex. A research companion for Claude. Your library, notes & memory stay on your machine; answers cited from your own library; 30+ specialist skills; auto cross-pollin
MCP
SVerITG/Metis
Added 11 June 2026
Overview
Metis is a local research companion for Claude that keeps your library, notes, and memory on your machine. It answers questions with citations from your own library, uses 30+ specialist skills, and automatically cross-pollinates across papers, meetings, ideas, notes, and journal entries. A weekly self-review drafts improvements for your approval, and reasoning runs on the Claude API.
Best for
Best for
Researchers and developers who want a private, automated research assistant that integrates with Claude
Use cases
- Organize and query personal research notes and papers with cited answers
- Automatically connect ideas across meetings, journals, and academic papers
- Receive weekly self-review suggestions to improve your research workflow
How to use
Install
pip install -e "."Tools exposed
sqlite-vec
Tested with
Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT
Notes
Metis is a local research companion for Claude that keeps your library, notes, and memory on your machine. It answers questions with citations from your own library, uses 30+ specialist skills, and automatically cross-pollinates across papers, meetings, ideas, notes, and journal entries. A weekly self-review drafts improvements for your approval, and reasoning runs on the Claude API.
0 stars on GitHub. Last updated 2026-06-08. Licensed AGPL-3.0.
Use cases
- Organize and query personal research notes and papers with cited answers
- Automatically connect ideas across meetings, journals, and academic papers
- Receive weekly self-review suggestions to improve your research workflow
Pros
- Data stays local on your machine for privacy
- Answers are cited from your own library, increasing trust
- Automated cross-pollination saves time connecting disparate notes
Cons
- Requires the Claude API, adding ongoing cost
- Setup and maintenance may be complex for non-developers
- Limited to the capabilities and context window of the underlying Claude model
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Data stays local on your machine for privacy
- Answers are cited from your own library, increasing trust
- Automated cross-pollination saves time connecting disparate notes
Cons
- Requires the Claude API, adding ongoing cost
- Setup and maintenance may be complex for non-developers
- Limited to the capabilities and context window of the underlying Claude model
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
topoteretes/cognee
Various
Memory platform for AI Agents in 6 lines of code
oraios/serena
Various
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
vectorize-io/hindsight
Various
Hindsight: Agent Memory That Learns
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.