Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
LanceDB vector store for @vivantel/rag-core (embedded, file-based)
ChromaDB vector store for @vivantel/rag-core (local or hosted)
Qdrant vector store for @vivantel/rag-core (local and cloud)
OpenCode plugin that gives coding agents persistent memory using local vector database
SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.
Zero-dependency TypeScript middleware for dynamic vector space transformation. Warp embeddings at runtime with WASM-accelerated affine transforms, quantization, online learning, and ColBERT — no retraining needed.
Universal Knowledge Protocol™ - World's first Triple Intelligence database unifying vector, graph, and document search in one API. Stage 3 CANONICAL: 42 nouns × 127 verbs covering 96-97% of all human knowledge.
TypeScript client for Quiver — a security-first, memory-frugal vector database.
VelesDB TypeScript SDK: The Local Vector Database for AI & RAG. Microsecond semantic search in Browser & Node.js.
TypeScript/JavaScript SDK for Dakera AI memory platform
TypeScript SDK for Cognipeer Console - Multi-tenant AI services platform
OpenCode plugin that gives coding agents persistent memory using local vector database
JavaScript & TypeScript Client SDK for CyborgDB: The Confidential Vector Database
NestJS Qdrant vector database integration for semantic search and retrieval
Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory. Branch a base memory in ~0.5ms / 162 bytes regardless of base size — 83x faster, 3000x smaller than full-copy snapshots. Exact read-through queries (parent ∪ edits, chil
Chitta - permission-aware memory for AI agents: a knowledge-graph + vector memory MCP server with per-user access control. Runs on Bun. By 100xprompt.
Zero-Config Chroma DB Workbench — An AI-native GUI for the Chroma vector database.Browse collections, perform semantic search, explore metadata, visualize embeddings, and interact with a powerful query console — all without any configuration. Launch inst
The AI-native GUI for Weaviate. Browse schemas, run GraphQL queries, use RAG tools, perform hybrid search, and import CSV data — all in one place. Get started instantly with: npx weaviate-db-extensionAccess the Weaviate client from anywhere: npm, deskto
JavaScript/TypeScript client for nidus — a small, fast vector store. Connects to a local or remote nidus serve over HTTP.
Brain-inspired, model-agnostic persistent memory for LLMs. Learn, recall, forget — like a brain. Works with OpenAI, Claude, Gemini, Llama.
Advanced memory management system for AI agents with semantic retrieval, hierarchical structures, and multi-agent support
VelesDB for WebAssembly - Vector search in the browser
Monomind CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code