updated 2026-08-08 13:31 UTC

Memory & Knowledge

38 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-08-08 13:31 UTC

HVTracker independently evaluates 38 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 87.1/100 (Grade A). Other leading projects include Vespa and Mem0.

38
Agents
64
Avg Trust
968.5k
Total Stars
6
Grade A
1
Warnings
# Agent Trust Stars Language
1 LanceDB A Listed Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. 87.1 11.1k Rust
2 Vespa A Listed The AI search platform 86.3 7.0k Java
3 Mem0 A Listed Universal memory layer for AI Agents 86.3 62.8k Python
4 Graphiti A Listed Build Real-Time Knowledge Graphs for AI Agents 86.0 29.7k Python
5 LightRAG A Listed [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" 83.7 38.6k Python
6 Hindsight A Listed Hindsight: Agent Memory That Learns 83.0 19.3k Python
7 FAISS B Listed A library for efficient similarity search and clustering of dense vectors. 75.7 40.7k C++
8 Weaviate B Listed Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector 75.0 16.7k Go
9 Chroma B Listed Search infrastructure for AI 74.7 29.0k Rust
10 ReMe B Listed ReMe: Memory Management Kit for Agents - Remember Me, Refine Me. 74.0 3.3k Python
11 GraphRAG B Listed A modular graph-based Retrieval-Augmented Generation (RAG) system 72.6 35.3k Python
12 Milvus B Listed Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search 72.4 45.6k Go
13 RAGFlow B Listed RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capa 72.0 87.1k 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 40.4k Go
15 Qdrant B Listed Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also av 71.4 33.9k 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 29.9k Python
17 Khoj B Listed Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, d 68.8 36.4k Python
18 txtai B Listed 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows 68.5 12.8k Python
19 Vellum Assistant B Listed An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time. 67.7 1.0k TypeScript
20 agentmemory B Listed #1 Persistent memory for AI coding agents based on real-world benchmarks 66.8 26.7k TypeScript
21 Zvec C Listed A lightweight, lightning-fast, in-process vector database 64.6 15.4k C++
22 WeKnora C Listed Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-m 61.9 19.5k Go
23 memU C Listed Personal memory across agents 61.5 14.3k Python
24 Beads C Listed Beads - A memory upgrade for your coding agent 61.0 26.1k Go
25 PrivateGPT C Listed Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works wi 59.9 57.4k Python
26 MemOS C Listed Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 59.2 10.6k TypeScript
27 pgvector C Listed Open-source vector similarity search for Postgres 58.6 22.5k C
28 OpenViking C Listed Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. 55.7 28.1k Python
29 Letta C Listed Platform for stateful agents: AI with advanced memory that can learn and self-improve over time. 55.4 24.2k Python
30 LLM Wiki Agent C Listed A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extra 51.4 3.3k Python
31 LightMem C Listed [ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation 50.3 1.1k Python
32 Memvid D Listed Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents 49.3 16.2k Rust
33 LycheeMemory D Listed Lightweight Long-Term Memory for LLM Agents. 48.1 1.2k Python
34 ByteRover CLI D Listed ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher) 47.4 4.9k TypeScript
35 EverOS D Listed One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, t 46.7 11.9k Python
36 AnythingLLM D Listed Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience 43.6 64.5k JavaScript
37 Quivr D Needs review Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in exis 30.8 39.4k Python
38 inno-agent D Listed An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversati 23.5 646 TypeScript

Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology