Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

ICLR 2025 paper: 3DMolFormer: A Dual-channel Framework for Structure-based Drug Discovery

Official code for "Self-Distilled Agentic Reinforcement Learning"

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

SDE-Harness (Scientific Discovery Evaluation Framework)

Paper list of agent for science

Python and JavaScript bindings for calling the Earth Engine API.

Protein reasoning foundation models for drug discovery.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Official repository of "ODesign: A World Model for Biomolecular Interaction Design"

The agent that grows with you

BioReason-Pro: Advancing Protein Function Prediction with Multimodal Biological Reasoning

Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation

OpenClaw-RL: Train any agent simply by talking

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

Single-stage End-to-End Training for Tokenization and Generation

The absolute trainer to light up AI agents.

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution