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
Add documentation for using Supermemory with CrewAI multi-agent
systems. Covers user profiles, memory storage, search, and includes
a complete research crew example.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clawdbot docs
Changes:
- Added integrations/clawdbot.mdx — ClawdBot Supermemory Plugin documentation page with shrimp icon
- Added "Plugins" group to the bottom of the Integrations sidebar in docs.json
- Page covers: API key setup (zsh/bash/PowerShell), plugin install, how it works (auto-recall/auto-capture), features (AI
tools, slash commands, CLI), manual configuration, and advanced options
- Created a new `useOrgOnboarding` hook that uses `org.metadata.isOnboarded` to track onboarding state
- Updated the home page to conditionally use either the old localStorage-based onboarding or the new DB-backed onboarding based on feature flag
- Added a "Restart Onboarding" option in the user dropdown menu
- Improved the onboarding chat sidebar with per-link loading indicators
- Enhanced the X/Twitter research API to better handle different URL formats
- Updated the integrations step to use the new onboarding completion method
- Added `updateOrgMetadata` function to the auth context for easier metadata updates
#### RE-RAISING Pipecat live speech PR
### Added native speech-to-speech model support
### Summary:
- Speech-to-speech support - Auto-detect audio frames and inject memories to system prompt for native audio models (Gemini Live, etc.)
- Fix memory bloating - Replace memories each turn using XML tags instead of accumulating
- Add temporal context - Show recency on search results ([2d ago], [15 Jan])
- New inject_mode param - auto (default), system, or user
### Docs update
- Update the docs for native speech-2-speech models
### Add user display name functionality and enhance space management with emoji support and deletion capabilities.
### What changed?
- Added support for user display names, which are now stored and displayed throughout the app
- Implemented emoji support for spaces (projects), allowing users to customize their space icons
- Created a new `AddSpaceModal` component with emoji picker for creating spaces
- Added space deletion functionality with options to move content to another space or delete everything
- Enhanced the space selector UI to show emojis and delete options
### TL;DR
Redesigned the browser extension UI with a dark theme and improved the Twitter bookmarks import experience with a new onboarding flow.
### What changed?
- Added a new `RightArrow` icon component for UI navigation
- Completely redesigned the popup UI with a dark theme and improved layout
- Enhanced Twitter bookmarks import functionality:
- Added an onboarding toast that appears the first time a user visits the bookmarks page
- Implemented a persistent import intent system that automatically opens the import modal when navigating to the bookmarks page
- Created a progress toast to show import status
- Improved folder import UI
- Updated the extension icon and added a new logo SVG
- Improved the project selection modal with better styling
