mirror of
https://github.com/supermemoryai/supermemory.git
synced 2026-09-07 08:26:15 +00:00
9553434c9a
adds withSupermemory wrapper and input/output processors for
mastra agents:
- input processor fetches and injects memories into system prompt
before llm calls
- output processor saves conversations to supermemory after
responses
- supports profile, query, and full memory search modes
- includes custom prompt templates and requestcontext support
const agent = new Agent(withSupermemory(
{ id: "my-assistant", model: openai("gpt-4o"), instructions:
"..." },
"user-123",
{ mode: "full", addMemory: "always", threadId: "conv-456" }
))
includes docs as well
this pr also reworks how the tools package works into shared modules
3 lines
459 B
XML
3 lines
459 B
XML
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 34 21">
|
|
<path fill="currentColor" d="M4.5 11.7a4.5 4.5 0 1 1 0 9 4.5 4.5 0 0 1 0-9M10.4 0a4.5 4.5 0 0 1 4.4 5.5c-.3 1.4-.6 3 .2 4.2l1.3 1.8.3.2q.2 0 .3-.2l1.3-1.9c.8-1.1.5-2.7.2-4a4.5 4.5 0 1 1 8.8 0c-.3 1.3-.6 2.8 0 4l1.3 2a4.5 4.5 0 1 1-4.3 3.5c.3-1.3.6-2.8 0-4l-1.2-2h-.2L21.5 11c-.8 1.2-.5 2.8-.2 4.2a4.5 4.5 0 1 1-8.8.2q.5-2-.4-3.8l-.9-1.3q-.9-1.1-2.4-1.6A4.5 4.5 0 0 1 10.4 0"/>
|
|
</svg>
|
