Write like you always have. AI's already plugged in.
Write it, or import it from Notion. One API key and your agent lets itself in — ask, and the answer's instant.
Why Rootr
Same way you write. New AI attached.
Just like Notion
Real-time co-editing, callouts, diagram blocks. Write like always — or bring your whole Notion workspace over.
AI lets itself in
Hand over one API key and an agent like Claude Code lets itself in. Say "build me a workspace" — it does the rest.
Upload it. Get answers.
Save it, and it's organized instantly. Ask, and the answer comes back with its source.
No pipeline. No setup. Just write, and ask.
How it's different
Not a keyword search. A cause-finder.
Generic AI search pulls a few documents that share your keywords and stitches an answer together. Rootr reads across your docs, logs, and records — and connects them to explain what actually happened.
In practice
Say a machine fails. Rootr doesn't just quote the manual — it checks the maintenance doc, reads the sensor log, and links yesterday's work record to point out: "B changed a setting yesterday, and that's why A stopped today."
For your team
Keep working in docs and sheets like always. Rootr weaves that knowledge together so it outlives turnover — a new hire finds answers like a ten-year veteran.
For your engineers
No embedding, chunking, or vector-DB nights. Drop in markdown or logs and a GraphRAG backend comes out — build on the API and llms.txt.
A database anyone can use
Skip the SQL. Just ask.
Database, logs, or millions of lines of docs — one sentence replaces the query. The answer comes back in plain language any executive can read.
In SQL
SELECT service, COUNT(*) FROM deploy_logs WHERE status='failed' GROUP BY service ORDER BY COUNT(*) DESC LIMIT 5;With Rootr
What were the top 5 services with the most deploy failures last month?
Ask it like this
- What were the top 5 services with the most deploy failures last month?
- Which three regions had the highest revenue in Q3?
- What onboarding steps does a new hire need in their first week?
→ Comes back with the source attached
The old way
Write a SELECT ... FROM ... query, or ask an engineer and wait.
With Rootr
One sentence replaces the query — like "show me the top 5 deploy failures." The answer comes back instantly, with its source.
It doesn't matter how deep the docs go. Ask, and you get an answer any executive can understand right away.
Features
Docs, databases, logs — one workspace.
Document editor
Write like Notion. Tables, diagrams, all of it.
A single "deploy process" doc holds a callout, a table, and a rendered Mermaid diagram — no separate wiki, no separate diagramming tool. Edit it together in real time, and the whole page round-trips to plain markdown underneath.
- Real-time co-editing, no save button
- Callout, table & diagram blocks in one page
Database
View it as a table. Flip to a board. Same data.
The "incident tracker" holds 8 rows tagged by status and severity. Flip the view from table to kanban board and the same 8 records rearrange themselves — no export, no second copy to keep in sync.
- Status & severity badges (Resolved/In Progress/Investigating, P1–P3)
- Table ↔ board, same records, zero re-entry
Other doc types
Spreadsheets, whiteboards, forms — all in one workspace.
Spreadsheet
Formulas work too.
The "quarterly budget" sheet isn't a static table — cells reference each other, and formulas like =SUM(...) recalculate the moment a number changes.
Whiteboard
Sketch the structure.
In this "architecture sketch," boxes for Next.js, NestJS, and Postgres connect with edges, laying out how the pieces fit together without a paragraph of explanation.
Forms
Submit it, and it lands in a database.
Submit this "customer feedback" form and the response lands as a new row in the connected database immediately — no copy-paste, no separate spreadsheet to reconcile later.
Typed logs
Anomalies turn red automatically.
In this "equipment temperature log," two entries that break from the normal range are flagged red automatically. A lineage panel at the bottom links those readings straight to the "maintenance records" that document what was done about them.
- Automatic anomaly detection, no thresholds to set
- Built-in lineage panel to upstream docs
Data lineage
Draw a relation, get a cause chain.
A relation field on the temperature log points to the maintenance record via an AFFECTS relation — no manual diagramming. Follow that edge across the graph, hop by hop, to trace a reading back to its likely cause.
- Relation fields = automatic lineage
- Visualized as nodes & edges
Knowledge graph
The more you write, the more the graph grows.
Every document, database record, and log entry becomes a node; every relation and reference becomes an edge. The graph updates automatically as you write — no separate modeling step.
Use cases
From team docs, to your own agent, to incident response.
Team knowledge base
Instead of Notion, or migrated straight from it. A new hire asks "what's our deploy process?" — the assistant answers with the source attached.
A RAG backend for your agent
Building your own LLM app? Skip building a doc store. Point it at Rootr via API, and it's a ready-made answer engine.
Ops & root-cause analysis
An alert fires at 2am — the assistant scans recent logs and lineage, narrows it to a handful of likely causes. From there, it's a human call.
Developers
Drop in markdown. Get a RAG endpoint.
Every doc is automatically parsed and woven into a queryable graph in the background — no pipeline to build, no vector DB to provision. Query it via REST or GraphQL, or point your agent at llms.txt. Scoped API keys per integration.
Read the API docsExample: how an agent lets itself in
# 1) the agent reads the workspace + how to auth curl https://YOUR_WORKSPACE.rootr.io/llms.txt # 2) ask, with a scoped API key → a sourced answer POST /api/v1/ask # 3) or let it build a whole new workspace POST /v1/scaffold/workspace
One line of llms.txt and an agent reads the structure and how to authenticate. From there, /api/v1/ask for a sourced answer, or /v1/scaffold/workspace to build a new workspace.
Built for people organizing team knowledge, builders wiring their own agents to real data, and ops teams tracking down root causes on live systems.
Pricing
Simple, per-seat pricing.
Prices shown are monthly. Pay annually and get 2 months free.
Free
$0
3 seats · 256 MB storage · 500 AI credits / month · 2,000 graph credits / month (auto knowledge-graph sync)
Team
$6
per seat / month, billed monthly
Up to 25 seats · 1 GB + 0.25 GB/seat storage · 20,000 AI credits / month · 20,000 graph credits / month (auto knowledge-graph sync)
Business
$14
per seat / month, billed monthly
Unlimited seats · 10 GB + 2.5 GB/seat storage · 100,000 AI credits / month · 100,000 graph credits / month (auto knowledge-graph sync)
Platform
Usage-based
Custom seat & usage terms · Unlimited AI & graph credits · API-first access · Dedicated onboarding
Free: 3 seats · 256 MB · 500 AI credits/month · 2,000 graph credits/month · no credit card
Taxes may apply and will be calculated at checkout.
FAQ
Questions, answered.
- Isn't this just Notion?
- The editor's as familiar as Notion — you can even import a whole workspace. The difference: the moment you write, it's AI-searchable, and one API key lets your agent answer from it directly.
- Is there a click-through wizard where AI sets everything up?
- Not a dedicated screen yet. Give an API key to the embedded assistant or an agent like Claude Code, and it builds the structure via API instead.
- Can I pull data without knowing SQL?
- Yes. Ask in plain language against your typed data stores or docs — no query syntax to learn.
- Do I need to restructure my logs to use this?
- Define typed columns once; relation fields become lineage automatically. No separate ETL pipeline.
- Can I connect my own LLM or agent?
- Yes. REST, GraphQL, and llms.txt work with any model or agent.
- Is the AI inside Rootr built on Claude?
- No. Rootr's built-in features run on our own AI models. External agents like Claude Code can connect via our API — that's not the same as Rootr being built on Claude.
- What happens to my docs?
- Write the way you normally would. Everything else happens automatically in the background.
- Do I need a credit card to try it?
- No. Free includes 3 seats, 256 MB storage, 500 AI credits, and 2,000 graph credits per month.
- How is this priced?
- Per seat, plus AI credits and storage that scale with your plan. See full pricing →
- Who is this for?
- Teams organizing shared knowledge, developers wiring their own agents to real data, and ops/manufacturing teams tracking down root causes.
Keep writing the way you do. We already attached the AI.
No credit card required · 3 seats free