LangMem
LangMem is a lightweight, flexible Python SDK from LangChain that equips AI agents with long-term memory capabilities, enabling them to extract, store, update, and retrieve meaningful information from past interactions to become smarter and more personalized over time. It supports three memory types and offers both hot-path tools for real-time memory management and background consolidation for efficient updates beyond active sessions. Through a storage-agnostic core API, LangMem integrates seamlessly with any backend and offers native compatibility with LangGraph’s long-term memory store, while also allowing type-safe memory consolidation using schemas defined in Pydantic. Developers can incorporate memory tools into agents using simple primitives to enable seamless memory creation, retrieval, and prompt optimization within conversational flows.
Learn more
Hindsight
Hindsight is an agent memory system built to create smarter AI agents that learn over time instead of starting every conversation from zero. Most agent memory systems focus on recalling conversation history, but Hindsight is focused on making agents learn, not just remember. It gives AI agents persistent long-term memory using biomimetic data structures, helping them retain facts, recall relevant context, and reflect on experience as part of reasoning. Hindsight is designed for agents that need to understand who a user is, what has been discussed, what preferences have emerged, what decisions were made, and how behavior should adapt across sessions. It provides three core operations: retain, recall, and reflect. Retain stores new information, recall retrieves the right memories when needed, and reflect helps agents synthesize observations, form mental models, and learn from prior interactions.
Learn more
Pinecone
The AI Knowledge Platform.
The Pinecone Database, Inference, and Assistant make building high-performance vector search apps easy. Developer-friendly, fully managed, and easily scalable without infrastructure hassles.
Once you have vector embeddings, manage and search through them in Pinecone to power semantic search, recommenders, and other applications that rely on relevant information retrieval.
Ultra-low query latency, even with billions of items. Give users a great experience. Live index updates when you add, edit, or delete data. Your data is ready right away. Combine vector search with metadata filters for more relevant and faster results.
Launch, use, and scale your vector search service with our easy API, without worrying about infrastructure or algorithms. We'll keep it running smoothly and securely.
Learn more
Muse Spark 1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs built for agentic tasks, coding, computer use, tool use, and multimodal understanding. The model improves on the original Muse Spark with stronger performance in planning, orchestration, long-context work, coding workflows, and external app interactions. Muse Spark 1.1 can manage a 1 million token context window, remember earlier actions, retrieve important information, compact context, and delegate tasks across parallel subagents. It is designed to operate across tools, MCP servers, custom skills, browsers, native apps, scripts, images, video, PDFs, and audio-based workflows. Developers can access Muse Spark 1.1 through the new Meta Model API public preview, while users can try it in Thinking mode in the Meta AI app and on meta.ai.
Learn more
