ragflow
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
- 95k
- Go
- Apache-2.0
- 10 h ago
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
Master the art of building and enhancing AI agents. Learn to develop flow-based applications, implement agentic search, and incorporate human-in-the-loop systems using LangGraph's powerful components.
Official code for the paper "A New Role for Relevance: Guiding Corpus Interaction in Agentic Search"
Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.
Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.
Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools
OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.
Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and reproducible benchmarks.
A self-hosted knowledge broker for homelabs. Routes and fuses queries across Kiwix, FreshRSS, Open-Meteo, SearXNG, Uptime Kuma, and Home Assistant — and tracks what changed over time. REST API and MCP server, integrates natively with Open WebUI and Home Assistant.
Official repository for Deep Research Comparator: A Platform For Fine-grained Human Annotations of Deep Research Agents
A Benchmark for Evaluating Agentic Search and Deep Research Discovery, Completeness, and Traversal Depth
A verifiers RLM environment for testing whether adaptive recursive search outperforms brittle manual RAG choreography on long synthetic corpora.
Official repository for DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning.
Sentence similarity model, used with sentence-transformers.
Unofficial C# port of the T-Search agentic-search harness, on Microsoft Agent Framework. Byte-faithful to the upstream Python harness (turbo-llm/t-search-harness).
Sentence similarity model, used with sentence-transformers.
Sentence similarity model, used with sentence-transformers.
Feature extraction model, used with transformers.