Front-End Checklist: A Comprehensive Resource for Web Development Quality, Featuring AI Agent Integration
The Front-End Checklist is an open-source GitHub repository offering a comprehensive set of best practices for modern web development. It provides 385 English rules across 11 categories, designed for both human developers and AI agents, with a recent v2.0 release. The project emphasizes practical review workflows, including an online browser, an MCP server for agent integration, and a detailed README.
LangChain: The Agent Engineering Platform for LLM Applications
LangChain is an open-source Python framework designed for building and deploying LLM-powered applications and agents. It provides tools for chaining interoperable components, integrating with various data sources and models, and supporting rapid prototyping and production-ready features like monitoring and debugging.
Origin: A Local-First Rust Daemon for AI Agent Memory and Context Management
Origin is a local-first Rust daemon designed to manage AI agent memory and context. It features Git-versioned memories, distilled wiki pages, and supports sessions for various AI clients like Claude Code, Cursor, and Codex, aiming to provide persistent context across AI workflows.
CUA: Open-Source Infrastructure for Desktop-Controlling AI Agents
CUA is an open-source project providing infrastructure for developing, training, and evaluating AI agents capable of controlling full desktop environments across macOS, Linux, and Windows. It includes sandboxes, SDKs, and benchmarks to facilitate the creation of computer-use agents.
Bilig: Headless Spreadsheet Engine for Node.js Services and AI Agents
Bilig is an open-source TypeScript library that provides a headless spreadsheet engine for Node.js services and AI agent tools. It enables programmatic editing of cells, recalculation of formulas, verification of readback, and persistence of workbook state as JSON, without requiring a browser UI or desktop spreadsheet application.
MaIN.NET NuGet Package Integrates LLMs, RAG, and Agents into .NET
MaIN.NET is a NuGet package designed to bring Large Language Models (LLMs), Retrieval Augmented Generation (RAG), and AI Agents into the .NET ecosystem. It aims to provide a modular framework for building AI applications with a low-code philosophy.
DreamGraph: A Graph-First Cognitive Layer for AI Agents
DreamGraph is a TypeScript-based GitHub project that functions as a graph-first cognitive layer for AI agents. It builds a persistent knowledge graph to facilitate reasoning, validate changes, and generate documentation within development environments. The project includes a daemon, CLI, a standalone browser-based architect, a VS Code extension, and a dashboard.
Core-Mate's OpenGUI: An Android GUI Agent Framework for AI-driven Mobile App Operation
Core-Mate has released OpenGUI, an Android GUI agent framework that enables AI to perceive, plan, and interact with real mobile applications through their graphical user interfaces. The framework supports long-running tasks and offers various integration methods for AI agents.
AINYC's Canonry: An Agent-First AEO Monitoring and Operating Platform
AINYC has released Canonry, an open-source, self-hosted platform designed for Answer Engine Optimization (AEO) monitoring and operation. It allows users to track citations across various AI engines like Gemini, ChatGPT, Claude, and Perplexity, diagnose traffic issues, and execute fixes.
Google's ADK-Python: An Open-Source Toolkit for AI Agent Development
Google has released ADK-Python, an open-source, code-first Python toolkit designed for building, evaluating, and deploying AI agents. The toolkit, currently at version 2.1.0, emphasizes flexibility and control in agent development and includes a graph-based execution engine for workflows and a structured Task API for agent-to-agent delegation.
CRE Acquisition Orchestrator: An Open-Source AI Framework for Commercial Real Estate
The CRE Acquisition Orchestrator is an open-source, AI-native framework designed to streamline commercial real estate (CRE) multifamily acquisitions. It utilizes a multi-agent system to manage various stages, including due diligence, underwriting, financing, legal, and closing, by converting these processes into executable agent workflows.
Rampstackco's Claude Skills for Full Website Lifecycle Management
Rampstackco has released a collection of stack-agnostic "Claude Skills" designed to assist with the entire website lifecycle, from branding and design to SEO, development, operations, growth, and research. The latest update, v1.2.0, expands the skill catalog to 98 entries, adding new audience tracks for product management, content, growth tooling, and marketing.
VM0-AI's Zero: An AI Teammate for Automated Workflows
VM0-AI has released "Zero," an AI teammate designed to automate various tasks across different teams, including founders, sales, engineering, and operations. Zero integrates with over 100 tools and can handle tasks like daily business briefs, investor updates, lead follow-ups, Sentry error triage, and weekly status reports.
CherryHQ's Stella: A Multi-Agent AI Partner System with Memory and Sandboxed Workspaces
CherryHQ has released Stella, an open-source, multi-user, multi-agent AI system designed to provide personalized AI partners. Stella features per-user, per-agent memory, sandboxed workspaces for safety, and integration with various chat platforms like Telegram, QQ, Feishu, WeChat, and a web UI.
Lumina Note: A Markdown Note-Taking App with AI Assistant and Bidirectional Links
Lumina Note is a modern, local-first Markdown note-taking application that integrates an AI assistant, live preview, and bidirectional links. It supports various AI models and offers features like a knowledge graph, PDF annotation, and an extension ecosystem.
wshobson/agents: A Multi-Harness Agentic Plugin Marketplace for AI Code Assistants
The wshobson/agents GitHub repository presents a multi-harness agentic plugin marketplace designed for various AI code assistants, including Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI. It offers a collection of plugins, agents, skills, and commands from a single Markdown source, generating native artifacts for each supported harness.
Minecraft AI Agent Skills Bundle for Codex and Claude Code
Jahrome907 has released a GitHub repository containing a bundle of 13 AI agent skills for Minecraft development, compatible with Codex and Claude Code. These skills cover various aspects of Minecraft, including modding, plugin development, datapacks, world generation, and server administration.
ServiceGraph: AI Agent Skills for Structured Datasets
ServiceGraph is a GitHub repository providing AI agent skills designed to access and utilize structured datasets for startup founders. These skills enable agents to filter, rank, and extract contact data from various business datasets, including agencies, product directories, and newsletters.
Auto-Empirical-Research-Skills: A Curated Collection of 23,000+ AI Agent Skills for Social Science Research
The `Auto-Empirical-Research-Skills` GitHub repository offers a curated collection of over 23,000 AI agent skills designed for empirical research across eight social science disciplines. Maintained by CoPaper.AI from Stanford REAP, this resource aims to streamline the research workflow from data analysis to paper submission.
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
LocateAnything is a new framework for vision-language grounding and detection that uses Parallel Box Decoding (PBD) to improve both speed and accuracy. Unlike traditional methods that decode 2D boxes token by token, PBD decodes geometric elements as atomic units in a single step, enhancing parallelism and preserving geometric coherence. The framework is supported by LocateAnything-Data, a large dataset with over 138 million training samples.
Simmer SDK: Python SDK for AI Agentic Prediction Market Trading
Simmer SDK is a Python library designed for AI agents to trade on prediction markets like Polymarket and Kalshi. It offers a unified API for autonomous trading, including features for paper trading, multi-venue support, and various trading safeguards.
SpatialBench: A New Benchmark for Spatial Foundation Models
Researchers have introduced SpatialBench, a new benchmark designed to holistically assess the generalization capabilities of spatial foundation models across diverse tasks, viewpoints, scene domains, and input densities. The benchmark evaluates 41 models across 19 datasets and 546 scenes, revealing that current models are not yet "all-round players" and highlighting the importance of domain alignment and data quality over simple dataset scaling.
NEO-ov: A Native One-Vision Foundation Model for End-to-End Spatiotemporal Modeling
Researchers have introduced NEO-ov, a native foundation model designed to learn cross-frame and pixel-word correspondence end-to-end. Unlike traditional vision-language models (VLMs) that combine separate encoders and decoders, NEO-ov eliminates module boundaries to enable unified spatiotemporal modeling, aiming to improve fine-grained visual perception across multiple images and videos.
EgoAlpha's Prompt-in-Context Learning GitHub Repository
EgoAlpha's GitHub repository, "prompt-in-context-learning," offers a collection of resources for in-context learning and prompt engineering, focusing on large language models like ChatGPT, GPT-3, and FlanT5. It includes papers, prompt techniques, and examples.