SVerITG/Metis

AI built around researchers. Not a prompt box — a way of working.
Your papers, meetings, ideas, notes and journal — each one linked to the rest.
A research companion that reviews its own work and gets sharper every week.
It's 7:20. You open the dashboard. The morning brief reads:
"Three papers matching your configured topics landed overnight — one directly challenges a working hypothesis in your field. Your literature coverage in methods has grown to 84%. I've cross-referenced all three with your knowledge graph, connected them to your meeting note from Tuesday, and flagged four passages for your review. One tracked analysis is approaching a key deadline."
No prompt. No setup. Your research, connected — every morning.
🟢 Actively developed.  Latest: plan a run of days on one row · a Work view ordered by what you actually touched · and a month of controls that rendered perfectly and did nothing, found and fixed.   See what's new ↓
☁️ Light MCP server only
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.
One install, any field. Metis ships domain-agnostic and builds
your field's knowledge layer from your own documents during setup —
or from a downloadable background pack.
> ### 📚 Knowledge layers are built, not bundled
> Metis ships with the machinery to build a searchable knowledge layer and none of the content. Point it at a folder of your own papers, reports and guidance and it indexes them into a corpus you can ask grounded, cited questions against. Prefer to start with something? Install a **background pack** — an index over public sources, distributed as vectors and a manifest, never as the source documents.
---
See it in action
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.
---
Why researchers trust it
- **📚 It cites your own sources.** Knowledge answers are anchored in *your* indexed 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. (An automated test covers the retrieval half of this: that an in-corpus question returns the right document with its page, and that an out-of-corpus one scores markedly weaker. Whether the model then says so in words is not yet asserted by a test.)