past.dev
past.dev is a long-term memory API for developers building AI agents and applications. Applications send timestamped text from conversations, email, meetings, support records, CRM notes, and documents; the service derives memories and returns ranked results with dates and excerpts from the source data. Its API supports ingestion, batch ingestion, recall, deletion, project and identity management, audience-based access controls, and webhooks. Developers can connect through JSON endpoints or authenticated Model Context Protocol servers, and install companion plugins for Claude Code, Codex, Cursor, JetBrains IDEs, and Hermes Agent. The managed cloud service offers a console for API keys, usage, and request logs; enterprise deployments can run in a customer's AWS, Google Cloud, or Azure account. It is aimed at software teams adding persistent, source-grounded memory to AI agents and other applications.
Learn more
SenseLab
SenseLab is a cloud-based memory and learning layer for AI agents and agent-driven applications. It provides shared knowledge spaces (“Rooms”) where agents and teams can record, retrieve, and share context across sessions, models, and tools. Agents can store findings, decision context, and outcomes; the service maintains versioned records and uses outcome feedback to adjust confidence in knowledge. SenseLab provides an MCP server and Python and TypeScript SDKs for connecting agent clients and applications through API-key access. Teams can use it to carry context between agents, coordinate work, review decision histories, and retain structured traces for evaluation or model-training workflows. It is intended for developers and organizations building systems with multiple AI agents. The vendor also documents a self-hosting option through its open-source codebase.
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
Qdrant
Qdrant is a high-performance, composable vector search engine built in Rust for production-grade semantic, hybrid, and agentic workloads.
Combine dense vectors, sparse vectors, metadata filters, multi-vector representations, and custom scoring as primitives at query time. Written in Rust for memory efficiency, SIMD optimization, and predictable performance without garbage collection pauses. No wrappers, no bolt-ons, no legacy compromises — just a custom HNSW implementation and storage engine built specifically for vector workloads.
Learn more
