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

• Updated Nov 12, 2026
• Go

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

memory code-generation chat-bot agentic-search deep-research agentic-insight

• Updated Nov 9, 2026
• Python

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

mcp self-hosted knowledge-graph research-tool note-taking dag pkm infinite-canvas human-in-the-loop react-flow local-first ai-tools llm ollama agentic-search context-engineering dsh-plugin cordis-plugin deepseek-harness-plugin

• Updated Nov 8, 2026
• TypeScript

Scholar All-In-One: A research infrastructure for AI agents

scientific-computing scientific-research autonomous-research ai-agent research-tools ai-for-science computational-research agentic-search agentic-science research-workflow autoresearch

• Updated Oct 27, 2026
• Python

A Minimalistic Search Agent

agentic-search deep-research deep-research-agent

• Updated May 12, 2026
• TypeScript

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.

state-management human-in-the-loop ai-agents langchain langgraph flow-based-applications agentic-search essay-writing-agent agent-development ai-enhancement python-llm-integration agent-components task-division agent-accuracy

• Updated Jun 20, 2024
• Jupyter Notebook

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.

python ai-agents fastapi research-synthesis searxng openrouter gpt-researcher tavily agentic-search agentic-ai model-context-protocol mcp-server mcp-tools deep-research claude-code ai-research-tool qwen3 claude-mcp ai-research-agent perplexity-alternative

• Updated Sep 30, 2026
• Python

Official code for the paper "A New Role for Relevance: Guiding Corpus Interaction in Agentic Search"

ranking grep-search embeddings-similarity agentic-search

• Updated Oct 11, 2026
• Python

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

retrieval embeddings mlx reranker rag jina apple-silicon llm llama-cpp qwen agentic-search test-time-compute pi-dev closed-corpus-qa

• Updated Jun 26, 2026
• Python

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

open-source mcp cursor cline ai-agents autogen ai-agent langchain llamaindex gpt-researcher research-agent agentic-search mcp-server chinese-search deep-research claude-code perplexity-alternative claude-code-plugin agent-infrastructure tavily-alternative

• Updated Nov 12, 2026
• Python

Task-plan driven SEO and LLM-friendly website skill cluster

seo schema-org structured-data codex ai-agents search-optimization technical-seo llm agentic-search llms-txt codex-skills skill-cluster

• Updated Jun 11, 2026
• Python

python text-compression ai-agents cli-tool level-of-detail code-exploration llm-tools context-window agentic-search claude-code rag-alternative structure-aware-compression

• Updated Feb 5, 2026
• Python

OreoLook — an open-source, OpenAI-compatible agentic web search and deep-research engine with streaming, MCP tools, Redis memory, Qdrant retrieval, and PDF exports.

python redis self-hosted pdf-generation semantic-search web-search rag qdrant llm ai-search-engine retrieval-augmented-generation research-agent agentic-search model-context-protocol mcp-server pollinations-ai deep-research openai-compatible oreolook

• Updated Oct 27, 2026
• Python

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.

docker rss privacy self-hosted home-assistant kiwix homelab freshrss voice-assistant fastapi local-first searxng llm-tools local-ai ollama open-webui semantic-routing agentic-search mcp-server multi-source-search

• Updated Oct 16, 2026
• Python

Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and reproducible benchmarks.

python sqlite embeddings knowledge-base minimax bm25 reranking fts5 rag local-first hybrid-search llm retrieval-augmented-generation openrouter local-rag agentic-search vector-free jev jev-rag jevrag

• Updated Nov 8, 2026
• Python

Excellent hybrid search in the Postgres you own.

search-engine postgresql semantic-search keyword-search rag hybrid-search agentic-search

• Updated Nov 10, 2026
• TypeScript

Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.

open-source search-engine mcp web-crawler self-hosted knowledge-base semantic-search pdf-parsing gemini-api rag vector-search document-ingestion ai-agent llm generative-ai retrieval-augmented-generation agentic-search agentic-ai model-context-protocol mcp-server

• Updated Feb 15, 2026
• Go

An extensive and commented list of resources on agentic search and agentic deep research

agentic-search deep-research agentic-retrieval

• Updated Nov 2, 2026
• TeX

EviBack: Reinforcement Learning Search Agents via Evidence-Constrained Teacher Backoff

agent agent-framework agentic-search agentic-ai agent-skill

• Updated Aug 4, 2026
• Python

A novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy.

reinforcement-learning self-awareness llm agentic-search

• Updated Jun 13, 2026
• Python