# 📚 RAG / Retrieval / Vector DB

- [nvidia/Nemotron-3-Embed-1B-BF16](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-nvidia-nemotron-3-embed-1b-bf16/) — sentence-similarity · sentence-transformers, safetensors, ministral3
- [pat-jj/harness-1](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/model-pat-jj-harness-1/) — text-generation · transformers, safetensors, gpt_oss
- [rl-llm-wiki/knowledge-base](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/dataset-rl-llm-wiki-knowledge-base/) — · license:cc-by-4.0, arxiv:2203.02155, region:us
- [ducklelabs/duckle](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ducklelabs-duckle/) — Local-first ETL/ELT studio: a drag-and-drop visual pipeline designer that compiles to SQL and runs on DuckDB.…
- [amitshekhariitbhu/transformers-explained](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/amitshekhariitbhu-transformers-explained/) — Transformer architecture explained step by step - the full architecture, every attention variant, positional …
- [uw-math-ai/math-graph](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/dataset-uw-math-ai-math-graph/) — · task_categories:text-retrieval, task_categories:feature-extraction, language:en
- [Aliu-AiRobot/ESEILANE](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/aliu-airobot-eseilane/) — High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelli…
- [FlowElement-ai/m_flow](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/flowelement-ai-m-flow/) — A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
- [MADEVAL/FerryAI](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/madeval-ferryai/) — Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process…
- [DEEIX-AI/DEEIX-Chat](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/deeix-ai-deeix-chat/) — An enterprise AI workspace for model routing, multimodal chat, files, tools, billing, identity, and operation…
- [raiyanyahya/llmaker](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/raiyanyahya-llmaker/) — Selfhost modern LLM stacks. Run the whole fleet from your terminal
- [FutureUniant/WorkShadow](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/futureuniant-workshadow/) — 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 searc…
- [Egoist-Machines/LodeDB](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/egoist-machines-lodedb/) — World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU…
- [stuinfla/Repo-Explainer](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/stuinfla-repo-explainer/) — Repo Explainer — turn any GitHub repo into a visual explainer page. Pipeline + 5 live examples.
- [Graphify-Labs/graphify](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/graphify-labs-graphify/) — Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphi…
- [botAGI/AGmind-ML](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/botagi-agmind-ml/) — Fine-tuned local RAG models. First: agmind-rag-splitter-ru — a Russian context-aware document splitter (T-lit…
- [MemPalace/mempalace](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/mempalace-mempalace/) — The best-benchmarked open-source AI memory system. And it's free.
- [SantanderAI/linear-adapter-trainer](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/santanderai-linear-adapter-trainer/) — Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).
- [tmasjc/deka-oss](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/tmasjc-deka-oss/) — Deka — Aligning Human Intuition with Semantic Space
- [kldhsh123/Afterglow](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/kldhsh123-afterglow/) — 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。
- [ather-techie/rag-interview-system](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ather-techie-rag-interview-system/) — A complete collection of RAG interview questions, answers (505 questions & 41 RAG types), system design scena…
- [CodeAbra/iai-personal-memory-engine](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/codeabra-iai-personal-memory-engine/) — Independent Autistic Intelligence — a cyber brain for your AI. It never forgets a detail, remembers exactly w…
- [RyanCodrai/turbovec](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ryancodrai-turbovec/) — A vector index built on TurboQuant, written in Rust with Python bindings
- [infino-ai/infino](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/infino-ai-infino/) — Fast search engine on object storage, with full text search, vectors, and SQL, natively on Parquet.
- [mirkobozzetto/flowflow](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/mirkobozzetto-flowflow/) — Voice notes for iPhone and macOS - 100% Rust, Dioxus, local-first (SQLite + LanceDB + RIG)
- [ayoubnabil/aiondb](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ayoubnabil-aiondb/) — PostgreSQL-compatible SQL, graph, and vector database built from scratch in Rust.
- [lhh737/KnowledgeBase-RAG-LLM-System](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/lhh737-knowledgebase-rag-llm-system/) — 基于 Streamlit、LangChain 与 Chroma 的轻量级 RAG 学习项目，支持本地知识库上传、检索增强问答与聊天式交互。
- [ohdearquant/lattice](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ohdearquant-lattice/) — Run, quantize, and fine-tune LLMs on Apple Silicon. Pure Rust, no Python, no CUDA, no ONNX
- [CortexReach/memory-lancedb-pro](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/cortexreach-memory-lancedb-pro/) — Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-S…
- [jia-gao/leanctx](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/jia-gao-leanctx/) — Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Py…
- [giancarloerra/SocratiCode](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/giancarloerra-socraticode/) — Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP:…
- [0xMassi/webclaw](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/0xmassi-webclaw/) — Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CL…
- [Prismer-AI/PrismerCloud](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/prismer-ai-prismercloud/) — Prismer Cloud
- [ENDEVSOLS/LongParser](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/endevsols-longparser/) — Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG …
- [Sandermage/sndr_core_engine](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/sandermage-sndr-core-engine/) — SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86…
- [bohyy/academic-ai-prompt](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/bohyy-academic-ai-prompt/) — 一套为研究生和学术研究者设计的完整AI Prompt库 📖 包含内容： ✨ 40+ 精心设计的AI Prompt ✨ 论文选题系统方法（生成、评估、论证） ✨ 论文查找快速方案（8个不同方案） ✨ 文献综述框架和工具 …
- [Emmimal/context-engine](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/emmimal-context-engine/) — A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budge…
- [onyx-dot-app/EnterpriseRAG-Bench](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/onyx-dot-app-enterpriserag-bench/) — Dataset and benchmark for RAG on company internal documents.
- [JustVugg/distillery](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/justvugg-distillery/) — Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and p…
- [likeslines-maker/VectorRAG.Net](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/likeslines-maker-vectorrag-net/) — VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieva…
- [zilliztech/vector-graph-rag](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/zilliztech-vector-graph-rag/) — Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.
- [QingGo/engram-peft](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/qinggo-engram-peft/) — 🚀 Engram-PEFT: An unofficial implementation of DeepSeek Engram. Inject high-capacity conditional memory into …
- [EngramMemory/engram-memory](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/engrammemory-engram-memory/) — The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & bu…
- [bigint/rag.computer](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/bigint-rag-computer/) — Self-hostable RAG platform - document ingestion, embedding, and vector search behind a simple REST API
- [McKern3l/RAGdrag](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/mckern3l-ragdrag/) — RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS
- [GaeaRuiW/kube-llmops](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/gaearuiw-kube-llmops/) — 用 Kubernetes 管理大型語言模型的運維工具。
- [vixhal-baraiya/pageindex-rag](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/vixhal-baraiya-pageindex-rag/) — Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG)
- [lyonzin/knowledge-rag](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/lyonzin-knowledge-rag/) — [knowledge-rag] - Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid sear…
- [ogham-mcp/ogham-mcp](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/ogham-mcp-ogham-mcp/) — Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
- [marswangyang/personal-ai-memory](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/marswangyang-personal-ai-memory/) — A local-first Chrome extension that passively captures ChatGPT, Gemini, Claude, Grok, Perplexity conversation…
- [MicroClub-USTHB/mAIcro](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/microclub-usthb-maicro/) — A reusable, open-source AI infrastructure designed for communities and organizations. It understands structur…
- [radcrew/radcrew-unveiled](https://cenxialiu7-cloud.github.io/ai-oss-daily/en/p/radcrew-radcrew-unveiled/) — RadCrew.org website with LLM-powered chatbot