Understanding Palim
Palim is the shared, persistent knowledge base for the AI tools you connect.
Palim connects MCP-compatible AI tools to a shared knowledge base. You decide which work states, complete chats, and durable facts are stored. Another connected tool can retrieve them later.
The four building blocks
| Building block | Best for | Content |
|---|---|---|
| Context snapshot | Hand-offs between AI tools | A compact work state without the complete message history |
| Session | Traceable chat history | A full conversation with messages, summary, and metadata |
| Memory | Durable facts and decisions | A single piece of information that can be edited or deleted |
| Brain | An overview of recurring topics | A topic view derived from saved content in the dashboard |
Palim does not save every chat automatically
A connected AI client must call a Palim tool. You can request that directly or configure a suitable auto-save rule in your client.
A typical workflow
- Connect at least one AI client to Palim.
- Say: “Capture the current state for my other AI tools.”
- Open another connected tool later.
- Ask: “What did we decide about the auth flow in Project Atlas?”
Palim searches the stored content and returns matching results to the client. The AI then decides how to use those results in its response.
What search supports today
Palim uses PostgreSQL full-text search and text matching. You can also filter by date range, tags, project, and source. Semantic embedding search is not implemented yet.
Last updated on