Metis — Research Cortex

You ask Claude to build a monitoring dashboard for your current project. Metis recalls the dashboard you built eighteen months ago, your preferred layout, and your standard indicators. The right specialist agents deliver exactly what you need — in your style, to your domain's standards — without any re-explaining.

🔗 Cross-pollination
The moment everything connects

You capture a quick idea about a novel surveillance approach. Within seconds, Metis surfaces three things you'd forgotten existed: a methodology paper from fourteen months ago that used a similar approach, a meeting note from March where your field partner described the same barrier, and an open question you logged after a conference. You hadn't connected any of it. Metis did. The grant section writes itself.

🌐 Metis OS
The full picture — in development

Your calendar shows a meeting with a research collaborator. Yesterday you captured an idea about a new method. Metis has your April transcript with this person and this week's new papers. A briefing appears before you leave. After the meeting, you ask for a five-day course on that topic from the latest research. By evening, it's ready.

🩺 This is the Public Health & Epidemiology edition

The dashboard at a glance — your projects, tasks, the morning brief and what to focus on, in one calm view.

A tour through Metis — the system tab and every part of your Research Cortex: today, work, knowledge, meetings, ideas, learning and the control room.

The silent layer — one click on the morning brief opens Claude Desktop, primed with your work, ready to brainstorm.

Metis reviews its own work and proposes its own improvements — the self-improvement loop, in plan mode.

- 📚 It cites your own sources.Knowledge answers are anchored inyourindexed library, with document- and page-level citations — not the model's guesses. Your library grounds the answer; it doesn't fence it in. Metis still brings in recent literature, guidelines and wider knowledge where they matter, and tells you which is which — so anything worth citing that you don't have yet becomes a paper you can add.
- 🔗 It connects everything you know.Every paper, meeting transcript, idea, note, journal entry and task is linked to the rest of your work. The grant you write today surfaces a method paper from last year and a meeting note from March — you never go looking; Metis brings it to you.
- 🧠 It routes to the right expert.Ask in plain language, and Metis hands the work to the right one of 30+ specialist skills — Librarian, Methods Coach, Writing Partner, Meeting Memory, Epidemiologist, Course Builder, and more.
- 🔁 It improves itself.After every task it logs what worked and what fell short; each week it drafts improvements to its own behaviour and waits for your approval. Most MCP servers are static — Metis gets sharper the longer you use it.
- 🚫 It refuses to invent.Ask about something that isn't in your library and Metis tells you so, instead of fabricating a plausible-sounding answer. (This grounding behaviour is covered by an automated test.)
- 🔒 It stays on your machine.Local embeddings, local database, local files. Your papers, patient-adjacent data, and unpublished work never leave your computer.

🎥See it in actionabove — the dashboard, a tour of the tabs, the silent layer into Claude Desktop, and Metis improving its own work.

No programming background needed. Install in minutes, start working immediately. Everything Metis does is explained in plain language.

Open-source, extensible, well-architected. Build domain packs, add agents, extend the MCP server, or deploy for your institution.

Metis is aresearch companion built on top of Claudethat keeps your data on your own machine. It gives every AI conversation a persistent memory of your domain, your papers, your projects, and your working history. It routes your requests to the right specialist, does the work, records the result, and returns a plain answer — without requiring you to prompt or configure anything.

The short version:imagine an AI that already knew your field and your literature, connected every paper, meeting, idea and note you've captured, sent each request to the right specialist — and got sharper about your work,and about itself, the longer you used it. That's Metis.

Metis isnot a separate app you log into.It's a small service that runs quietly in the background and connects Claude to your research — your papers, your memory, your projects.
- A background service(the "MCP server") starts with your computer. It's the bridge between Claude and your files — you never interact with it directly.
- You talk to Metis through Claude, two ways:

- Claude Desktop(easiest): open it and pick aMetis prompt(e.g.Metis,Metis Doctor) from the prompt menu — or just ask.
- Claude Code(terminal): type/metisfollowed by your request.

That's it. There's nothing to learn before you start; the dashboard is optional visibilityon topof all this.

Every AI conversation starts from zero. You spend ten minutes re-explaining your context, and when the session ends, it's gone. Generic AI tools are powerful but stateless — they know everything about the world and nothing about you.

Metis is built on one idea: the AI should know you. And it should keep getting better — on its own.

Not just your name — your domain, your literature, your projects, your preferred working style, your open questions, your meeting notes from last month, and the paper you added to your library yesterday. The longer you use Metis, the better every response gets. Not because the AI changes — because Metis knows you better.

You don't need to follow developments in AI.Metis does that for you. Every week, Metis reviews its own performance across all your sessions, identifies where it could have done better, drafts improvements to its own behaviour, and waits for your approval before applying them. As better methods and models become available, those improvements are folded in the same way — always proposed for your approval, never applied behind your back. As a researcher, you focus on your research. Metis handles keeping itself sharp.

The core mechanism is cross-pollination.Every time you capture an idea, add a paper, record a meeting, or complete a task, Metis connects it to everything else in your research universe. A paper you indexed a year ago surfaces when you're writing a grant today. A meeting note from March links to the idea you captured this morning. An open question from six months ago connects to a new paper that just came out. These connections happen automatically, in the background, without you having to search for them. This is what makes Metis aresearch companionrather than a search tool — it thinks across your entire body of work so you don't have to hold it all in your head.

This is genuinely new ground. The individual components — local language models, retrieval-augmented generation, agent routing, vector search — all exist independently. What Metis presents is a coherent integration of all of them, purpose-built for the specific demands of research work: long timelines, sensitive data, deep literature, and knowledge that accumulates over years. A system that growswithyou, and surfaces connectionsforyou — rather than starting from zero every session. To our knowledge, nothing quite like this exists as a unified, locally-running, researcher-facing system.

Where things stand today:The MCP server, 30+ agents, and the 9-tab dashboard are fully operational and used daily. The one-click installer and the pre-loaded domain knowledge layer are still being refined. This is a working system — not vaporware — but it is also not finished. If something breaks, please open an issue. That feedback shapes what gets built next.

No programming background needed. Everything below is point-and-click or copy-paste.

How Metis is powered — you choose (you won't burn API tokens just by using it)

- On your Claude subscription—no API key, no per-token bills.This is the everyday path: you talk to Metis throughClaude Desktop or Claude Code, and the dashboard's "✦ Update with Claude" / brainstorm buttons open Claude Desktop on your subscription. Most people use Metis entirely this way.
- With an Anthropic API key— only needed for things that runwhile you're not there: the scheduled morning scan and automated brief generation. Pay-per-token, typically a few cents a day.
- With a local model (Ollama)— optional, for fully-offline helper tasks (e.g. the data assistant).

The installer asks for an API key so automationcanrun, but you canskip it and use Metis on your subscription alone. Nothing in the interactive experience requires the API.

The key stays on your computer. It is never uploaded or shared.

Double-click the installer. The wizard walks you through:
- Full or AI only— Full gives you the AI assistant + 9-tab research dashboard (~15 min). AI only is faster (~5 min) and you can add the dashboard later.
- Your projects— Tell Metis what you're working on. It creates a tracking record for each project, writes a context file into the project folder, and registers it in Claude Desktop automatically.
- Demo workspace— Pre-loads realistic example projects, meetings, literature, and tasks so you can explore every feature immediately. Recommended for first-time users.
- API key— Paste it once.

Everything else is automatic. Claude Desktop opens at the end with Metis ready to go.

bash <(curl -fsSL https://raw.githubusercontent.com/SVerITG/Metis_PH/main/system/mcp-server/setup-mcp.sh)

The script asks two questions (Full or AI only, demo workspace) and does the rest. Registers Metis with Claude Desktop and Claude Code automatically. Works on Ubuntu 20/22/24, Debian, and macOS.

After installation — API key and updating

API key (optional):Copysystem/.env.exampletosystem/.envand add your key, or the installer will prompt you. The key enables automated features (morning briefs, scheduled scans); interactive use through Claude works without it.

Updating aftergit pull:The MCP server runs from a local copy of the source (not the repo directly). After pulling new code, re-sync with:

bash system/mcp-server/setup-mcp.sh --update

This re-copies the source, reinstalls the package, and applies migrations — without re-running the full wizard.

Moved the Metis folder?Update the marker file at~/.local/share/metis-mcp/.metis-rc-rootwith the new path, or re-run the installer.

The installer registers Metis with Claude Desktop and Claude Code automatically — you normally don't need to edit any config by hand. The blocks below are for reference (and for MCP directories): they show how themetis-rcserver is wired in.

Metis is not a one-linenpx/uvxserver.Run the installer first — it builds the local virtual environment, initialises the database, and generates the launch script (run.sh) the configs below point to.

Step 0 — install (builds the venv + DB, generatesrun.sh):

Claude Code (any OS)— done for you by the installer, or add it manually:

claude mcp add metis-rc ~/.local/share/metis-mcp/run.sh

Claude Desktop — macOS— in~/Library/Application Support/Claude/claude_desktop_config.json: