tierlist.tech
中EN

#检索增强

200

2026-10-06 elstongun/leviathan S **Deep memory for agents over large datasets.** Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or anything a database CLI can export) into a ranked full-text index.
2026-08-25 Tencent/WeMM-Embedding A WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.
2026-08-24 liangdabiao/deepseek-v4-flash-vision-video-rag A DeepSeek V4-Flash Vision Video RAG 让 AI 真正"看懂" 一段视频，然后你对它提问：它告诉你答案、答案发生在 第几分几秒，并切出那一段的可播放片段和关键帧给你核对。 基于 DeepSeek 视觉大模型 deepseek-v4-flash-vision-exp 的视频理解与问答 （video RAG）agent skill。先按时间轴抽帧阅读、建立索引（一次性），再对问题做 本地粗筛 → 视觉精排 → 深读回答；回答带 [MM:SS] 时间戳引用，自动生成 自包含 HTML 预览页（内嵌可播放片段 + 关键帧 + 答案），双击浏览器即看。
2026-09-23 Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why A Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lending, fraud, clinical triage), then bolt on "guardrails" after the fact. It runs the two in series instead: 1. A pure-Python Rete engine evaluates YAML rules against your facts. The verdict comes only from here. Same facts, same verdict, every time, with salience-based conflict resolution. 2. RAG retrieves passages from your own policy documents, and an LLM writes a plain-English explanation of the decision that was already made, citing those passages. It can't change the verdict. A few things that went further than I expected: - Rules are a graph, not flat lists: nested all/any/not, and rules can assert facts that other rules consume (forward chaining). The decision trace shows the causal chain. - Audit mode records every rule evaluated, including the ones that didn't fire, condition by condition, with a snapshot of the rule set for replay. - Rules can steer retrieval (a fired rule narrows which documents get searched), and retrieved text can be turned into facts for the engine. - Non-technical authors can build rules in a visual editor, or paste a policy document and get LLM-drafted rules with citations. Drafts are never saved without review. YAML is still there for engineers. The landing page has a live demo with no signup (8 demo domains: loan, fraud, clinical, insurance, legal, ops, e-commerce, blockchain). There's also an MCP server, so Claude and other agents can call /decide as a tool: `uvx ai-rete-rag-mcp`. To be upfront: it's a hosted product with a free tier. The MCP client is open source (MIT, github.com/zaharajabeen13-create/ai-rete-rag-mcp); the engine and platform are not open source right now. I'd especially like to hear from anyone who has had to explain an automated decision to a regulator or an auditor: what did they actually ask for?
2026-08-28 brooxiacaigonv/AIrecall A Drop-in long-term memory layer for AI agents - episodic + semantic memory, hybrid retrieval, and auto-summarization. Python SDK + Go memory server.
2026-09-09 arnsri33/embedflow A Zero downtime embedding upgrades
2026-10-09 beianchuqing111/agentic-kb A 法规/规程知识库智能体:混合检索(bge-m3 稠密+稀疏 → 服务端 RRF → 交叉编码器重排)+ GraphRAG + 带三道闸与审计的 ReAct 智能体。含检索质量评测设施、FastAPI 接口与 React 界面。
2026-10-21 MemTensor/MemT-1.0 B Official repository for MemT-1.0
2026-09-08 misraj-ai/qalam A Arabic PDF text extraction that doesn't quietly corrupt your corpus: logical word order, base letters not presentation forms, ligatures intact and a per-page verdict telling you which pages genuinely need OCR. Rust + Python, no OCR.
2026-09-19 LingxiangXu/traceclause B Local-first document requirements and evidence review workbench with traceable citations and human review.
2026-08-23 Consensus-NLP/consensus-mcp A Official MCP server for Consensus. Search 220M+ peer-reviewed research papers from Claude, ChatGPT, Cursor, and any MCP client.
2026-10-24 Show HN: We had AI write a wiki from 45k Enron emails, every fact cited B
2026-10-17 Tencent-Hunyuan/Hy-Memory A
2026-10-05 raphaelmansuy/edgextract A Turn markdown into a knowledge graph with an ontology you write and a cutoff you own. Closed yes/no decisions, not free-form JSON.
2026-09-24 amitshekhariitbhu/ai-engineering-course B AI Engineering Course - A free and complete AI Engineering Course to learn AI Engineering step by step - from Machine Learning, Neural Networks, and Transformers to LLMs, Fine-Tuning, RAG, AI Agents, LLM Inference, Evaluation, AI Safety, and AI System Design.
2026-09-10 bluesky585/nibble B A Go library for splitting long text into retrieval-sized chunks for RAG.
2026-10-28 pinecone-io/pg_pinecone B Pinecone for Postgres: one pgvector column, three engines
2026-09-06 r0b0tlab/hermes-zvec-memory B Local-first Hermes memory provider on zvec-grep (hybrid BM25+vector RRF over Markdown vault)
2026-08-31 drephantom/memory-garden B Personal cognitive-retrospect Agent over Obsidian notes: stance snapshots, hybrid retrieval, read-only MCP tools. 48 tests, 3 reproducible evals.
2026-08-30 NousResearch/hermes-plugin-backsearch B BackSearch plugin for Hermes Agent — point-in-time web search & fetch over a frozen news archive (General Reasoning)
2026-08-27 Encephos/markdown-link-resolver B A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.
2026-09-23 cairodavila/tisco B Question video transcripts, inspect the evidence, and organize clips from the terminal.
2026-09-10 dmoshehun-prog/learn-from-materials B Turn PDFs, books and papers into interactive learning webpages｜将复杂材料转化为可追溯、可测验、可做笔记的学习网页
2026-09-10 Show HN: EmbedFlow –> Upgrade embedding models without re-embedding your corpus B I was playing around with embedding models and I realized the moving between embedding models on a large corpus can cause a huge backfill, as all of the previous documents would have to be re embedded. embedflow tries to forgo that; it takes candidate documents from the previous index, and reranks them in realtime with the new model. It supports faiss, qdrant, and pgvector people who have migrated large production vector indexes, would this be helpful for you?
2026-09-03 TheBlewish/Academic-AI-Literature-Reviewer-Ollama B Automated literature reviews using local LLMs via Ollama. Searches academic databases, acquires full-text papers, and writes APA 7th reviews where the model is structurally prevented from fabricating quotes — every quote is verified verbatim and is formated in APA7th.
2026-09-02 neuronto/agentic-resource-discovery B Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic retrieval, and ARD-Bench.
2026-08-31 Show HN: Hillock: Local neuro-symbolic memory engine in <1.2GB VRAM C
2026-09-30 Show HN: Sezwhere – Ask any document "where does it say that?" (built on Jev) C
2026-09-18 zeronezer/bidcraft B 标书匠 BidCraft · 对话式标书编制系统：AI 智能编制技术标，支持招标文件解析、标段选择、标书编写、知识库提炼与学习对话式改稿。LLM-Wiki 路线，基于LangGraph实现。Open-source AI agent for construction tender & bid documents.
2026-10-15 Lucent-Snow/agent-knowledge-mcp B Portable Markdown memory for agents: six MCP tools, local and remote access, Chinese lexical search, and multi-device sync.
2026-10-09 p10node/docflare-ai B Open-source AI chatbot & site search for your docs. One <script> tag, streaming answers with sources. 100% Cloudflare-native (Workers AI + Vectorize + D1), runs free on the free tier.
2026-10-10 appletea233/OneSearch-VL B A unified multimodal deep research agent for images and videos, with open models, datasets, and training and evaluation code.
2026-10-02 nemofq/open-finance-agent B An open-source financial research harness that enforces analyst standards in the agent loop itself: trusted sources first, no mental math with every figure computed in a Python sandbox, and every number traced to its source through an evidence ledger.
2026-10-06 metacoglabs/hypergraph B A persistent native vector-hypergraph database for higher-order interactions
2026-09-12 linqiu919/better-context-engine B ACE-compatible code context retrieval engine: real-time codebase indexing and low-latency context for AI coding assistants
2026-11-04 weir36/deep-research-langgraph B 基于 LangGraph 的多 Agent 深度研究助手：可中断恢复、按依赖并行、引用治理与评测，成本降低 45%
2026-10-26 Jason-Wu-7744/Financial-Report-Analyzer B AI-assisted financial report analysis for A-share and Hong Kong-listed companies: filing retrieval, PDF parsing, evidence-linked summaries, financial checks, and bilingual exports.
2026-09-18 nirbhay41120003/EchoMind B Local-first voice memory assistant — capture speech, transcribe live, and ask a private RAG chatbot grounded in what you've actually said. No cloud required.
2026-08-28 xiaotianfotos/indexed B A multimodal video memory for humans and AI agents
2026-08-26 jsdhwfmax/EvalForge B Open-source quality and security evaluation platform for RAG applications and AI assistants.
2026-10-20 ry0narushima/bettersearch B Deep research for any AI agent on DeepSeek's new Search API. Subagents, fact-checking, and a clean HTML report.
2026-09-02 razr001/audit-mind B AuditMind 是一个面向法规合规与审计场景的 AI Agent 系统，支持法规知识管理、可追溯规则抽取、文档合规审计、审计任务管理和基于原文证据的智能问答
2026-08-28 Autobricks-AI/Arlo-AI-Desktop B Self-hosted AI customer service. Your documents, your database, your data - answered with citations across every channel.
2026-08-23 dengzehan666-png/Review-RAG B 面向 Java 面试和 LeetCode Hot100 学习场景，搭建集多格式文档入库、语义检索、知识问答、随机刷题及错题复习于一体的 RAG 系统。系统优先依据个人知识库生成答案，证据不足时调用通用大模型补充，并通过人工确认机制将优质回答沉淀回知识库。
2026-10-23 khanhtq29vn/contextcraft B AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs
2026-09-08 superwesleyhys-ux/factcircuit B FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
2026-08-25 liangdabiao/deepseek-v4-flash-vision-rag B DeepSeek V4-Flash Vision RAG 让 AI 真正"看懂" 一份 PDF，然后你对它提问：它告诉你答案、答案在第几页， 并把那一页的原图展示出来给你核对。 基于 DeepSeek 视觉大模型 deepseek-v4-flash-vision-exp 的 PDF 深度问答与检索 （vision RAG）agent skill。支持文字版 PDF，也支持扫描版；能看懂 图表、表格、代码块、公式，而不只是认字。
2026-09-27 Jiarui-0410/multimodal-product-discovery C Full-stack multimodal product retrieval and personalized reranking with CLIP, FAISS, Spring Boot, FastAPI, and PostgreSQL.
2026-09-19 superagents-lab/jev-search C Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
2026-09-04 wanwan-666/DocChat-RAG C RAG 知识库服务，实现文档导入、自适应递归切片、Redis 向量检索，支持多轮长对话与流式问答。
2026-11-03 weir36/novel-config-copilot C 网文平台资源配置决策助手：GraphRAG 两阶段检索 + ReAct Agent + 规则引擎兜底，方案合法率 60%→100%
2026-08-24 Sherlockwz/AMA C Official implementation of AMA: Adaptive Memory via Multi-Agent Collaboration (Findings of ACL 2026)
2026-10-09 Show HN: DocFlare AI – Open-source docs chatbot on Cloudflare's free tier C
2026-09-23 rgem227/knoweldge-base C Personal or team knowledge base, supports MCP API calls.
2026-10-14 Ayesha-Ansa/research-evidence-analyst C An evidence-grounded RAG research assistant that combines semantic search, BM25 keyword retrieval, Reciprocal Rank Fusion, and cross-encoder reranking to answer questions from research papers with PDF page citations and evidence sufficiency checks.
2026-10-07 croma-labs/ventanilla C Ventanilla: answers about the Colombian State from official sources, powered by Croma
2026-10-02 renfei421/ResearchPilot C Evidence-grounded academic research agent with claim verification, prior-work analysis, and persistent research workspaces.
2026-09-25 TencentCloud/octop-memory C Help your agent remember what matters. Keep preferences, carry context across sessions, and bring your memory to the next agent.
2026-09-18 YunahJang/AdaptiveRAG-Robustness C Official repository for "How You Ask Matters! Adaptive RAG Robustness to Query Variations".
2026-10-16 gbh1234/Adaptive-rag C 基于 FastAPI、LangGraph 和 React 的 Adaptive-RAG 电商客服项目
2026-09-16 ruc-datalab/EvoOntology C EvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ EvoOntology插件为Claude Code/Codex 建立&进化本体层
2026-10-26 anonnerdfrenzy/survival-llm C A free AI assistant and survival library that runs on your own computer, with no internet needed. Shows the source of every answer.
2026-10-02 nuanu-ai/Corpus C Company knowledge. With receipts. A self-hosted AI workspace for documents, connected business data, and answers grounded in evidence.
2026-10-19 Dong-Fang-Bu-Bai/btr-dualrag D Source code for BTR-dualRAG: Bioinformatics Tool Recommendation With Dual Retrieval-Augmented Generation
2026-10-15 2430816465/campus-knowledge-agent C 校园知识服务 Agent 智能体平台：基于 FastAPI、Qwen3 与 RAG，贯通公开资料解析、时间范围检索、证据溯源及人工审核。
2026-08-27 atukunare/wiki-knowledge-agent C Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. Ad-detection, translate+summarize, local-first alerts, RAG-ready. Platform-independent AI skill (Hermes/Claude/Codex/Cursor), zero dependencies.
2026-09-26 kieranklaassen/truffler C Sniff out the right record: Jev-powered search for Rails with index-time labels, query understanding, and streamed reranking on top of your own keyword and embedding search
2026-09-21 samdotmak/jev-recall C Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev
2026-10-16 jaikydota/BullFlow C 推量牛 BullFlow — 开源企业级 RAG 解决方案：从企业知识库、营销内容自动化生产到全域内容分发 | Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. 知识库全链路本地开源模型，无需付费模型；AI Agent 创作图文 / 图片 / 视频，一键发布抖音、小红书、公众号、LinkedIn、YouTube 等 17 个平台。Commercial-grade, multi-tenant, billing & admin built in. MIT
2026-09-11 AZHi-xinxin/StillerBrain C 面向 AI 的长期记忆基础设施，支持选择性召回、可追溯记录与自我修订。源码开发预览，采用 PolyForm Noncommercial 非商业许可。
2026-09-02 SabreKeyZ/agent-xuetang C Agent学堂 · 从零到就业的中文学徒路线（客服工单台 + 理赔初审台，没有引用就先不答）
2026-08-31 git-syl/hermes-agent-demo C A multi-model Agent runtime built on Spring Boot 4 / Spring AI 2.0: model routing (Anthropic / DeepSeek / OpenAI / custom), thinking toggle, Task subagents, hot-pluggable Skills, Docker sandbox + Code Interpreter, MCP tools, dify/n8n integration, RAG with pgvector, Human-in-the-Loop approvals — all streamed as structured SSE events.
2026-09-30 Alpha-Park/genpark-locality-sensitive-hashing-lsh-cosine-index-skill C Random hyperplane Locality-Sensitive Hashing (LSH) for sub-linear cosine similarity candidate generation
2026-09-27 Ajakfial/Wilfred D A Open-Source Search Feature.
2026-09-03 dreamers-laboratory/rag-scaffold C A reusable pattern for turning PDFs into a searchable, evidence-verified record set.
2026-09-02 knowflow-ai/analytics C 基于语义建模的智能问数产品
2026-09-17 raitulh/RecallOs-Ai C Give your AI agents continuous, persistent long-term memory with hybrid vector-graph retrieval — running 100% privately on consumer hardware with sub-12ms latency.
2026-08-28 liangdabiao/glm-5.3-flash-vision-rag C glm-5.3-flash-vision RAG：三个 GLM 视觉技能总览 > 同一套"让 AI 看懂资料"的技术，嫁接到智谱 **GLM-5.3-Flash** 视觉大模型上， > 做成了三件趁手的工具：**看懂 PDF**、**看懂视频**、**把带货视频变成提示词
2026-08-27 YeamimHossainSajid/CodeMonk C CodeMonk 🥋 —>An open-source AI powered code intelligence platform that helps developers understand, explore, and navigate complex codebases using modern Spring Boot, Spring AI, RAG, knowledge graphs, and intelligent code analysis
2026-08-26 YoungBao-WHU-FDU/ai-intelligence-agent C AI 科技情报 Agent：聚合论文、GitHub、企业官网与网络信号，基于 LangChain 实现结构化理解、事件核验、个性化推荐与主动提醒。
2026-09-05 alipyth/AdaptiveMetric-Rag C AdaptiveMetric RAG is a self-hosted, multilingual knowledge assistant that changes its retrieval strategy for every question
2026-09-02 dzenplatform/embedder C Dzen embedder service with OpenAI/Cloudflare compatible API
2026-10-13 lattifai/awesome-EmbeddingGemma C EmbeddingGemma2 resources: local search apps, decision models, inference frameworks, tutorials, and datasets. English / 简体中文.
2026-10-06 kkjiangk/agent-py C Personal AIOps engineering project with durable workflows, scoped hybrid retrieval, reliable event delivery, and verified API/browser contracts.
2026-09-20 chopratejas/invalidate C The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.
2026-09-24 bodepudimuneendra-netizen/laya-jev-GraphRAG C Agentic GraphRAG engine using swappable System One decision models (local Laya / cloud Jev). Features a complete 4-phase pipeline (Ingestion, Pre-Retrieval, Traversal, Post-Retrieval) and evaluation across Neo4j, Memgraph, Apache AGE, and Kùzu driven by a custom A* traversal algorithm.
2026-09-13 abhi021410-ship-it/retain-ai D An elite, production-grade self-learning AI memory agent featuring a persistent RAG pipeline built with Python, FastAPI, ChromaDB, Gemini, and a cinematic Next.js neural interface.
2026-09-30 alphaparkinc/genpark-adaptive-retrieval-router-skill D Adaptive RAG retrieval routing classifier directing queries across direct LLM, single-hop, and multi-hop RAG
2026-09-15 Harvey-cream/accountings D 面向个人用户的一站式智能财务管理平台，覆盖日常记账、账单统计、预算、资产、发票及财务数据管理，并通过自然语言交互、RAG 与 Agent 工作流提供智能记账、财务问答和个性化分析，同时支持社区互动与用户成长体系。
2026-09-13 aiwindyjm/morpho-research-os D Turn research questions into source-grounded, living knowledge bases.
2026-09-11 dsm-1128/knowforge-metrics-rag D
2026-09-10 vigorlee/eidra-agent D Persona agents with explicit memory, retrieval, adversarial smoke tests and a practical post-training roadmap.
2026-08-28 ob-labs/powercontext-go D A powerful context engine: Let your AI Agent smarter.
2026-11-09 ngophatneknha/ai-engineering-hub D In-depth tutorials on LLMs, RAGs and real-world AI agent applications (Personal learning hub)
2026-10-23 Sanpan53/zhixin-campus-showcase D 知新校园 · 校园 RAG 知识库面试展示版：架构、技术说明与 Docker Compose 部署配置（不含业务源码）
2026-10-11 OkinoYu/PaperArbor D An AI-Powered Visual Research Knowledge Base — Where Papers Grow into Knowledge.
2026-10-01 surya-3699/REcall D REcall is a memory-aware AI product comparison agent that combines live web research with Hindsight persistent memory to help business teams make better purchasing decisions.
2026-09-25 initPM/ai-banking-support-copilot D A conversational AI banking copilot designed to deflect level-1 support tickets by classifying customer intents and simulating knowledge base retrieval.
2026-09-24 agencyenterprise/jev-recipes D 80+ composable TypeScript recipes powered by Jev for AI agents, retrieval, answer verification, and conversation workflows.
2026-09-21 erendikmenn/jev-rag-benchmark D Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG
2026-10-07 BaruqueRodrigues/rag_especialistas D Projeto de pesquisa com RAG e GraphRAG para artigos acadêmicos.
2026-08-26 alphaparkinc/genpark-multi-step-deliberative-search-graph-verifier-skill D Multi-step deliberative reasoning search graph verifier (Perplexity Pro style)
2026-10-04 tutuhong2001/LLM-Learning-Notes D Chinese AI learning notes and a minimal RAG demo with Sentence-Transformers, BM25, OpenAI-compatible APIs, and retrieval evaluation.
2026-09-27 xie-ying/Industry-DeepResearch-Assistant D 融合大模型问答、联网深度检索、本地知识库与行业资讯聚合的智能行业信息分析助手
2026-09-03 Laleeth/The-AI-Engineer-s-Playbook D Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design, and AI infrastructure.
2026-09-22 wjl8636/Financial-Report-RAG D
2026-10-04 ytt070666/OmniForge-AI D OmniForge AI：大模型、RAG、Agent 与多语言服务学习合集
2026-09-30 redwavetop/knowledge-agent D
2026-10-10 final-bench/ongrid D ONGRID — Ontology-Native Graph · Retrieval · Inference · Decision. 3D knowledge graph + zero-token ZTC answer verification. by VIDRAFT.
2026-10-04 pk14742952-AD/dsh-host-rsi D DSH host RSI for local LLMs (currently Qwen3.8 27B): per-use continual self-improvement, counter-reason self-check, critic escalation, and memory retrieval.
2026-08-28 lxl0825/RagMempool D RagMempool implements distributed memory pooling for optimized resource allocation and congestion management in decentralized networks.
2026-11-02 Kulolooo/Kumore_Agentic-RAG D
2026-09-22 memonative/memory-engine D
2026-11-08 Dongbumlee/ontosmith 未评级 A decision-model-based ontology & knowledge-graph builder — builds governed knowledge graphs from your documents, every fact gated and traceable to its evidence.
2026-11-08 Luciferutts/partspilot 未评级 面向中小汽配制造企业的 AI 业务工作台：真实产品目录、潜客发现与证据审核、RAG 资料问答、多轮询盘、人工交接和报价跟进，附可复现的分层评测。
2026-11-08 fatsearch/fatsearch 未评级 Search and read the web for AI agents at 99% fewer tokens. Free CLI + MCP.
2026-11-08 pnyn96/mindact-agent 未评级 MindAct: Community-Driven AI Agent for Claude, Obsidian, and RAG Knowledge Graphs
2026-11-07 Zleap-AI/SAG-Wiki 未评级 A lightweight knowledge base for people and agents
2026-11-07 didilili/mianstack 未评级 🚀 面栈 MianStack｜程序员面试题库天花板！Java、Python、数据库、算法、大模型、AI Agent、RAG 一栈备齐。真实面经关联高频考点，按公司、岗位定向备考；图文题解、精华专题、项目源码拆解，全系标配。面试官出题，面栈出招！免费开源，持续更新。
2026-11-07 liangjianshu/multimodal-image-retrieval 未评级 多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。
2026-11-07 zaxiu88888/issue-rag 未评级 RAG over GitHub issues, with a hand-reviewed eval set and an audit of the judge itself. Reports the interval, not just the best number.
2026-11-06 ConardLi/garden-skills 未评级 ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.
2026-11-05 NVIDIA/auto-ontology 未评级 Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for LLM and agent workflows.
2026-11-03 Elio896/dsh-familiar-memory 未评级 给 DeepSeek Harness 的本地记忆层：养大肥鱼的可以下载来玩，经过测试下载之后比单纯用RAG和外部记忆库更有人情味更自然了。
2026-11-03 jjs202210-jpg/dashi-wo-wu-le 未评级 大师，我悟了｜多轮启发式教学智能体
2026-11-03 peterpoal134/memory-brain 未评级 给 AstrBot 的可落地 AI 记忆与生活层：五类记忆、混合检索、遗忘治理、情绪边界、自主生活循环。不覆盖人格。
2026-11-02 gh9ko8y/graphmemory 未评级 Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
2026-11-02 sahenjp/RustXNG 未评级 Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later)
2026-11-02 wp1461772181-glitch/FinBot 未评级
2026-11-02 patchy631/ai-engineering-hub 未评级 In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
2026-11-01 chatvia/chatvia 未评级 Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.
2026-11-01 lalabase/lalabase 未评级 Self-hosted project management for devs and their clients: tickets, time tracking, docs and meetings, with an AI assistant that cites its sources. AGPL-3.0.
2026-10-31 MUSE-AI-Lab/SurveyGraph 未评级 SurveyGraph
2026-10-30 yjid/kensaku 未评级 Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
2026-10-29 undrgrnd-labs/hunch 未评级 a systemone proxy using embeddings that distills a teacher model
2026-10-27 YOLOW92/pagesift 未评级 High-performance, memory-efficient Rust web crawler & content extraction engine for AI agents and RAG. Adaptive crawling, clean Markdown, structured data, PDF/RSS parsing, browser rendering, Firecrawl-compatible APIs, and Python/Node.js SDKs.
2026-10-24 JackWang666666/my-rag 未评级 我的rag系统，可以用于导入知识库进行知识问答，可集成第三方mcp，也做了权限隔离等
2026-10-24 Show HN: Instant – Local AI search with a 95% hit rate (uses Perplexity models) 未评级 Hi HN! Instant Search is the first accurate local AI file search that uses the latest embedding models from Perplexity to find the exact file (and page) with the content you’re looking for with a 95% hit rate. Search never worked properly, especially with local files. Now, you can find the right image, document, or Obsidian file in seconds. Looking for your driver’s license? Just type “driver’s license”. Looking for a particular note? Just explain the context. Why not Finder&#x2F;Spotlight? Spotlight is just a keyword search. It doesn’t understand file content. Instant finds the exact file you’re describing in under a second. Why not RAG? Traditional RAG models give you a single embedding vector per entire body of text. That means either you have a vector that’s not detailed enough to give you an accurate semantic representation, or it’s too precise and doesn’t contain enough surrounding context. Instant circumvents these problems by relying on a bidirectional late-interaction embedding model that works flawlessly. How much space does indexing need? An average library of content needs less than 1GB of disk space. Check it out, share with friends, and let me know your feedback! It&#x27;s free.
2026-10-22 gouchengyujibei-alt/E-commerce-After-sales-Agent-LangGraph-HITL-Writes-Eval-Loop 未评级
2026-10-21 anning945/PARC 未评级
2026-10-21 dameng2026/xianyu-pilot-pro 未评级
2026-10-21 VectifyAI/PageIndex 未评级 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
2026-10-21 Show HN: Skillsync – Coding agent memory but it's just search 未评级 I built a claude mod that searches every session (across harnesses) on each prompt. On every prompt, it runs a series of decision models to pick the right sessions + messages and adds anything relevant to the context. Requires no indexing or setup and works out of the box Demo: https:&#x2F;&#x2F;youtu.be&#x2F;o5vEf8tgus4
2026-10-20 JEen-wang/Adaptive-rag 未评级 电商客服adaptive-rag
2026-10-20 salikhussain71-code/PAKGOV-RAG-project 未评级 Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation.
2026-10-20 headroomlabs-ai/headroom 未评级 Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
2026-10-20 Show HN: Algebrix Identity-IAM for developers tired of stitching things together 未评级
2026-10-17 scozn/FinServe-Agent 未评级
2026-10-17 Show HN: Tennis, a local/offline context store 未评级 Hi everyone! I&#x27;m Joe, and I built Tennis: a CLI that indexes and searches your context offline. You can index any files, your Chat &amp; Claude sessions, Codex history, etc. All local and offline. I&#x27;ve always hated having chats siloed in Claude and not having an easy way to connect that context in other apps. Anything that exists today has a subscription and is stored on their servers, and really wanted something fast, local, and offline. How Tennis works: * SQLite&#x2F;FTS5 (keyword) + vec0 (vector) * model2vec &#x2F; potion-retrieval-32M (512-dim, 123MB). This is a flat vector table, and what helps make this work well local&#x2F;offline. * RRF (k=60) fuses BM25 keyword rank + cosine semantic rank into one score Tennis also creates markdown files called &#x27;cards&#x27; at indexing time. This gives you an easy, summarized, human readable format to see what Tennis has. You can edit these files (but won&#x27;t change the embeddings in SQLite). You can use Tennis via API and MCP. It&#x27;s incredibly fast, and the MCP works great as a connector to different applications (ChatGPT, Claude, Opencode, etc). You can install and use it today: https:&#x2F;&#x2F;tennis.jlachance1.workers.dev&#x2F; Thanks for checking this out! I would love any feedback. Thank you
2026-10-16 FengZhenfei/carrel 未评级 Ontology-Augmented Generation for AI agents.
2026-10-16 1173591564/Dynamics-memory 未评级 LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamics + tension adjudication + causal-replay evals.
2026-10-16 1940762465/MultiModeGraphRag 未评级
2026-10-16 ARahim3/DigUp 未评级 Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
2026-10-16 AllSpark-Research/Iris 未评级 Climbing to the Search Frontier.
2026-10-16 Anton2025-11-06/DRAGON-AI 未评级 🐉 DRAGON-AI — AI Middle Platform
2026-10-16 ArihantDeva/heimdall 未评级 A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
2026-10-16 BenyRonald77/uajy-academic-rag-chatbot 未评级 Production-grade RAG chatbot for Universitas Atma Jaya Yogyakarta academic handbook with Streamlit, FAISS vector search, and Google Gemini 2.5 Flash.
2026-10-16 Fazmin/AILearningGuide 未评级 Interactive desktop app with 51 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.
2026-10-16 HHU-JialeChen/CogniJet-Lume 未评级
2026-10-16 IvenKooLab/loci 未评级 A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.
2026-10-16 JouJouoo/agent-campus 未评级 A multi-agent campus social simulation built with LangGraph, featuring memory, RAG, personality evolution, and durable execution.
2026-10-16 Karry-coder-dev/RAVEL 未评级
2026-10-16 VanGong1999/FDE 未评级 更新中｜收集FDE AI前线部署工程师相关全部内容｜从0到1｜ AI Agent，Workflows，工作流 ,RAG,知识库，推理优化与部署，vllm与sglang，workflow,graph/loop/conext/prompt工程
2026-10-16 Vaquill-AI/open-india-law 未评级 Open, structured Indian primary law: 32.5M judgment chunks from the Supreme Court and all 25 High Courts, 1.1M legislation provisions, and the scrapers that build it. CC BY 4.0.
2026-10-16 VectifyAI/jev-doc-search 未评级 Long-document search with Jev and PageIndex
2026-10-16 agent-for-dummys/Agent-For-Dummies 未评级 Agent/RAG/AI应用：Agent学习笔记 图文结合零基础入门学习笔记
2026-10-16 chenkanglin198904/Personal_External_Brain 未评级 Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge graph — running entirely on your own machine.
2026-10-16 context-dot-dev/sgrep 未评级
2026-10-16 crow-hq/llm-wiki-v2 未评级 Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens.
2026-10-16 erictrainnlpinxihu/Grader-agent 未评级 Grader 的 agent 采用五阶段主循环：perceive→plan→act→observe→respond，由 harness 驱动。模型只决定意图与置信度，路由、工具集、风险等级由代码钉死。act 分只读 ReAct、RAG、人工提案、批量初批。四个写动作不在工具表，只能产提案。批改输出结构化 GradingDraft，逐条绑定 rubric 与段落 hash，保证可重放。
2026-10-16 extend-hq/jevbox 未评级
2026-10-16 het2333/OrgMesh 未评级 企业私有 AI 知识工作台：中文搜索、飞书接入、Agent 与演示文稿
2026-10-16 himovo/movo 未评级 Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
2026-10-16 hydra-db/open-glean 未评级 An open-source AI platform for knowledge work. Connect your apps, find answers, and get work done.
2026-10-16 iamzulx/crypto-rag 未评级 Asisten crypto berbahasa Indonesia: RAG pengetahuan 267 topik + data pasar realtime (6 bursa, WebSocket, derivatif, on-chain, TVL, DeFi) + tool-calling agent + LLM synthesis
2026-10-16 jiarui-liu/IdeaScientist 未评级
2026-10-16 junjiezhang207/mediLoop-agent 未评级
2026-10-16 luxir-search/luxir 未评级 search at the speed of light
2026-10-16 lxcshine/zilan 未评级 知澜 — 知识汇聚成澜：RAG、Agent 推理与自动Wiki一体化的智能知识中枢
2026-10-16 modelscope/ms-cookbook 未评级 魔搭紫皮书｜ModelScope Cookbook：面向开发者的开源模型应用实战指南，覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC，从跑通第一个模型到构建实际应用。
2026-10-16 nikonotnicotine/Uranus_Imessage 未评级
2026-10-16 oce-ai/oce 未评级 OpenContextEngine is a self-hosted, ACE-compatible code retrieval service. It indexes source files with cAST-aware chunking, stores metadata in PostgreSQL or SQLite, performs dense vector retrieval in Milvus 3.0, and reranks results with an LLM before coverage-aware selection.
2026-10-16 qwdwqfwq/topconf-paper-figure-gallery 未评级 3,516 curated Figure 1 / teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI (2023-2026), with tier badges and FigureForge retrieval-augmented figure drafting
2026-10-16 solis-team/CrossCoder 未评级 [EMNLP 2026] Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation
2026-10-16 stepll2026/OntiCards 未评级 OntiCards 是面向企业的 AI 数据中枢（AI Data Hub），围绕业务数据库提供一站式能力：数据源连接、元数据理解、自然语言查询、跨源融合、数据质检、查询审计与数据资产管理等
2026-10-16 tigerless-labs/agent-memory 未评级 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.
2026-10-16 tntexploding/StruInfo 未评级 Self-hosted, traceable document-to-knowledge workspace with deterministic workflows, optional AI, search, RAG, and an editable knowledge graph.
2026-10-16 turkiyeyapayzekaakademisi/llm-rag-memory-ai-agents 未评级
2026-10-16 uehaj/sys1grep 未评级 grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる
2026-10-16 wp1461772181-glitch/market-evidence-agent 未评级
2026-10-16 yj-liuzepeng/dsh-project-brain 未评级 Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
2026-10-16 youngyangyang04/llm-master 未评级 大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。
2026-10-16 yvetteYSY/creator-agent 未评级 Build AI agents grounded in a creator's documents, audio, and video.
2026-10-16 zykkk-power/NxusAgent 未评级 智能问答助手
2026-10-16 xerj-org/xerj 未评级 XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. Elasticsearch compatible, so existing clients just work.
2026-10-15 Show HN: Using the long book of the law to improve PA health insurance appeals 未评级
2026-10-15 Show HN: Caesarcipher.org 未评级
2026-10-14 Show HN: Search for AI agents with usefulness score built in 未评级 Hi HN. I partnered with Simon Kley to build this project at innovation intelligence hackathon (Berkeley). Simply, we’re building a usefulness score on top of search for ai-agents. Instead of agents reading 10 ranked relevant pages, we run a usefulness score first and give it only those that pass. We’re able to save token and cost with this and slightly better answers. During our research, we found out that the current search results already do justice when it comes to simple queries. The rankings work well. They struggle when the task requires deep research or recency matters. So, we decided to talk to devs building ai-agents that research companies for sales outreach. Deep research and recency matters a lot to them. And in their words “every so often, stale facts reach emails.” They catch them by someone responding to the email or human review. From our tests, When an agent got outdated alert for 7 companies, it pitched outdated news for 4 out of them. Talking to the engineers already building this agents, we learned that cost saving is not the real goal. They’re ready to pay premium for confident results. So we added another check to our score. We call it superseding score, it check for pages replaced by newer news. For example, if two recent pages were fetched for news on Humane ai pin. If the first talks about how groundbreaking the product is and the second did that + talked about the HP acquisition, then the second page supersedes the first. The first page gets a lower score. We’re looking for feedbacks here and also teams that are building agents that research companies for outreach. Thanks. Plus, we rank a page once and every agent reuses it, so the more the agents use us, the cheaper the search gets.
2026-10-13 Show HN: Ctxvitals – a vitals check for your AI agent stack (npx ctxvitals) 未评级
2026-10-10 Tencent/WeKnora 未评级 Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.