GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) is a technique that improves large language models by retrieving relevant information from external sources and using it to generate more accurate and context-aware responses. A RAG system combines information retrieval with a language model. It is commonly used in AI assistants, search systems, document question answering, and applications that need access to private or frequently updated information. Here are 64,969 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
ui ai mcp openapi self-hosted openai webui rag llm llms ollama llm-ui ollama-webui llm-webui open-webui
The agent engineering platform.
python open-source enterprise framework typescript ai gemini openai multiagent agents ai-agents rag pydantic llm generative-ai chatgpt langchain anthropic langgraph deepagents
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
tree-sitter skills mcp code-analysis ast gemini knowledge-graph code-search developer-tools cursor leiden codex ai-agents rag graphify llm graphrag antigravity claude-code openclaw
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
ai sqlite embeddings artificial-intelligence ai-agents claude memory-engine long-term-memory rag anthropic chromadb ai-memory mem0 claude-code supermemory openmemory claude-agents claude-agent-sdk claude-code-plugin claude-skills
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
ai ai-agents knowledge-compilation rag context-engine retrieval-augmented-generation context-management agentic-search agentic-ai context-engineering agent-harness agentic-retrieval harness-engineering search-harness agent-native-database retrieval-harness
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
ocr pdf-parser kie document-translation rag chineseocr ai4science pp-ocr document-parsing pp-structure pdf-extractor-rag pdf2markdown paddleocr-vl
Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.
python markdown open-source crawler scraper ai mcp web-crawler web-scraping data-extraction web-crawling ai-agents rag playwright llm crawl4ai-cloud
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
agent deep-learning openai language-model agents ai-agents rag prompt-engineering llms generative-ai chatgpt
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.
python agent typescript compression ai proxy mcp tokens openai cursor rag fastapi llm prompt-engineering langchain anthropic context-window claude-code token-optimization context-engineering
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
python state-management ai memory memory-management agents ai-agents long-term-memory rag llm chatgpt genai agentic-memory agentic-memory-system
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
ai-agents multimodal rag vector-database llm localai local-ai agentic-workflow agentic-ai computer-use self-hosted-ai agent-orchestration agent-harness hermes-agent agent-computer
A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
real-time mongodb self-hosted semantic-search pathway no-code pinecone document-search live-data rag weaviate milvus vector-database duckdb qdrant llm pgvector chromadb document-qa retrieval-augmented-generation
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
learning interactive-learning multi-agent-systems ai-agents cli-tool rag ai-tutor deepresearch clawbot
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
agent reinforcement-learning book mcp multi-agent multimodal rag ai-agent large-language-models llm agent-memory coding-agent context-engineering
Build AI Agents, Visually
react javascript typescript chatbot artificial-intelligence openai multiagent-systems agents workflow-automation low-code no-code rag large-language-models chatgpt langchain agentic-workflow agentic-ai
LlamaIndex is the document processing platform for AI
一款免费开源的 AI 低代码平台，也是 AI 时代构建复杂业务系统的开源基座！权限、多租户、工作流、报表、大屏、AI 知识库等通用能力开箱即用，AI 只需生成业务差异部分。AI Skills 一句话生成完整系统——建表、前后端代码、菜单权限、BPM 流程、表单、报表、大屏全自动。内置 AI 应用平台（聊天、知识库、流程编排、MCP），兼容主流大模型
agent cli ai skills mcp codegenerator antd springboot activiti mybatis-plus codex springcloud low-code flowable rag vue3 llm langchain4j spring-ai claude-code
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
golang distributed nearest-neighbor-search cloud-native image-search vector-similarity faiss anns rag hnsw vector-search vector-database llm embedding-database embedding-store vector-store embedding-similarity diskann
Related topicsartificial-intelligence embeddings generative-ai llms |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |