SakanaAI / AI-ScientistLinks
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
☆11,654Updated 6 months ago
Alternatives and similar repositories for AI-Scientist
Users that are interested in AI-Scientist are comparing it to the libraries listed below
Sorting:
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search☆1,709Updated last week
- Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your resea…☆5,040Updated 2 months ago
- SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersec…☆17,657Updated this week
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆20,547Updated 7 months ago
- High accuracy RAG for answering questions from scientific documents with citations☆7,767Updated last week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,861Updated last week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆17,979Updated this week
- 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation☆18,253Updated last month
- PyTorch native post-training library☆5,564Updated this week
- TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.☆3,027Updated 3 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆14,648Updated last week
- Train transformer language models with reinforcement learning.☆16,012Updated this week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆28,915Updated this week
- DSPy: The framework for programming—not prompting—language models☆29,488Updated this week
- Sky-T1: Train your own O1 preview model within $450☆3,345Updated 3 months ago
- Minimal reproduction of DeepSeek R1-Zero☆12,317Updated 6 months ago
- Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)☆4,953Updated 3 weeks ago
- Knowledge Agents and Management in the Cloud☆4,190Updated last week
- g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains☆4,224Updated last month
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.☆47,355Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆60,980Updated this week
- [NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat☆3,364Updated 2 weeks ago
- llama3 implementation one matrix multiplication at a time☆15,180Updated last year
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆9,043Updated this week
- Vision agent☆5,086Updated 2 months ago
- Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.☆41,695Updated this week
- [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models☆5,632Updated 9 months ago
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,727Updated 3 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆19,900Updated this week
- s1: Simple test-time scaling☆6,585Updated 4 months ago