# 2560 Applications F9b340d6
> App and Agent
- Skill: `tools-only/2560-applications-f9b340d6` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add tools-only/2560-applications-f9b340d6`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tools-only/2560-applications-f9b340d6/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: tools-only (https://skillmd.com/u/tools-only)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/tools-only/2560-applications-f9b340d6
---
# App and Agent
## **Contents**
- [RAG (Retrieval-Augmented Generation)](#rag-retrieval-augmented-generation)
- [Advanced RAG](#advanced-rag)
- [GraphRAG](#graphrag)
- [RAG Application](#rag-application)
- [Vector Database & Embedding](#vector-database--embedding)
- [AI Application](#ai-application)
- [Top Agent Frameworks](#top-agent-frameworks)
- [Orchestration Framework](#orchestration-framework)
- [Frameworks / SDKs / Building Blocks](#frameworks--sdks--building-blocks)
- [Multi-Agent & Swarm Frameworks](#multi-agent--swarm-frameworks)
- [General Agent Frameworks](#general-agent-frameworks)
- [Official Vendor SDKs](#official-vendor-sdks)
- [Tool Integration & Infrastructure](#tool-integration--infrastructure)
- [Monitoring, Training & Optimization](#monitoring-training--optimization)
- [NLP & ML Libraries](#nlp--ml-libraries)
- [Apps / Demos / Ready-to-use Agents](#apps--demos--ready-to-use-agents)
- [General Autonomous Agents](#general-autonomous-agents)
- [Coding & Development](#coding--development)
- [Research, Web & Knowledge Tools](#research-web--knowledge-tools)
- [Productivity & Personal Assistants](#productivity--personal-assistants)
- [Data, Finance & Analytics](#data-finance--analytics)
- [Specialized Agents](#specialized-agents)
- [No Code & User Interface](#no-code--user-interface)
- [Personal AI assistant & desktop](#personal-ai-assistant--desktop)
- [Infrastructure & Backend Services](#infrastructure--backend-services)
- [Caching](#caching)
- [Data Processing](#data-processing)
- [Gateway](#gateway)
- [Memory](#memory)
- [Agent Protocol](#agent-protocol)
- [Model Context Protocol (MCP)](#model-context-protocol-mcp)
- [A2A](#a2a)
- [Computer use](#computer-use)
- [Coding & Research](#coding--research)
- [Coding](#coding)
- [Skill](#skill)
- [Domain-Specific Agents](#domain-specific-agents)
- [Deep Research](#deep-research)
## **RAG (Retrieval-Augmented Generation)**
- RAG integrates retrieval (searching) into LLM text generation, enabling models to access external information. [✍️](https://towardsdatascience.com/rag-vs-finetuning-which-is-the-best-tool-to-boost-your-llm-application-94654b1eaba7) [25 Aug 2023]
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks📑](https://arxiv.org/abs/2005.11401): Meta's 2020 framework for giving LLMs access to information beyond training data. [22 May 2020]
- RAG-sequence — Retrieve k documents to generate all output tokens.
- RAG-token— Retrieve k documents per token generation.
- RAG-sequence is the industry standard due to lower cost and simplicity. [✍️](https://towardsdatascience.com/add-your-own-data-to-an-llm-using-retrieval-augmented-generation-rag-b1958bf56a5a) [30 Sep 2023]
### **Advanced RAG**
- [9 Effective Techniques To Boost Retrieval Augmented Generation (RAG) Systems✍️](https://towardsdatascience.com/9-effective-techniques-to-boost-retrieval-augmented-generation-rag-systems-210ace375049) [🗄️](9-effective-rag-techniques.png): ReRank, Prompt Compression, Hypothetical Document Embedding (HyDE), Query Rewrite and Expansion, Enhance Data Quality, Optimize Index Structure, Add Metadata, Align Query with Documents, Mixed Retrieval (Hybrid Search) [2 Jan 2024]
- Advanced RAG Patterns: How to improve RAG peformance [✍️](https://cloudatlas.me/why-do-rag-pipelines-fail-advanced-rag-patterns-part1-841faad8b3c2) / [✍️](https://cloudatlas.me/how-to-improve-rag-peformance-advanced-rag-patterns-part2-0c84e2df66e6) [17 Oct 2023]
- Data quality: Clean, standardize, deduplicate, segment, annotate, augment, and update data to make it clear, consistent, and context-rich.
- Embeddings fine-tuning: Fine-tune embeddings to domain specifics, adjust them according to context, and refresh them periodically to capture evolving semantics.
- Retrieval optimization: Refine chunking, embed metadata, use query routing, multi-vector retrieval, re-ranking, hybrid search, recursive retrieval, query engine, [HyDE📑](https://arxiv.org/abs/2212.10496) [20 Dec 2022], and vector search algorithms to improve retrieval efficiency and relevance.
- Synthesis techniques: Query transformations, prompt templating, prompt conditioning, function calling, and fine-tuning the generator to refine the generation step.
- HyDE: Implemented in [LangChain: HypotheticalDocumentEmbedder✨](https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb). A query generates hypothetical documents, which are then embedded and retrieved to provide the most relevant results. `query -> generate n hypothetical documents -> documents embedding - (avg of embeddings) -> retrieve -> final result.` [✍️](https://www.jiang.jp/posts/20230510_hyde_detailed/index.html)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG📑](https://arxiv.org/abs/2501.09136) [15 Jan 2025]
- [Azure RAG with Vision Application Framework✨](https://github.com/Azure-Samples/rag-as-a-service-with-vision) [Mar 2024] 
- [Contextual Retrieval✍️](https://www.anthropic.com/news/contextual-retrieval): Contextual Retrieval enhances traditional RAG by using Contextual Embeddings and Contextual BM25 to maintain context during retrieval. [19 Sep 2024]
- Demystifying Advanced RAG Pipelines: An LLM-powered advanced RAG pipeline built from scratch [✨](https://github.com/pchunduri6/rag-demystified) [19 Oct 2023]
- [Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG📑](https://arxiv.org/abs/2411.07688): Ultra High Resolution (UHR) remote sensing imagery, such as satellite imagery and medical imaging. [12 Nov 2024]
- [Evaluation with Ragas✍️](https://towardsdatascience.com/visualize-your-rag-data-evaluate-your-retrieval-augmented-generation-system-with-ragas-fc2486308557): UMAP (often used to reduce the dimensionality of embeddings) with Ragas metrics for visualizing RAG results. [Mar 2024] / `Ragas provides metrics`: Context Precision, Context Relevancy, Context Recall, Faithfulness, Answer Relevance, Answer Semantic Similarity, Answer Correctness, Aspect Critique [✨](https://github.com/explodinggradients/ragas) [May 2023]
- From Simple to Advanced RAG (LlamaIndex) [✍️](https://twitter.com/jerryjliu0/status/1711419232314065288) / [🗄️](../files/archive/LlamaIndexTalk_PyDataGlobal.pdf) /💡[✍️](https://aiconference.com/speakers/jerry-liu-2023/) [10 Oct 2023]
- [How to improve RAG Piplines](https://www.linkedin.com/posts/damienbenveniste_how-to-improve-rag-pipelines-activity-7241497046631776256-vwOc?utm_source=li_share&utm_content=feedcontent&utm_medium=g_dt_web&utm_campaign=copy): LangGraph implementation with Self-RAG, Adaptive-RAG, Corrective RAG. [Oct 2024]
- How to optimize RAG pipeline: [Indexing optimization](https://newsletter.theaiedge.io/p/how-to-optimize-your-rag-pipelines) [24 Oct 2023]
- [localGPT-Vision✨](https://github.com/PromtEngineer/localGPT-Vision): an end-to-end vision-based Retrieval-Augmented Generation (RAG) system. [Oct 2024] 
- [Multi-Modal RAG System✍️](https://machinelearningmastery.com/implementing-multi-modal-rag-systems/): Building a knowledge base with both image and audio data. [12 Feb 2025]
- [🗣️](https://twitter.com/yi_ding/status/1721728060876300461) [7 Nov 2023] `OpenAI has put together a pretty good roadmap for building a production RAG system.` Naive RAG -> Tune Chunks -> Rerank & Classify -> Prompt Engineering. In `llama_index`... [📺](https://www.youtube.com/watch?v=ahnGLM-RC1Y)
- [Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering📑](https://arxiv.org/abs/2411.17073): Using HistoCartography to improve pathology image analysis and boost PathVQA-Open performance. [26 Nov 2024]
- [RAG Hallucination Detection Techniques✍️](https://machinelearningmastery.com/rag-hallucination-detection-techniques/): Hallucination metrics using the DeepEval, G-Eval. [10 Jan 2025] - [UniversalRAG✨](https://github.com/wgcyeo/UniversalRAG) [29 Apr 2025] 
- [VideoRAG📑](https://arxiv.org/abs/2501.05874): Not only does it retrieve relevant videos from a large video corpus, but it also integrates both the visual and textual elements of videos into the answer-generation process using Large Video Language Models (LVLMs). [10 Jan 2025]
- [Visual RAG over PDFs with Vespa✍️](https://blog.vespa.ai/visual-rag-in-practice/): a demo showcasing Visual RAG over PDFs using ColPali embeddings in Vespa [✨](https://github.com/vespa-engine/sample-apps/tree/master/visual-retrieval-colpali) [19 Nov 2024]
- [What is Agentic RAG](https://weaviate.io/blog/what-is-agentic-rag): The article published by Weaviate. [5 Nov 2024]
### **GraphRAG**
- [Fast GraphRAG✨](https://github.com/circlemind-ai/fast-graphrag): 6x cost savings compared to `graphrag`, with 20% higher accuracy. Combines PageRank and GraphRAG. [Oct 2024] 
- [FalkorDB✨](https://github.com/FalkorDB/FalkorDB): Graph Database. Knowledge Graph for LLM (GraphRAG). OpenCypher (query language in Neo4j). [Jul 2023] 
- [GitNexus✨](https://github.com/abhigyanpatwari/GitNexus): Indexes codebases into a knowledge graph and exposes it via MCP tools for AI agents. [Aug 2025] 
- [Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!📑](https://arxiv.org/abs/2405.11706): using a knowledge graph, the Text-to-SQL accuracy improved from 16% to 54%. [20 May 2024]
- [Graph RAG (by NebulaGraph)](https://medium.com/@nebulagraph/graph-rag-the-new-llm-stack-with-knowledge-graphs-e1e902c504ed): NebulaGraph proposes the concept of Graph RAG, which is a retrieval enhancement technique based on knowledge graphs. [demo](https://www.nebula-graph.io/demo) [8 Sep 2023]
- [GraphRAG (by Microsoft)📑](https://arxiv.org/abs/2404.16130):🏆1. Global search: Original Documents -> Knowledge Graph (Community Summaries generated by LLM) -> Partial Responses -> Final Response. 2. Local Search: Utilizes vector-based search to find the nearest entities and relevant information.
[✍️](https://microsoft.github.io/graphrag) / [✨](https://github.com/microsoft/graphrag) [24 Apr 2024]
- [DRIFT Search✍️](https://www.microsoft.com/en-us/research/blog/introducing-drift-search-combining-global-and-local-search-methods-to-improve-quality-and-efficiency/): DRIFT search (Dynamic Reasoning and Inference with Flexible Traversal) combines global and local search methods to improve query relevance by generating sub-questions and refining the context using HyDE (Hypothetical Document Embeddings). [31 Oct 2024]
- ["From Local to Global" GraphRAG with Neo4j and LangChain](https://neo4j.com/developer-blog/global-graphrag-neo4j-langchain/) [09 Jul 2024]
- [GraphRAG Implementation with LlamaIndex✨](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/cookbooks/GraphRAG_v1.ipynb) [15 Jul 2024]
- [Improving global search via dynamic community selection✍️](https://www.microsoft.com/en-us/research/blog/graphrag-improving-global-search-via-dynamic-community-selection/): Dynamic Community Selection narrows the scope by selecting the most relevant communities based on query relevance, utilizing Map-reduce search, reducing costs by 77% without sacrificing output quality [15 Nov 2024]
- [LazyGraphRAG✍️](https://www.microsoft.com/en-us/research/blog/lazygraphrag-setting-a-new-standard-for-quality-and-cost/): Reduces costs to 0.1% of full GraphRAG through efficient use of best-first (vector-based) and breadth-first (global search) retrieval and deferred LLM calls [25 Nov 2024]
- [LightRAG✨](https://github.com/HKUDS/LightRAG): Utilizing graph structures for text indexing and retrieval processes. [8 Oct 2024] 
- [nano-graphrag✨](https://github.com/gusye1234/nano-graphrag): A simple, easy-to-hack GraphRAG implementation [Jul 2024]
- [Graphiti✨](https://github.com/getzep/graphiti)
- [GraphSearch✨](https://github.com/DataArcTech/GraphSearch): An Agentic Workflow for Graph RAG. [Oct 2025]
- [HippoRAG✨](https://github.com/OSU-NLP-Group/HippoRAG):💡RAG + Knowledge Graphs + Personalized PageRank. [23 May 2024] 
- [How to Build a Graph RAG App✍️](https://towardsdatascience.com/how-to-build-a-graph-rag-app-b323fc33ba06): Using knowledge graphs and AI to retrieve, filter, and summarize medical journal articles [30 Dec 2024]
- [HybridRAG📑](https://arxiv.org/abs/2408.04948): Integrating VectorRAG and GraphRAG with financial earnings call transcripts in Q&A format. [9 Aug 2024]
- [Neo4j GraphRAG Package for Python✨](https://github.com/neo4j/neo4j-graphrag-python) [Feb 2024] 
### **RAG Application**
1. [AutoRAG✨](https://github.com/Marker-Inc-Korea/AutoRAG): RAG AutoML tool for automatically finds an optimal RAG pipeline for your data. [Jan 2024] 
1. [Canopy✨](https://github.com/pinecone-io/canopy): open-source RAG framework and context engine built on top of the Pinecone vector database. [Aug 2023] 
1. [Chonkie✨](https://github.com/SecludedCoder/chonkie): RAG chunking library [Nov 2024] 
1. [Cognita✨](https://github.com/truefoundry/cognita): RAG (Retrieval Augmented Generation) Framework for building modular, open-source applications [Jul 2023] 
1. [Danswer✨](https://github.com/danswer-ai/danswer): Ask Questions in natural language and get Answers backed by private sources: Slack, GitHub, Confluence, etc. [Apr 2023] 
1. [Fireplexity✨](https://github.com/mendableai/fireplexity): AI search engine by Firecrawl's search API [Jun 2025] 
1. [FlashRAG✨](https://github.com/RUC-NLPIR/FlashRAG): A Python Toolkit for Efficient RAG Research [Mar 2024] 
1. [Gemini-Search✨](https://github.com/ammaarreshi/Gemini-Search): Perplexity style AI Search engine clone built with Gemini [Jan 2025] 
1. [Haystack✨](https://github.com/deepset-ai/haystack): LLM orchestration framework to build customizable, production-ready LLM applications. [5 May 2020] 
1. [KAG✨](https://github.com/OpenSPG/KAG): Knowledge Augmented Generation. a logical reasoning and Q&A framework based on the OpenSPG(Semantic-enhanced Programmable Graph). By Ant Group. [Oct 2024] 
1. [Khoj✨](https://github.com/khoj-ai/khoj): Open-source, personal AI agents. Cloud or Self-Host, Multiple Interfaces. Python Django based [Aug 2021] 
1. [kotaemon✨](https://github.com/Cinnamon/kotaemon): Open-source clean & customizable RAG UI for chatting with your documents. [Mar 2024] 
1. [llm-answer-engine✨](https://github.com/developersdigest/llm-answer-engine): Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Mixtral, LangChain, OpenAI, Brave & Serper [Mar 2024] 
1. [llmware✨](https://github.com/llmware-ai/llmware): Building Enterprise RAG Pipelines with Small, Specialized Models [Sep 2023] 
1. [Marqo✨](https://github.com/marqo-ai/marqo): Tensor search for humans [Aug 2022] 
1. [MedGraphRAG📑](https://arxiv.org/abs/2408.04187): MedGraphRAG outperforms the previous SOTA model, [Medprompt📑](https://arxiv.org/abs/2311.16452), by 1.1%. [✨](https://github.com/medicinetoken/medical-graph-rag) [8 Aug 2024] 
1. [Meilisearch✨](https://github.com/meilisearch/meilisearch): A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. [Apr 2018] 
1. [MemFree✨](https://github.com/memfreeme/memfree): Hybrid AI Search Engine + AI Page Generator. [Jun 2024] 
1. [MindSearch✨](https://github.com/InternLM/MindSearch): An open-source AI Search Engine Framework [Jul 2024] 
1. [MiniRAG✨](https://github.com/HKUDS/MiniRAG): RAG through heterogeneous graph indexing and lightweight topology-enhanced retrieval. [Jan 2025] 
1. [Morphic✨](https://github.com/miurla/morphic): An AI-powered search engine with a generative UI [Apr 2024] 
1. [PageIndex✨](https://github.com/VectifyAI/PageIndex): a vectorless, reasoning-based RAG system that builds a hierarchical tree index [Apr 2025] 
1. [PaperQA2✨](https://github.com/Future-House/paper-qa): High accuracy RAG for answering questions from scientific documents with citations [Feb 2023] 
1. [Perplexica✨](https://github.com/ItzCrazyKns/Perplexica):💡Open source alternative to Perplexity AI [Apr 2024] 
1. [PrivateGPT✨](https://github.com/imartinez/privateGPT): 100% privately, no data leaks. The API is built using FastAPI and follows OpenAI's API scheme. [May 2023] 
1. [Pyversity✨](https://github.com/Pringled/pyversity): A rerank library for search results [Oct 2025] 
1. [quivr✨](https://github.com/QuivrHQ/quivr): A personal productivity assistant (RAG). Chat with your docs (PDF, CSV, ...) [May 2023] 
1. [R2R (Reason to Retrieve)✨](https://github.com/SciPhi-AI/R2R): Agentic Retrieval-Augmented Generation (RAG) with a RESTful API. [Feb 2024] 
1. [RAG Builder✨](https://github.com/KruxAI/ragbuilder): Automatically create an optimal production-ready Retrieval-Augmented Generation (RAG) setup for your data. [Jun 2024] 
1. [RAG capabilities of LlamaIndex to QA about SEC 10-K & 10-Q documents✨](https://github.com/run-llama/sec-insights): A real world full-stack application using LlamaIndex [Sep 2023] 
1. [RAG-Anything✨](https://github.com/HKUDS/RAG-Anything): "RAG-Anything: All-in-One RAG System". [Jun 2025] 
1. [RAGApp✨](https://github.com/ragapp/ragapp): Agentic RAG. Custom GPTs, but deployable in your own cloud infrastructure using Docker. [Apr 2024] 
1. [RAGChecker📑](https://arxiv.org/abs/2408.08067): A Fine-grained Framework For Diagnosing RAG [✨](https://github.com/amazon-science/RAGChecker) [15 Aug 2024] 
1. [RAGflow✨](https://github.com/infiniflow/ragflow):💡Streamlined RAG workflow. Focusing on Deep document understanding [Dec 2023] 
1. [RAGFoundry✨](https://github.com/IntelLabs/RAGFoundry): A library designed to improve LLMs ability to use external information by fine-tuning models on specially created RAG-augmented datasets. [5 Aug 2024] 
1. [RAGLite✨](https://github.com/superlinear-ai/raglite): a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite [Jun 2024] 
1. [RAGxplorer✨](https://github.com/gabrielchua/RAGxplorer): Visualizing document chunks and the queries in the embedding space. [Jan 2024] 
1. [Renumics RAG✨](https://github.com/Renumics/renumics-rag): Visualization for a Retrieval-Augmented Generation (RAG) Data [Jan 2024] 
1. [Scira (Formerly MiniPerplx)✨](https://github.com/zaidmukaddam/scira): A minimalistic AI-powered search engine [Aug 2024] 
1. [Semantica✨](https://github.com/Hawksight-AI/semantica): Semantic intelligence layer that makes your AI agents auditable, explainable, and compliant — beyond Text Similarity [Jun 2025] 
1. [Semantra✨](https://github.com/freedmand/semantra): Multi-tool for semantic search [Mar 2023] 
1. [Simba✨](https://github.com/GitHamza0206/simba): Portable KMS (knowledge management system) designed to integrate seamlessly with any Retrieval-Augmented Generation (RAG) system [Dec 2024] 
1. [smartrag✨](https://github.com/aymenfurter/smartrag): Deep Research through Multi-Agents, using GraphRAG. [Jun 2024] 
1. [SWIRL AI Connect✨](https://github.com/swirlai/swirl-search): SWIRL AI Connect enables you to perform Unified Search and bring in a secure AI Co-Pilot. [Apr 2022] 
1. [turboseek✨](https://github.com/Nutlope/turboseek): An AI search engine inspired by Perplexity [May 2024] 
1. [txtai✨](https://github.com/neuml/txtai): Semantic search and workflows powered by language models [Aug 2020] 
1. [Typesense✨](https://github.com/typesense/typesense): Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch [Jan 2017] 
1. [UltraRAG✨](https://github.com/OpenBMB/UltraRAG): A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines [Jan 2025] 
1. [UniversalRAG✨](https://github.com/wgcyeo/UniversalRAG): RAG framework that retrieves across multiple modalities. [29 Apr 2025] 
1. [Verba✨](https://github.com/weaviate/Verba): Retrieval Augmented Generation (RAG) chatbot powered by Weaviate [Jul 2023] 
1. [WeKnora✨](https://github.com/Tencent/WeKnora): LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm. [Jul 2025] 
1. [Xyne✨](https://github.com/xynehq/xyne): an AI-first Search & Answer Engine for work. We're an OSS alternative to Glean, Gemini and MS Copilot. [Sep 2024] 
### **Vector Database & Embedding**
- [A Comprehensive Survey on Vector Database📑](https://arxiv.org/abs/2310.11703): Categorizes search algorithms by their approach, such as hash-based, tree-based, graph-based, and quantization-based. [18 Oct 2023]
- [A Gentle Introduction to Word Embedding and Text Vectorization✍️](https://machinelearningmastery.com/a-gentle-introduction-to-word-embedding-and-text-vectorization/): Word embedding, Text vectorization, One-hot encoding, Bag-of-words, TF-IDF, word2vec, GloVe, FastText. | [Tokenizers in Language Models✍️](https://machinelearningmastery.com/tokenizers-in-language-models/): Stemming, Lemmatization, Byte Pair Encoding (BPE), WordPiece, SentencePiece, Unigram [23 May 2025]
- Azure Open AI Embedding API, `text-embedding-ada-002`, supports 1536 dimensions. Elastic search, Lucene based engine, supports 1024 dimensions as a max. Open search can insert 16,000 dimensions as a vector storage. Open search is available to use as a vector database with Azure Open AI Embedding API.
- [A SQLite extension for efficient vector search, based on Faiss!✨](https://github.com/asg017/sqlite-vss) [Jan 2023]
- [Chroma✨](https://github.com/chroma-core/chroma): Open-source embedding database [Oct 2022]
- [Contextual Document Embedding (CDE)📑](https://arxiv.org/abs/2410.02525): Improve document retrieval by embedding both queries and documents within the context of the broader document corpus. [✍️](https://pub.aimind.so/unlocking-the-power-of-contextual-document-embeddings-enhancing-search-relevance-01abfa814c76) [3 Oct 2024]
- [Contextualized Chunk Embedding Model✍️](https://blog.voyageai.com/2025/07/23/voyage-context-3/): Rather than embedding each chunk separately, a contextualized chunk embedding model uses the whole document to create chunk embeddings that reflect the document's overall context. [✍️](https://blog.dailydoseofds.com/p/contextualized-chunk-embedding-model) [23 Jul 2025]
- [EmbedAnything✨](https://github.com/StarlightSearch/EmbedAnything): Built by Rust. Supports BERT, CLIP, Jina, ColPali, ColBERT, ModernBERT, Reranker, Qwen. Mutilmodality. [Mar 2024] 
- [Embedding Atlas✨](https://github.com/apple/embedding-atlas): Apple. a tool that provides interactive visualizations for large embeddings. [May 2025]
- [Faiss](https://faiss.ai/): Facebook AI Similarity Search (Faiss) is a library for efficient similarity search and clustering of dense vectors. It is used as an alternative to a vector database in the development and library of algorithms for a vector database. It is developed by Facebook AI Research. [✨](https://github.com/facebookresearch/faiss) [Feb 2017]
- [FalkorDB✨](https://github.com/FalkorDB/FalkorDB): Graph Database. Knowledge Graph for LLM (GraphRAG). OpenCypher (query language in Neo4j). For a sparse matrix, the graph can be queried with linear algebra instead of traversal, boosting performance. [Jul 2023] 
- [Fine-tuning Embeddings for Specific Domains✍️](https://blog.gopenai.com/fine-tuning-embeddings-for-specific-domains-a-comprehensive-guide-5e4298b42185): The guide discusses fine-tuning embeddings for domain-specific tasks using `sentence-transformers` [1 Oct 2024]
- [Is Cosine-Similarity of Embeddings Really About Similarity?📑](https://arxiv.org/abs/2403.05440): Regularization in linear matrix factorization can distort cosine similarity. L2-norm regularization on (1) the product of matrices (like dropout) and (2) individual matrices (like weight decay) may lead to arbitrary similarities. [8 Mar 2024]
- OpenAI Embedding models: `text-embedding-3`
- [lancedb✨](https://github.com/lancedb/lancedb): LanceDB's core is written in Rust and is built using Lance, an open-source columnar format. [Feb 2023] 
- [LEANN✨](https://github.com/yichuan-w/LEANN): The smallest vector database. 97% less storage. [Jun 2025] 
- Milvus (A cloud-native vector database) Embedded [✨](https://github.com/milvus-io/milvus) [Sep 2019]: Alternative option to replace PineCone and Redis Search in OSS. It offers support for multiple languages, addresses the limitations of RedisSearch, and provides cloud scalability and high reliability with Kubernetes.
- [MongoDB's GenAI Showcase✨](https://github.com/mongodb-developer/GenAI-Showcase): Step-by-step Jupyter Notebook examples on how to use MongoDB as a vector database, data store, memory provider [Jan 2024] 
- [Not All Vector Databases Are Made Equal✍️](https://towardsdatascience.com/milvus-pinecone-vespa-weaviate-vald-gsi-what-unites-these-buzz-words-and-what-makes-each-9c65a3bd0696): Printed version for "Medium" limits. [🗄️](../files/vector-dbs.pdf) [2 Oct 2021]
- [pgvector✨](https://github.com/pgvector/pgvector): Open-source vector similarity search for Postgres [Apr 2021] / [pgvectorscale✨](https://github.com/timescale/pgvectorscale): 75% cheaper than pinecone [Jul 2023]  
- [Pinecone](https://docs.pinecone.io): A fully managed cloud Vector Database. Commercial Product [Jan 2021]
- [Qdrant✨](https://github.com/qdrant/qdrant): Written in Rust. Qdrant (read: quadrant) [May 2020]
- [Redis extension for vector search, RedisVL✨](https://github.com/redis/redis-vl-python): Redis Vector Library (RedisVL) [Nov 2022]
- [text-embedding-ada-002✍️](https://openai.com/blog/new-and-improved-embedding-model):
Smaller embedding size. The new embeddings have only 1536 dimensions, one-eighth the size of davinci-001 embeddings,
making the new embeddings more cost effective in working with vector databases. [15 Dec 2022]
- [The Semantic Galaxy🤗](https://huggingface.co/spaces/webml-community/semantic-galaxy): Visualize embeddings in 3D space, powered by EmbeddingGemma and Transformers.js [Sep 2025]
- [Vector Search with OpenAI Embeddings: Lucene Is All You Need📑](https://arxiv.org/abs/2308.14963): For vector search applications, Lucene's HNSW implementation is a resilient and extensible solution with performance comparable to specialized vector databases like FAISS. Our experiments used Lucene 9.5.0, which limits vectors to 1024 dimensions—insufficient for OpenAI's 1536-dimensional embeddings. A fix to make vector dimensions configurable per codec has been merged to Lucene's source [here✨](https://github.com/apache/lucene/pull/12436) but was not yet released as of August 2023. [29 Aug 2023]
- [Weaviate✨](https://github.com/weaviate/weaviate): Store both vectors and data objects. [Jan 2021]
- [zvec✨](https://github.com/alibaba/zvec): Lightweight vector database by Alibaba Cloud. [Dec 2025] 
### **AI Application**
- [900 most popular open source AI tools](https://huyenchip.com/2024/03/14/ai-oss.html):🏆What I learned from looking at 900 most popular open source AI tools [list](https://huyenchip.com/llama-police) [Mar 2024]
- [Awesome LLM Apps✨](https://github.com/Shubhamsaboo/awesome-llm-apps):💡A curated collection of awesome LLM apps built with RAG and AI agents. [Apr 2024]
- [Azure OpenAI Samples✨](https://github.com/kimtth/azure-openai-cookbook): 🐳 Azure OpenAI (OpenAI) Sample Collection - 🪂 100+ Code Cookbook 🧪 [Mar 2025]
- [GenAI Agents✨](https://github.com/NirDiamant/GenAI_Agents):🏆Tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. [Sep 2024]
- [GenAI Cookbook✨](https://github.com/dmatrix/genai-cookbook): A mixture of Gen AI cookbook recipes for Gen AI applications. [Nov 2023] 
- [Generative AI Design Patterns✍️](https://towardsdatascience.com/generative-ai-design-patterns-a-comprehensive-guide-41425a40d7d0): 9 architecture patterns for working with LLMs. [Feb 2024]
- [Open100: Top 100 Open Source achievements.](https://www.benchcouncil.org/evaluation/opencs/annual.html)
#### Agent & Application
##### **Top Agent Frameworks**
- [AG2✨](https://github.com/ag2ai/ag2): Multi-agent conversational framework (formerly AutoGen)
- [Agno✨](https://github.com/agno-agi/agno): Agent orchestration framework
- [AWS Bedrock Agents✨](https://github.com/awslabs/amazon-bedrock-agent-samples): AWS-native agent framework
- [CrewAI✨](https://github.com/crewAIInc/crewAI): Role-based
…(truncated)