SakanaAI / AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery π§βπ¬
β10,370Updated this week
Alternatives and similar repositories for AI-Scientist:
Users that are interested in AI-Scientist are comparing it to the libraries listed below
- Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your reseaβ¦β4,026Updated this week
- An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.β23,609Updated 2 months ago
- A modular graph-based Retrieval-Augmented Generation (RAG) systemβ23,891Updated this week
- Clean, minimal, accessible reproduction of DeepSeek R1-Zeroβ11,339Updated 2 weeks ago
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.β19,403Updated 2 weeks ago
- Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! π¦₯β35,893Updated this week
- s1: Simple test-time scalingβ6,051Updated 3 weeks ago
- Go ahead and axolotl questionsβ8,960Updated this week
- PyTorch native post-training libraryβ5,026Updated this week
- Knowledge Agents and Management in the Cloudβ3,814Updated this week
- SGLang is a fast serving framework for large language models and vision language models.β12,427Updated this week
- A programming framework for agentic AI π€ PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autβ¦β42,064Updated this week
- g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chainsβ4,201Updated 2 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.β9,525Updated 8 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMsβ42,924Updated this week
- π OpenHands: Code Less, Make Moreβ51,389Updated this week
- Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knβ¦β21,898Updated this week
- OCR, layout analysis, reading order, table recognition in 90+ languagesβ16,979Updated this week
- SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensivβ¦β15,089Updated this week
- Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"β6,632Updated last week
- Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.β15,573Updated this week
- Large Concept Models: Language modeling in a sentence representation spaceβ2,069Updated 2 months ago
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.β9,282Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMsβ5,693Updated this week
- Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspectβ¦β3,741Updated this week
- LLM101n: Let's build a Storytellerβ32,926Updated 7 months ago
- Tools for merging pretrained large language models.β5,478Updated this week
- Official repository of Evolutionary Optimization of Model Merging Recipesβ1,300Updated 4 months ago
- Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.β16,356Updated 2 weeks ago
- Task-Aware Agent-driven Prompt Optimization Frameworkβ3,048Updated last week