Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
II-Researcher: a new open-source framework designed to aid building search / research agents
| Date | Stars |
|---|---|
| 2026-07-31 | 496 |
| 2026-08-06 | 496 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">  # II-Researcher **An open-source deep search agent that browses the web, reasons over what it finds, and writes comprehensive, fully-referenced answers to hard questions.** [](https://pypi.org/project/ii-researcher/) [](https://github.com/Intelligent-Internet/ii-researcher/actions/workflows/test.yml) [](LICENSE) [](https://www.python.org/) [](https://github.com/Intelligent-Internet/ii-researcher/stargazers) [Blog post](https://www.ii.inc/web/blog/post/ii-researcher) · [Website](https://ii.inc) · [PyPI](https://pypi.org/project/ii-researcher/) · [Report a bug](https://github.com/Intelligent-Internet/ii-researcher/issues) · [Request a feature](https://github.com/Intelligent-Internet/ii-researcher/issues) </div> --- ## 📰 News - **2025-08** — Added a demo of **II-Search-CIR-4B**, our 4B search-reasoning model with Code-Integrated Reasoning. See [`examples/ii_search_4b`](examples/ii_search_4b). - **2025-06** — II-Researcher scores **84.12%** on Google's [Frames benchmark](https://huggingface.co/datasets/google/frames-benchmark/viewer/default/test) using DeepSeek-R1-0528. [Details below ↓](#-benchmarks) ## 📖 Table of Contents - [Overview](#-overview) - [Features](#-features) - [Benchmarks](#-benchmarks) - [Demo](#-demo) - [Architecture](#%EF%B8%8F-architecture) - [Quick Start](#-quick-start) - [Usage](#%EF%B8%8F-usage) - [CLI](#using-the-cli) - [Web Interface](#using-the-web-interface) - [MCP (Claude Desktop)](#using-mcp) - [Docker](#-run-with-docker) - [Advanced Configuration](#-advanced-configuration) - [Contributing](#-contributing) - [License](#-license) - [Citation](#-citation) - [Acknowledgments](#-acknowledgments) ## 🔍 Overview II-Researcher is a deep search agent built by [Intelligent Internet](https://ii.inc). Given a question, it autonomously searches the web, visits and reads pages, reflects on intermediate findings, and synthesizes a comprehensive final answer with references — the same workflow a human researcher would follow, fully automated. It ships as a complete, self-hostable stack: a Python library and CLI, a streaming FastAPI backend, a Next.js web UI, and an MCP server that plugs directly into Claude and other MCP-compatible clients. For the design story and evaluation details, read our [blog post](https://www.ii.inc/web/blog/post/ii-researcher). ## ✨ Features - 🔍 **Intelligent web search** with pluggable providers (Tavily, SerpAPI, Jina) - 🕸️ **Web scraping and content extraction** with multiple providers (Firecrawl, Browser, BeautifulSoup, Tavily Extract, Jina), including PDF and YouTube handling - 🧠 **Multi-step reasoning and reflection** — the agent thinks, acts, and self-corrects until it has enough evidence - 🗜️ **Context compression** — embedding-based and LLM-based compressors keep long pages within the model's context window - ⚙️ **Model-agnostic** via LiteLLM — run OpenAI, DeepSeek, Gemini, OpenRouter, or any OpenAI-compatible endpoint (including self-hosted models) - ⚡ **Fully asynchronous** with token-level streaming end to end (CLI, SSE API, and web UI) - 📝 **Referenced report generation** with selectable `basic` and `advanced` report types and multilingual support - 🔌 **MCP server** for one-line integration with Claude Desktop and other MCP clients - 🧱 **Structured outputs** powered by [BAML](https://github.com/BoundaryML/baml) ## 📊 Benchmarks We benchmarked II-Researcher on the [Frames dataset](https://huggingface.co/datasets/google/frames-benchmark/viewer/defa
Excerpt of 13,786 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:49bc4c55118a949d, topic:agents, topic:agentic-ai, topic:agentic-workflow