Stars
A markdown native slides tool for academics building with agents.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
The World's First Unified Virtual Filesystem For AI Agents
An Evaluation Framework for Web Search APIs
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on …
jdr - SOTA performance on "DeepSearch" benchmarks in < 1500 lines of code
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Code for steering and monitoring with concepts vectors in LLMs (initial draft)
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
Expand -> Retrieve -> Rerank - simple method with strong results on BRIGHT benchmark
Search, understand, reproduce, and improve an idea with ease
CodeScientist: An automated scientific discovery system for code-based experiments
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
II-Researcher: a new open-source framework designed to aid building search / research agents
II-Agent: a new open-source framework to build and deploy intelligent agents
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
A library for making RepE control vectors
[ICLR 2025] General-purpose activation steering library
A library for mechanistic interpretability of GPT-style language models
Representation Engineering: A Top-Down Approach to AI Transparency
Exploring Applications of GRPO
A playbook for systematically maximizing the performance of deep learning models.
This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.