RAG: open-source projects on GitHub
533 repositories on RAG, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
MULTIMODAL RAG SURVEY
Comprehensive survey of multimodal RAG methods: from retriever architectures to generation strategies. 545 stars on GitHub. Perfect for topic entry.
★ 545BYTESDESK AI CHAT FOR TEAMS
Open IM service with AI chat, email, tickets and omni‑channel support — an alternative to Slack, Zendesk and Intercom.
★ 540 · JavaLocal-First AI Creation Workstation
A local-first full-stack AI workstation with chat, comics, drama, writing, and learning modules, supporting vLLM, llama.cpp, and Transformers for multi-engine inference w
★ 535 · PythonTALK WITH ANY ARXIV PAPER
Project talk2arxiv lets you chat with any arXiv article using ChatGPT's power. Via a RAG approach it quickly finds relevant passages and answers with citations. Source co
★ 532 · TypeScriptOpen-Source RAG Marketing Suite
Open-source enterprise RAG solution with local models for knowledge management, AI content creation, and one-click publishing to 17+ platforms.
★ 532 · TypeScriptAI PERSONALIZED EXAM SYSTEM
🧠 Adaptive system for generating exam questions based on LLM, knowledge graph, and BKT algorithm.
★ 531 · PythonModelScope Developer Handbook
A hands‑on guide for developers to select, run, fine‑tune, evaluate, and deploy open‑source models, covering RAG, agents, and AIGC from first run to production.
★ 526 · HTMLOCTOCODE — CODE SEARCH WITH MEANING
Useful codebase search and utility for developers. Written in Rust, already 399 stars on GitHub.
★ 524 · RustDreamServer: Local AI
DreamServer is an open-source project for running LLMs locally with a chat interface, voice control, agents, workflows, RAG, and image generation, operating without cloud
★ 523 · PythonAWESOME-RAG: RESOURCE LIBRARY
A curated collection of resources on Retrieval-Augmented Generation for LLMs. Perfect for developers working with RAG technologies.
★ 521OPEN-SOURCE AIaaS PLATFORM
RESTai — an AIaaS platform with Ollama/vLLM support, built-in image and audio generation, visual block programming, and analytics.
★ 520 · PythonCONTINUOUS-EVAL - LLM EVALUATION ON DATA
Platform for automatic evaluation of LLM applications based on real data. Enables measuring quality and improving models without manual effort.
★ 519 · PythonMEMTRACE: MEMORY FOR AI AGENTS
Structural memory for AI coding agents with a bi‑temporal graph, MCP‑native integration and zero LLM calls. Works in Cursor, Claude Code, VS Code and more.
★ 515 · PythonCORTEXDB: AI MEMORY FILE
A full-featured pure Go library for storing knowledge graphs and AI memory in a single file.
★ 514 · GoMASTER-SKILL: Buddhist AI Framework
Framework for creating a Buddhist AI persona based on FoJin, with accuracy verification, boundary awareness, and runtime readiness.
★ 508 · PythonAGENTIC AI: BUILDING AGENTS
Practical materials for designing and building Gen‑AI agents in Python: architecture, tools, and ready examples.
★ 504 · PythonATHENA-PUBLIC OS FOR AI AGENTS
Linux operating system that gives AI agents persistent memory, autonomy, and time awareness. Manage state, rent intelligence.
★ 497 · PythonUNIVERSAL AI AGENT ON BEDROCK
bedrock-engineer — universal AI agent on Amazon Bedrock. Creates and edits files, executes commands, searches the web, uses knowledge base and multi-agents. Supports imag
★ 487 · TypeScriptMIRA: AI AGENT WITH LONG-TERM MEMORY
Mira — a synthetic entity with a set of primitives for long-term state persistence. The package includes ready‑made modules for an AI‑agent, assistant, and chatbot, inclu
★ 485 · PythonSOURCEWEFT: OPEN AI WORKING STATION....
SourceWeft — open-source self-hosted alternative to ChatGPT and NotebookLM with agents, skills, MCP and a cited knowledge base. Use your models and infrastructure, gettin
★ 477 · TypeScriptNEXT-GEN JAVA AI FRAMEWORK
solon-ai is a powerful Java framework for building AI applications with LLM, RAG, MCP, and agent support. Compatible with Java 8–25 and SpringBoot.
★ 473 · JavaVectorRAG.Net — Vector RAG for .NET
High-performance library for semantic search and RAG on .NET. LSH + exact re-ranking via dot/cosine.
★ 470 · C#ASER: SELF-ASSEMBLY AI AGENT
Aser — lightweight framework for self-assembling AI agents on Python. Supports the a2a protocol, agente memory, and fast deployment via simple scripts.
★ 470 · PythonTELEMEM - MEM0 KILLER IS HERE
High-performance replacement for Mem0 with semantic deduplication, long-term dialog memory, and multimodal video analysis.
★ 464 · PythonSwarmVault: Local Wiki for LLM
Open tool for building knowledge graphs, RAG database, and agent memory. An Obsidian alternative for personal knowledge management and AI second brain.
★ 463 · TypeScriptMIRA OSS: AI IN A BOX
Modular OS with self-configuring tools and self-learning memory. Run and chat via cURL requests.
★ 461 · PythonOFFICIAL SDK FOR PINECONE
Official Python SDK from Pinecone for working with the vector database. Simplifies integrating vector search into your projects.
★ 457 · PythonPOLYWISE - REVIVE YOUR CONTENT
Polywise is an open agent system for animating content, self-sufficiently launching on any platform.
★ 456 · TypeScriptAwesome-Agent-Memory - LLM Memory
A curated list of systems, benchmarks, and articles on memory for LLM/MLLM: long‑term context, retrieval, and reasoning.
★ 456DATAMIND SMART ASSISTANT FOR DATA
DataMind — AI assistant on LlamaIndex with RAG, GraphRAG, NL2SQL, skills and memory. Supports multimodal input and working with data of any type.
★ 456 · PythonAGENTIC RAG WITH RL SUPPORT
Harness-RL — agentic RAG framework where RL optimizes search and generation. Supports GRPO, work with LLM, and extension via Python API.
★ 452 · PythonHEYM: AI Automation Server
Self-hosted platform for AI workflows with a visual canvas, agents, RAG, HITL, MCP, and observability in a single runtime.
★ 451 · PythonAI4J: Agent SDK for Java
Universal Java agent for LLM, Tool Calling, RAG, and a built‑in Coding Agent. Supports OpenAI, Anthropic, DeepSeek, and others.
★ 441 · JavaMARM-MEMORY: LOCAL AI MEMORY
Memory layer for Claude Code and Cursor: combines session history, code indexes, and concept graphs in SQLite, providing cloud‑free context.
★ 438 · PythonDEVELOPER DOCUMENTATION
AnythingLLM — AI platform for working with documents, YouTube, and hosting resources. Boost your ideas!
★ 433 · MDXShiny Colors AI Companion
Chat with The Idolmaster Shiny Colors idols in real-time using Japanese voice with Chinese subtitles. Features story recall, shared memory across characters, and easy Doc
★ 430 · PythonRUOYI-WEB AI AGENT CHAT
RuoYi-Web provides a modern web interface for communicating with AI agents, configuring prompts, and working with knowledge bases via RAG. Users can ask questions, get an
★ 429 · VuePROMPT CACHE SAVINGS 80%
Intelligent semantic cache for LLM prompts, reduces costs up to 80% and delivers sub‑millisecond responses. Provider‑agnostic Go proxy.
★ 427 · GoAZURE OPENAI LLM NOTES - MONTHLY
A curated collection of resources on Azure OpenAI, LLM, RAG, and agents with monthly updates. Ideal for quick start and deep dive.
★ 422 · PythonRAG System for GitHub Issues
RAG over GitHub issues with hand-reviewed eval set and judge audit. Reports confidence intervals, not just point metrics.
★ 419 · PythonNEXTCLOUD-MCP-SERVER - SIMPLIFIED CLOUD ACCESS
The MCP server for Nextcloud provides a simple Python interface to the cloud: authentication, file sync, and extensible plugins.
★ 413 · PythonAURA: AUTONOMOUS RUST SRE AGENT
AURA turns an LLM into a reliable autonomous SRE agent: guardrails, API, state management, auth, streaming and tool integrations for production.
★ 413 · RustIQ-SERIES - AI IN THE CLOUD
Practical introduction to Microsoft IQ via video, notebooks, and Azure deployment templates.
★ 412 · Jupyter NotebookADAPTIVE CHUNKING FOR RAG
Automatically selects the optimal chunking method for each document to improve RAG pipelines. Accepted at LREC 2026.
★ 404 · PythonENTROLY - 80% SAVINGS ON AI
Entroly compresses AI context, detects hallucinations, and saves up to 80% on API costs for OpenAI, Anthropic, and Gemini.
★ 402 · PythonFile system for agents
File system specially developed for AI agents, featuring cutting-edge search, automatic memory profiles, and synchronization. Upload any file types and instantly find wha
★ 396 · RustEDDI: AI Agents from JSON
Quarkus engine turns JSON into ready AI agents with support for 12+ LLM, RAG, and enterprise security.
★ 394 · JavaUniversal Exam Skill
Transforms slides, notes, and past work into a structured knowledge base and test bank, training only on your materials without fabrication. Bilingual EN/中文.
★ 387 · PythonCONVERT PDF TO MARKDOWN
pdf2md is a browser‑based tool that converts PDF files into clean Markdown without installation or complex setup.
★ 385 · TypeScriptANTFLY - POWERFUL TOOL ON ZIG
antfly is a Zig project with 376 stars on GitHub. A fast and efficient tool for developers.
★ 376 · ZigOPEN SOURCE CODING AGENT FOR TERMINAL
Codai — open-source coding agent in C#, runs directly in terminal. Supports Claude and ChatGPT, 374 GitHub stars.
★ 376 · C#DATAMATE - PLATFORM FOR FINE‑TUNING
DataMate – an enterprise platform for data processing, model fine‑tuning, and RAG search in TypeScript.
★ 375 · TypeScriptVECTORDB-PLUGIN: DOCUMENT SEARCH
Ask questions about your documents, audio, and video — get instant answers thanks to vector search in Python.
★ 372 · PythonCHONK TEXT WITH CHONKIE JS
Fast and lightweight TS library for text chunking. Ideal for LLM, RAG, and working with large documents.
★ 370 · TypeScriptDEEPDIVE DEEP RESEARCH AGENT..
Deepdive — skill for Claude Code: 12‑stage pipeline with plan‑review, parallel search, claim verification with dissent protection and multilayer verification. Has 105 blo
★ 368 · PythonRAG DOCUMENTATION HELPER
Reference implementation of a RAG documentation assistant using LangChain, Pinecone, and Tavily. Finds answers in code and web, returns exact source links.
★ 368 · Jupyter NotebookRUSHDB — SCHEMALESS FOR AI
RushDB — a graph‑vector database and memory layer for AI agents. It accepts any JSON and returns typed, searchable records with links — no schemas or migrations required.
★ 367 · TypeScriptORBIT SELF-HOSTED AI
Orbit — self-hosted platform for private RAG and multimodal AI applications in Python.
★ 364 · PythonAGENTICA AI LONG-TASK AGENT
Python framework for AI agents working for hours: auto context assembly, cost budgets, and death-spiral protection.
★ 364 · PythonCOLPALI-COOKBOOKS — COOKING MULTIMODAL RAG
A collection of recipes for training and adapting the ColPali model for your multimodal search tasks.
★ 357New projects on this topic in Telegram
Telegram →