Go · PyPI88Excellenthealth index
weaviate/weaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Go★ 16.6KJul 17, 2026
Go · PyPI87Excellenthealth index
creativesoftwarefdn/weaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Go★ 16.6KJul 17, 2026
Go · PyPI87Excellenthealth index
semi-technologies/weaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Go★ 16.6KJul 17, 2026
Go86Excellenthealth index
milvus-io/milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Go · Python · C++★ 45.2KJul 15, 2026
Go · npm · PyPI84Goodhealth index
danswer-ai/danswerOpen Source AI Platform - AI Chat with advanced features that works with every LLM
Python · TypeScript★ 30.9KJul 17, 2026
PyPI · crates.io84Goodhealth index
nuclia/nucliadbNucliaDB, The AI Search database for RAG
Python · Rust★ 718↓ 71.5K/moJul 22, 2026
PyPI · Go · npm84Goodhealth index
onyx-dot-app/onyxOpen Source AI Platform - AI Chat with advanced features that works with every LLM
Python · TypeScript★ 30.9K↓ 3,993/moJul 17, 2026
crates.io83Goodhealth index
meilisearch/meilisearchA lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
Rust★ 58.6KJul 15, 2026
Maven · RubyGems83Goodhealth index
vespa-engine/vespaThe AI search platform
Java · C++★ 7,020Jul 16, 2026
redis/redis-vl-pythonRedis Vector Library (RedisVL) -- the AI-native Python client for Redis.
Python★ 416↓ 2.5M/moJul 21, 2026
PyPI · Go · npm80Goodhealth index
infiniflow/infinityThe AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
C++★ 4,609Jul 15, 2026
weaviate/weaviate-python-clientA python native client for easy interaction with a Weaviate instance.
Python★ 226Jul 18, 2026
redis/redisFor developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
C · Tcl★ 75.6KJul 22, 2026
Go · npm · PyPI77Goodhealth index
Tencent/WeKnoraOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Go · Vue · TypeScript★ 18.7KJul 21, 2026
qdrant/fastembedFast, Accurate, Lightweight Python library to make State of the Art Embedding
Python · Jupyter Notebook★ 3,092Jul 18, 2026
weaviate/typescript-clientOfficial Weaviate TypeScript Client
TypeScript★ 101↓ 1.4M/moJul 22, 2026
crates.io · npm · Go +173Goodhealth index
ashvardanian/NumKongSIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐
C · C++★ 1,851↓ 34K/moJul 21, 2026
qdrant/qdrant-clientPython client for Qdrant vector search engine
Python★ 1,327↓ 24M/moJul 18, 2026
crates.io72Goodhealth index
Anush008/fastembed-rsRust library for generating vector embeddings, reranking locally!
Rust★ 963↓ 416.6K/moJul 17, 2026
PyPI · crates.io72Goodhealth index
pinecone-io/python-sdkOfficial Python SDK for the Pinecone vector database
Python★ 447↓ 7.9M/moJul 21, 2026
crates.io · Go · Maven +272Goodhealth index
unum-cloud/USearchFast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
C++★ 4,211↓ 181.9K/moJul 14, 2026
npm · crates.io69Moderatehealth index
GlitterKill/sdl-mcpSymbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.
TypeScript★ 448↓ 17.1K/moJul 17, 2026
PyPI · npm68Moderatehealth index
cdeust/CortexPersistent memory for Claude Code built on computational neuroscience, not just retrieval. 36 cited brain mechanisms consolidate what matters, keep it current as your project evolves, and reconstruct the right context at the right time — a living memory, not a flat RAG. Says "I don't know" when unsure, flags contradictions. Local-first · MCP · MIT.
Python★ 67↓ 2,447/moJul 15, 2026
npm68Moderatehealth index
dcostenco/prism-coderPersistent memory + local AI for coding agents. 2B–27B open-weight LLM fleet, cross-session Mind Palace, cognitive routing, L3 grounding verifier, multi-agent Hivemind. Works with Claude Code, Cursor, VS Code. Offline-first, HIPAA-ready. Free tier included.
TypeScript★ 155↓ 5,205/moJul 18, 2026
NuGet67Moderatehealth index
JerrettDavis/JD.SemanticKernel.ExtensionsSemantic Kernel extensions for Claude Code skills, hooks, context compaction, and semantic memory.
C#★ 1Jul 21, 2026
npm66Moderatehealth index
flowing-abyss/obsidian-hybrid-searchHybrid search over your Obsidian vault – CLI and MCP server
TypeScript★ 88↓ 4,503/moJul 18, 2026
crates.io · Go · npm +166Moderatehealth index
major7apps/pensyveUniversal memory runtime for AI agents
Rust · Python★ 56↓ 127/moJul 17, 2026
npm · PyPI66Moderatehealth index
qualixar/superlocalmemoryWorld's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588
Python★ 197↓ 9,312/moJul 19, 2026
npm66Moderatehealth index
rush-db/rushdbRushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
TypeScript★ 315↓ 0/moJul 14, 2026
npm65Moderatehealth index
aliasunder/vault-cortexStandalone MCP server for Obsidian vaults — hybrid search, structured memory, tasks, and full vault access for any AI agent
TypeScript★ 9↓ 3,083/moJul 14, 2026