Letta builds a smart assistant
The story so far
Letta has built Stateful Agentic Engineering Copilots capable of persistent memory, shared state, and semantic search. LangChain found that nearly 70% of Managed Deep Agents run from scheduled tasks, enabling agents to possess proactivity, personalization, and ambient characteristics through mechanisms such as memory, proactivity, intelligent filtering, and reminders.
AI-written from the reports · Updated 21 days ago
Developments
2 developments
- 28 Oct, 15:15 · 1 reportsPublishing tutorialLangChain Blog:Why aren’t you building proactive agents yet?
- 24 Oct, 18:29 · 1 reportsBuilding engineering assistants with persistent memoryMarkTechPost:Stateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows
Coverage timeline
Follow the coverage to see every side of the story.
- LangChain BlogWhy aren’t you building proactive agents yet?
LangChain found that nearly 70% of Managed Deep Agents run from scheduled tasks. Crons enables agents to have proactivity, personalization, and ambient characteristics by implementing mechanisms such as memory ('dreaming'), proactivity (exploring new actions), intelligent filtering (monitoring event streams), and reminders (scheduled tasks).
- MarkTechPostStateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows
Letta allows developers to create Stateful Agentic Engineering Copilots with persistent memory, shared state, and semantic search capabilities.