A separate knowledge layer for organization-specific AI agents
The design puts a between an organization’s documents and the AI tools people already use, such as ChatGPT or Claude. It is not meant to be another chatbot. It gives an a controlled place to read trusted material and write back useful results.
Each organization gets its own isolated installation, with its own server and its own data, so one organization’s information cannot accidentally mix with another’s. Original Word, PowerPoint, PDF, and similar files stay unchanged on disk. Extracted text is stored as markdown with extra notes about the file.
The and database are treated as rebuildable caches, not as the main . If the or chunker changes, the system can rebuild the index from disk instead of running a complicated data migration. A manifest and event log record why each document exists and which extractor, chunker, , and access policy handled it.
Key points
- Each organization would run its own separate server and data store.
- connect through MCP instead of being replaced by this system.
- Original documents stay untouched, while extracted text is stored as markdown.
- The and database can be rebuilt from files on disk.
- Changing the or chunker means reindexing, not migrating the main data.