Memory & Knowledge
44 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-08-29 06:32 UTC
HVTracker independently evaluates 44 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 ReMe with a trust score of 88.3/100 (Grade A). Other leading projects include Vespa and LanceDB.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | ReMe A Listed ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. | 88.3 | 3.4k | Python |
| 2 | Vespa A Listed The AI search platform | 87.9 | 7.1k | Java |
| 3 | LanceDB A Listed Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. | 86.6 | 11.3k | Rust |
| 4 | Mem0 A Listed Universal memory layer for AI Agents | 86.2 | 64.3k | Python |
| 5 | Graphiti A Listed Build Real-Time Knowledge Graphs for AI Agents | 85.4 | 30.4k | Python |
| 6 | LightRAG A Listed [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" | 84.0 | 39.3k | Python |
| 7 | Hindsight A Listed Hindsight: Agent Memory That Learns | 83.4 | 21.6k | Python |
| 8 | Weaviate B Listed Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector | 74.7 | 16.8k | Go |
| 9 | FAISS B Listed A library for efficient similarity search and clustering of dense vectors. | 74.2 | 40.8k | C++ |
| 10 | Chroma B Listed Search infrastructure for AI | 73.8 | 29.2k | Rust |
| 11 | GraphRAG B Listed A modular graph-based Retrieval-Augmented Generation (RAG) system | 73.6 | 35.7k | Python |
| 12 | Milvus B Listed Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search | 73.1 | 45.9k | Go |
| 13 | RAGFlow B Listed RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capa | 72.1 | 89.6k | Go |
| 14 | Tidb B Listed TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, a | 71.5 | 40.5k | Go |
| 15 | Qdrant B Listed Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also av | 71.3 | 34.2k | Rust |
| 16 | Cognee B Listed Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions | 69.1 | 30.3k | Python |
| 17 | Code-Graph-RAG B Listed The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowle | 68.6 | 4.8k | Python |
| 18 | Vellum Assistant B Listed An AI Assistant thatβs easy to setup, does your work 24/7, knows your preferences and gets better over time. | 68.6 | 1.2k | TypeScript |
| 19 | txtai B Listed π‘ All-in-one AI framework for semantic search, LLM orchestration and language model workflows | 68.2 | 12.9k | Python |
| 20 | Khoj B Listed Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, d | 67.4 | 36.8k | Python |
| 21 | agentmemory B Listed #1 Persistent memory for AI coding agents based on real-world benchmarks | 67.1 | 27.7k | TypeScript |
| 22 | Zvec C Listed A lightweight, lightning-fast, in-process vector database | 64.3 | 15.5k | C++ |
| 23 | MemOS C Listed Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with | 62.3 | 11.1k | TypeScript |
| 24 | Beads C Listed Beads - A memory upgrade for your coding agent | 61.6 | 26.7k | Go |
| 25 | Letta C Listed Platform for stateful agents: AI with advanced memory that can learn and self-improve over time. | 61.5 | 24.5k | Python |
| 26 | WeKnora C Listed Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-m | 61.3 | 20.9k | Go |
| 27 | memU C Listed Personal memory across agents | 61.0 | 14.4k | Python |
| 28 | PrivateGPT C Listed Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works wi | 59.5 | 57.5k | Python |
| 29 | pgvector C Listed Open-source vector similarity search for Postgres | 57.9 | 22.8k | C |
| 30 | Titen C Listed Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over std | 57.9 | 11 | TypeScript |
| 31 | OpenViking C Listed Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | 56.6 | 34.2k | Python |
| 32 | LLM Wiki Agent D Listed A personal knowledge base that builds and maintains itself. Drop in sources β Claude (or Codex/Gemini) reads them, extra | 49.7 | 3.5k | Python |
| 33 | LightMem D Listed [ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation | 49.3 | 1.1k | Python |
| 34 | ByteRover CLI D Listed ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher) | 46.0 | 5.0k | TypeScript |
| 35 | Memvid D Listed Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents | 45.8 | 16.5k | Rust |
| 36 | EverOS D Listed One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, t | 45.7 | 12.5k | Python |
| 37 | LycheeMemory D Listed Lightweight Long-Term Memory for LLM Agents. | 43.8 | 1.2k | Python |
| 38 | AnythingLLM D Listed Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | 43.6 | 65.4k | JavaScript |
| 39 | CodeGraphContext D Listed An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants. | 43.2 | 4.1k | Python |
| 40 | Honcho D Listed Memory library for building stateful agents | 40.4 | 6.9k | Python |
| 41 | IWE D Listed Markdown knowledge graph β LSP for your editor, CLI + MCP memory for your AI agents | 39.2 | 1.6k | Rust |
| 42 | Pond D Listed Lossless storage and search for AI agent sessions, across every agentic client. | 38.5 | 53 | Rust |
| 43 | 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 | 30.8 | 39.4k | Python |
| 44 | inno-agent D Listed An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversati | 23.8 | 980 | TypeScript |
Grade = trust band: A β₯ 80, B β₯ 65, C β₯ 50, D < 50 β methodology