33 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-07-15 01:30 UTC
HVTracker independently evaluates 33 memory & knowledge using daily signals from GitHub, package registries, and security databases. The category is open-source-first, with a limited set of public GitHub-hosted proprietary or source-available comparators when they are important ecosystem reference points. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked memory & knowledge is LanceDB with a trust score of 86.8/100 (Grade A). Other leading projects include Mem0 and Vespa.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | LanceDB A Listed Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. | 86.8 | 10.9k | HTML |
| 2 | Mem0 A Listed Universal memory layer for AI Agents | 86.1 | 60.8k | TypeScript |
| 3 | Vespa A Listed The AI search platform | 85.6 | 7.0k | Java |
| 4 | LightRAG A Listed [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" | 82.8 | 37.7k | Python |
| 5 | Graphiti A Listed Build Real-Time Knowledge Graphs for AI Agents | 82.7 | 28.7k | Python |
| 6 | Hindsight A Listed Hindsight: Agent Memory That Learns | 82.5 | 18.4k | Python |
| 7 | Chroma B Listed Search infrastructure for AI | 76.4 | 28.8k | Rust |
| 8 | FAISS B Listed A library for efficient similarity search and clustering of dense vectors. | 74.8 | 40.5k | C++ |
| 9 | GraphRAG B Listed A modular graph-based Retrieval-Augmented Generation (RAG) system | 71.8 | 34.4k | Python |
| 10 | Milvus B Listed Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search | 71.7 | 45.2k | Go |
| 11 | Tidb B Listed TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, a | 70.8 | 40.3k | Go |
| 12 | Khoj B Listed Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, d | 69.8 | 35.7k | Python |
| 13 | Weaviate B Listed Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector | 67.9 | 16.6k | Go |
| 14 | Cognee B Listed Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions | 66.9 | 27.9k | Python |
| 15 | RAGFlow B Listed RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capa | 66.1 | 85.0k | Go |
| 16 | Vellum Assistant B Listed An AI Assistant thatβs easy to setup, does your work 24/7, knows your preferences and gets better over time. | 65.9 | 881 | TypeScript |
| 17 | txtai C Listed π‘ All-in-one AI framework for semantic search, LLM orchestration and language model workflows | 64.7 | 12.7k | Python |
| 18 | Zvec C Listed A lightweight, lightning-fast, in-process vector database | 64.0 | 14.9k | C++ |
| 19 | Beads C Listed Beads - A memory upgrade for your coding agent | 62.0 | 25.3k | Go |
| 20 | MemOS C Listed Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with | 61.5 | 10.2k | TypeScript |
| 21 | agentmemory C Listed #1 Persistent memory for AI coding agents based on real-world benchmarks | 60.2 | 25.1k | TypeScript |
| 22 | PrivateGPT C Listed Interact with your documents using the power of GPT, 100% privately, no data leaks | 57.1 | 57.3k | Python |
| 23 | WeKnora C Listed Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-m | 56.7 | 18.3k | Go |
| 24 | pgvector C Listed Open-source vector similarity search for Postgres | 56.4 | 22.2k | C |
| 25 | Qdrant C Listed Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also av | 55.5 | 33.3k | Rust |
| 26 | Letta C Listed Platform for stateful agents: AI with advanced memory that can learn and self-improve over time. | 55.0 | 23.8k | Python |
| 27 | ByteRover CLI C Listed ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher) | 52.7 | 4.9k | TypeScript |
| 28 | LLM Wiki Agent C Listed A personal knowledge base that builds and maintains itself. Drop in sources β Claude (or Codex/Gemini) reads them, extra | 50.3 | 3.2k | Python |
| 29 | OpenViking D Listed Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | 47.1 | 26.7k | Python |
| 30 | AnythingLLM D Listed Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | 43.1 | 63.3k | JavaScript |
| 31 | Quivr D Needs review Opiniated RAG for integrating GenAI in your apps π§ Focus on your product rather than the RAG. Easy integration in exis | 29.4 | 39.2k | Python |
| 32 | EverOS D Listed One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, t | 22.6 | 11.0k | Python |
| 33 | Memvid D Listed Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents | 20.8 | 15.8k | Rust |