Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

A set of ready to use scientific skills for Claude

AgentEvolver: Towards Efficient Self-Evolving Agent System

A curated collection of automated research tools, covering literature search, paper reading, experiment management, and code generation to help researchers accelerate their workflow.

The first open-source all-in-one AI productivity platform

Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824

Biomni: a general-purpose biomedical AI agent

Open-source orchestration for zero-human companies

AI agents running research on single-GPU nanochat training automatically

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Agent Zero AI framework

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460. Any other account is fake.

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

让自动化AI科研只剩最后一块拼图

AgentFlow: In-the-Flow Agentic System Optimization

deep research. Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"