DeepCode: An Open Agentic Coding System That Turns Papers Into Code DeepCode from the Data Intelligence Lab at The University of Hong Kong (HKUDS) is an open agentic coding system that turns research papers and natural language requirements into working code. It aims ... agents code-generation HKU MCP Paper2Code Python RAG research-reproduction Streamlit
M3-Agent: A Multimodal Agent with Long-Term Memory The quest to create agents that can interact with the world as seamlessly as humans is on the horizon. But a significant hurdle has been equipping AI with the ability to form and recall long-term memo... AI ByteDance Long-Term Memory M3-Agent Multimodal Agent Open Source
ScreenEnv: Desktop Automation and AI Agent Development Building robust AI agents that interact with desktop applications has always been challenging. Virtual machines are cumbersome, and traditional automation scripts often break with the slightest system... AI agents desktop automation Docker GUI automation Hugging Face open source Python
LangChain and LangGraph Enter v1.0 Alpha: A New Era for Agentic AI Development The AI community has reason to be excited as LangChain and LangGraph achieve their 1.0 alpha milestone in both Python and JavaScript. These open-source platforms are redefining how developers build ad... agent orchestration AI agents developer tools JavaScript LangChain LangGraph open source Python
Agent Client Protocol: Making Agentic Editing Portable The Agent Client Protocol (ACP) is an open effort by Zed Industries to standardize how code editors talk to AI coding agents. If the Language Server Protocol decoupled languages from editors, ACP aims... ACP AI Agents Code Editors JSON-RPC MCP Open Source Rust TypeScript
Plausible Analytics: Privacy-first Web Analytics You Can Actually Understand Plausible Analytics is a lightweight, open-source alternative to Google Analytics built around privacy, simplicity, and speed. The core app lives in plausible/analytics and powers both the company’s m... analytics clickhouse elixir open source plausible privacy
GitHub Copilot Vulnerability: How Prompt Injection Opened the Door to RCE Attacks A critical vulnerability in GitHub Copilot , identified as CVE-2025-53773 exposed developers to remote code execution (RCE) and full system compromise, all triggered by malicious prompt injection with... AI security cybersecurity developer tools GitHub Copilot Microsoft prompt injection remote code execution vulnerability
Hermes 4: Open-Source AI Rivaling Industry Leaders Without Content Limits Hermes 4, the latest innovation from Nous Research is an open-source AI project gaining traction by setting new standards and outperforming popular systems like ChatGPT while removing the content rest... AI benchmarks AI training content moderation Hermes 4 language models open-source AI user control
Claude Code in the Terminal: An agent that reads your repo and ships PRs Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you ship faster by explaining complex code, drafting changes, and handling git workflows through...
The Python Reflex Web Framework In the ever-evolving world of software development, the line between different programming domains is constantly blurring. Data scientists are building dashboards, machine learning engineers are deplo... Open Source Python web development
Gabber: The Visual Builder Revolutionizing Real-time AI Applications Building real-time AI applications that can simultaneously process voice, video, text, and multiple data streams has traditionally required extensive expertise across numerous domains. Enter Gabber , ... AI Multi-modal AI Node-based Development Open Source Real-time Visual Programming WebRTC
Pruning LLMs With Regional Gradients: Inside Wanda++ Large language models are hard to deploy because memory and latency balloon with scale. In Findings of the Association for Computational Linguistics: ACL 2025, Yifan Yang and colleagues from the Unive... AWQ Quantization Fine Tuning Large Language Models LLaMA Model Compression Model Pruning OpenLLaMA Regional Gradients Semi-Structured Sparsity Sparsity TensorRT Wanda++