* [AnythingLLM v1.17.0](https://github.com/Mintplex-Labs/anything-llm) – Full-stack application for turning documents into context for LLMs with multi-user management.

* [anymd v7.0.0](https://github.com/SylphxAI/anymd) – Local-first PDF-to-Markdown conversion for AI agents with page-level tables, locators, and citations that avoid OCR and guesswork.

* [Onyx v4.8.0](https://github.com/onyx-dot-app/onyx) – Feature-rich, self-hostable chat UI that works with any LLM and supports agents, RAG, connectors, web search, and code execution.

* [SurfSense v2.0.0](https://github.com/MODSetter/SurfSense) – Highly customizable AI research agent integrating personal knowledge bases with multiple external sources and advanced search capabilities.

* [FastGPT v4.17.2](https://github.com/labring/FastGPT) – Knowledge-based platform leveraging LLMs for data processing, retrieval, and AI workflow orchestration.

* [Pinecone Go SDK v7.0.0](https://github.com/pinecone-io/go-pinecone) – Go client for interacting with Pinecone data, control, and admin APIs via gRPC and REST.

* [Deuz SDK v2.3.0](https://github.com/Deuz-AI/Deuz-SDK) – Zero-dependency TypeScript runtime for production AI agents, providing durable execution, persistent memory, tool calling, approvals, and resumable runs across Node, Bun, Deno, and edge.

* [CortexDB v2.125.0](https://github.com/liliang-cn/cortexdb) – Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.

* [Bytedesk v4.8.0](https://github.com/Bytedesk/bytedesk) – AI-powered omnichannel customer service platform with team chat, ticketing, knowledge base, and agent workflows for support teams.

* [Garden Skills motion-showreel-v0.1...](https://github.com/ConardLi/garden-skills) – Curated set of production-ready agent skills for Claude Code, Cursor, Codex, and other AI coding agents.

* [Aivory v2.5.0](https://github.com/hjxwz123/Aivory) – Production-ready, self-hosted multi-model AI workspace with interleaved tool execution, RAG knowledge bases, persistent Python sandbox, team workspaces, and full admin backend.

* [SQLBot v1.10.2](https://github.com/dataease/SQLBot) – RAG-based conversational data analysis and Text-to-SQL generation using large language models.

* [Wren AI wren-v0.15.0](https://github.com/Canner/WrenAI) – Generative Business Intelligence agent that allows teams to interact with data for generating insights, reports, and visualizations.

* [AI LocalBase v1.4.11](https://github.com/veyliss/ai-localbase) – Local-first RAG knowledge base connecting local Markdown, TXT, and PDF documents to retrieval search and LLM chat.

* [RAGFlow v1.0.0-rc1](https://github.com/infiniflow/ragflow) – RAG engine combining large language models with document understanding for accurate question answering and citation.

* [BISHENG v3.0.0-beta3](https://github.com/dataelement/bisheng) – LLM application devops platform tailored for enterprise scenarios with comprehensive features.

* [VidLens auto-881a13ca0df28be...](https://github.com/junnhwan/vid-lens) – Go and React-based video RAG system that builds a unified index for OCR, ASR, and frame vision, enabling multi-round agent retrieval with pgvector search.