Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

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

Open-source orchestration for zero-human companies

A set of ready to use scientific skills for Claude

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.

Suna - Open Source Generalist AI Agent

AgentEvolver: Towards Efficient Self-Evolving Agent System

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

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.

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

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

Agent Zero AI framework

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

AgentFlow: In-the-Flow Agentic System Optimization

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

Biomni: a general-purpose biomedical AI agent

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