Top RAG & Eval tools
Sustained, decay-weighted momentum leaders in retrieval and evaluation.
- 19· newawesome-evalsNewA curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.ai-agentsrag-eval+870.2
- 32· newmdfluxTurn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.rag-evaldesktop-app+1266.4
- 61· newHello-AgentsNew🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applicationsai-agentsrag-eval+1062.1
- 65· newbili-noteExtract Bilibili videos into learning-oriented Markdown notes with full subtitle and comment archivesrag-evalbilibili+461.3
- 69· newcodeseekRust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.ai-dev-toolsmcp-servers+1960.8
- 72· newPixelRAGThe end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/ai-agentsrag-eval+960.4
- 81· newWorkShadow如影随形 · 本地优先桌面工作日志：富文本记录、语义检索、工作台总结/问答；模型自配，数据留在本机。 Local-first desktop work journal—rich logs, semantic search, AI summary & Q&A. BYO models, data stays yours.rag-evalagpl-3+1960.1
- 100· newawesome-agentic-ai-zhA trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。ai-agentsai-dev-tools+2159.0
- 105· newtrove-ai中文互联网内容的个人 AI 稍后读 + 知识库 · Read-later + AI knowledge base for the Chinese internetrag-evalai+1058.6
- 116· newgarden-skillsConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.ai-agentsrag-eval+658.0
- 129· newawesome-architecture🧭 Architecture-first system design: 26 bilingual tutorials, 25 architecture templates, and 6 end-to-end cases covering distributed systems, AI-native systems, RAG, coding Agents, and production trade-offs.ai-agentsrag-eval+1957.5
- 130· newSearchCLIOpen CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systemsai-agentsai-dev-tools+1857.5
- 151· newongridAn ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.ai-agentsrag-eval+1956.5
- 160· newNubase🔥🔥🔥 Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.ai-agentsai-dev-tools+1656.1
- 171· newAgent_Memory_TechniquesAgent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.ai-agentsrag-eval+1955.8
- 189· newspecrag面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。mcp-serversrag-eval+1255.2
- 191· newcaura-memclawGoverned shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.ai-agentsmcp-servers+1555.1
- 193· newfuture-agiOpen-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.rag-evalai+555.1
- 194· newopen-genaiNewデジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。rag-evaldigital-agency+1555.1
- 204· newAfterglow使用社交软件聊天记录结合向量数据库让AI更好的扮演对方的角色，在不微调模型的情况下可以达到可观的效果。把曾经的美好，续成往后的陪伴。rag-evalafterglow+1054.7
- 214· newknowhereKnowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.ai-agentsai-dev-tools+1554.1
- 229· newsecond-brain-cloudflareOne memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.ai-dev-toolsmcp-servers+1853.5
- 234· newTencentDB-Agent-MemoryTencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.ai-agentsrag-eval+953.2
- 239· newmemory-osA 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.rag-evalai-memory+1153.0
- 246· newAIGuideAI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。ai-agentsai-dev-tools+1452.7
- 263· newClawBenchOpen-source benchmark for browser AI agents on daily tasks.ai-agentsrag-eval+1952.0
- 271· newBoxThe most advanced, fully offline client-side AI suite on Android today.mcp-serversrag-eval+3151.6
- 279· newmarginaliaA library-science-inspired personal knowledge management system with LLM agentsai-agentsrag-eval+2051.0
- 285· newumadevUmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.ai-agentsai-dev-tools+1650.8
- 291· newsembleFast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+readai-agentsmcp-servers+850.5
- 303· newOpenKBOpenKB: Open LLM Knowledge Baseai-agentsrag-eval+649.7
- 309· newscope-recall-hermesHermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.ai-agentsrag-eval+1649.2
- 310· newpmbLocal-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.ai-agentsai-dev-tools+2148.9
- 313· newhealthy-diet-ai-agentHealthy Diet AI Agent is a Bun + TypeScript backend for nutrition chat, food-image analysis, RAG document ingestion, and knowledge-grounded diet guidance.ai-agentsrag-eval+348.7
- 326· newArgus🌱 Argus 是一个基于 RAG 架构的开源知识库平台，后端采用 Java 21 + Spring Boot + MyBatis-Plus + PostgreSQL/pgvector，前端采用 Vue 3 + TypeScript + Element Plus，AI 层基于 Spring AI Alibaba（通义千问）+ ReactAgent 图引擎，以 MinIO + Elasticsearch 为存储与检索引擎。rag-evalrag+347.7
- 348· newKwipuAsk questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.ai-dev-toolsmcp-servers+2146.4
- 366· newFinSight-AIAI equity research agent with resilient workflows, Redis Lua single-flight, pgvector RAG, versioned reports, evidence tracing, and RAG evaluation.ai-agentsrag-eval+1044.7
- 373· newagent-systems-handbookA practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.ai-agentsai-dev-tools+2144.3
- 375· newcavemem🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like cavemanai-dev-toolsrag-eval+1444.3
- 387· newllmwikiOpen Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki ! ai-agentsmcp-servers+1143.4
- 389· newgraphmindLocal-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MCP tools.ai-agentsai-dev-tools+2043.3
- 396· newiai-personal-memory-engineMCP memory server for AI coding assistants. Works with Claude Code, Cursor, Codex, Gemini CLI, Cline, Continue, Cherry Studio, Zed, Hermes, OpenClaw, and any MCP client. Local, encrypted, verbatim recall. MIT.ai-dev-toolsmcp-servers+2142.7
- 404· newLLMInternSkillLLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Project Scout. 大模型实习简历与求职工具箱。ai-agentsrag-eval+2042.2
- 409· newvelaAI-powered IDE for novel writing — local LLM + RAG, privacy-first, BYOK. For web fiction authors and creative writers.rag-evalai-tool+942.0
- 411· newsuper-agent企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。ai-agentsmcp-servers+1142.0
- 421· newarkonArkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.mcp-serversrag-eval+1241.4
- 425· newstatewaveOpen-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.ai-agentsrag-eval+941.3
- 434· newBYO-LLM-WIKIBuild your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. Try Live Demo: https://byo-wiki-demo.onrender.comai-agentsmcp-servers+940.9
- 441· newagent-skills-evalA test runner for agentskills.io-style AI agent skillsai-agentsai-dev-tools+1240.5
- 458· newflowcraftProduction-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.ai-agentsrag-eval+1440.2
The weekly drop
Get the weekly rising list
The top risers across agents, MCP servers and dev tools, once a week in your inbox. No spam, unsubscribe anytime.