1
Your sources
Files, pages, recordings, notes — whatever your agent should remember.
Rag Capsules
The RAG offering, in one page. A capsule is a Rag Capsule: your files become memory your agents read from and write to, reachable over MCP and REST from the day it finishes building.
How it works
One pipeline, from a folder of files to a grounded answer.
A capsule is memory your agents read from and write to. The stack that builds it — the embeddings and the index — is disposable and rebuildable. The corpus, manifest, and eval set are the permanent asset.
2
Build
We distill the facts, embed them, and index them into a namespace that is yours alone.
Disposable — rebuildable at any time.
3
The capsule
corpusmanifesteval set
The permanent asset. Agents read and write — every write carries provenance and can be reverted.
4
Any agent
Ask, remember, recall — grounded answers with citations back to your sources.
Score each version against your own eval set, and export the whole capsule — rebuild the stack on any vector database, embedding model, or cloud.Read the open capsule spec →
Make your first Rag Capsule.
Free on the Developer tier — one capsule, no card. Drop in your files and query it from Claude, ChatGPT, or Gemini.