Memory & Knowledge

49 agents tracked · ranked by trust score · Updated 2026-10-13 08:09 UTC · the three strongest right now:

#1 in category OpenViking

88.3A39.8k ★

#2 in category ReMe

87.8A3.6k ★

#3 in category EverOS

87.4A13.4k ★

Grade mix49 agents

10 A20 B13 C6 D

#	Agent	Trust	Stars	Language
1	OpenViking A Listed Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.	88.3	39.8k	Python
2	ReMe A Listed ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.	87.8	3.6k	Python
3	EverOS A Listed One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.	87.4	13.4k	Python
4	Graphiti A Listed Build Real-Time Knowledge Graphs for AI Agents	87.1	31.7k	Python
5	Vespa A Listed The AI search platform	86.7	7.1k	Java
6	LanceDB A Listed Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.	86.7	11.7k	Rust
7	Mem0 A Listed The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.	86.2	67.1k	Python
8	Cognee A Listed Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free	85.8	32.1k	Python
9	Hindsight A Listed Hindsight: Agent Memory That Learns	85.0	49.0k	Python
10	LightRAG A Listed [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation	84.8	40.1k	Python
11	Qdrant B Listed Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/	76.1	35.1k	Rust
12	agentmemory B Listed #1 Persistent memory for AI coding agents based on real-world benchmarks	75.9	29.4k	TypeScript
13	FAISS B Listed A library for efficient similarity search and clustering of dense vectors.	75.0	41.1k	C++
14	RAGFlow B Listed RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs	74.7	92.1k	Go
15	Honcho B Listed Memory library for building stateful agents	73.6	7.6k	Python
16	Weaviate B Listed Weaviate 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.	73.1	16.9k	Go
17	Letta B Listed Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.	73.1	25.1k	—
18	GraphRAG B Listed A modular graph-based Retrieval-Augmented Generation (RAG) system	73.0	36.3k	Python
19	Tidb B Listed TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.	72.3	40.6k	Go
20	Milvus B Listed Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search	72.2	46.4k	Go
21	txtai B Listed 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows	71.3	13.0k	Python
22	zvec-grep B Listed Local-first search across your workspace, built for humans and AI agents.	69.3	4.1k	Rust
23	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.	68.5	1.4k	TypeScript
24	Code-Graph-RAG B Listed The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs	68.0	5.2k	Python
25	Pond B Listed Lossless storage and search for AI agent sessions, across every agentic client.	67.7	81	Rust
26	WeKnora B Listed Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.	67.4	33.6k	Go
27	CodeGraphContext B Listed An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.	67.2	4.3k	Python
28	Quivr B Listed An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.	66.5	39.6k	Go
29	Utopia B Listed World's first open-source enterprise world model.	66.3	8.3k	Rust
30	IWE B Listed Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents	65.2	1.8k	Rust
31	Chroma C Listed Search infrastructure for AI	64.9	29.5k	Rust
32	Beads C Listed Beads - A memory upgrade for your coding agent	64.0	27.8k	Go
33	Zvec C Listed A lightweight, lightning-fast, in-process vector database	63.3	16.1k	C++
34	PipesHub C Listed The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.	62.1	3.8k	Python
35	AnythingLLM C Listed Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience	61.6	67.0k	JavaScript
36	Khoj C Listed Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.	61.1	37.7k	Python
37	PrivateGPT C Listed Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.	59.1	57.6k	Python
38	memU C Listed Personal memory across agents	56.7	14.5k	Python
39	MemOS C Listed Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.	55.4	11.8k	TypeScript
40	Memmy C Listed 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.	54.5	2.1k	TypeScript
41	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 stdio against a local SQLite store. Drop-in for the MCP reference memory server. Every memory keeps its source, who may read it, and the evidence that contradicts it.	54.5	16	TypeScript
42	pgvector C Listed Open-source vector similarity search for Postgres	52.7	23.3k	C
43	inno-agent C Listed An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.	52.2	1.3k	TypeScript
44	LLM Wiki Agent D Listed A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.	48.4	3.6k	Python
45	LightMem D Listed [ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation	46.1	1.2k	Python
46	Memvid D Listed Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.	42.9	16.6k	Rust
47	ByteRover CLI D Needs review ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)	41.3	5.0k	TypeScript
48	LycheeMemory D Listed Lightweight Long-Term Memory for LLM Agents.	41.3	1.1k	Python
49	Tigerless Agent Memory D Listed Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.	25.0	3.4k	Python

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

About Memory & Knowledge

HVTracker independently evaluates 49 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 OpenViking with a trust score of 88.3/100 (Grade A). Other leading projects include ReMe and EverOS.

Agents

Avg Trust

1.1M

Total Stars

Grade A

Warnings