VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Open-source models for financial risk detection and fraud analytics

**Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.

1.1

The summary of code and paper for unified model towards context-dependent (CD) concept segmentation.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk

公募REITs专属AI多智能体查询分析平台

A database operations and data analysis AI agent

Easiest and laziest way for building multi-agent LLMs applications.

FreqMod Spline Network : Frequency Spline Networks for Burst Image Separation

💯 Perfecting AI workflows with human intelligence

Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

A project aims to improve LLMs' pixel reasoning ability.

ScreenCoder — Turn any UI screenshot into clean, editable HTML/CSS with full control. Fast, accurate, and easy to customize.

❓Curie: Automated and Rigorous Scientific Experimentation with AI Agents

NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation

A lightweight, elegant, and performant in-memory cache written purely in Swift

NetworkConnectivityKit is a lightweight Swift library for testing network connectivity using multiple validation methods.

Python library for the Tessera embeddings

Tensor-Var: Efficient four-dimensional variational data assimilation

The code for TPAMI paper "Text-Guided Human Image Manipulation via Image-Text Shared Space"

semqreg package

Klavis AI (YC X25): MCP integration layers that let AI agents use thousands of tools reliably.