UditAkhourii/adhd: A Tree-of-Thought Skill for AI Coding Agents
The UditAkhourii/adhd repository introduces a TypeScript-based skill for AI coding agents, implementing a tree-of-thought approach with pruning. It is designed to facilitate parallel divergent thinking and ideation, leveraging the Claude & Codex Agent SDK. This tool aims to enhance creative and interdisciplinary work by systematically exploring and refining multiple cognitive frames.
Herdr: A Terminal-Based Agent Multiplexer for AI Development
Herdr is a terminal-based agent multiplexer designed to manage and orchestrate AI agents directly within the command line interface. Written in Rust, it provides a unified environment for developers working with AI agents, offering features akin to traditional terminal multiplexers like tmux but tailored for AI workflows. The project has recently seen a fresh release and significant community attention.
AI Engineering From Scratch: A Comprehensive Learning Resource
The `rohitg00/ai-engineering-from-scratch` GitHub repository offers a comprehensive learning resource for AI engineering, covering topics from machine learning to generative AI and agents. With a recent release and substantial community engagement, it aims to guide users through building and deploying AI solutions. The project is primarily written in Python and includes a `requirements.txt` file for dependency management.
WMUX: A Workspace Multiplexer for AI Agents
WMUX is a TypeScript-based workspace multiplexer designed for AI agents, facilitating browser automation and multi-agent operations. It integrates with various AI models like Claude and Gemini, offering a structured environment for AI-driven development tasks. The project recently received an update, indicating active development.
Cindy: An Open-Source, Out-of-the-Box AI Agent for Multiple Platforms
The `makecindy/cindy` GitHub repository introduces an open-source AI agent designed for immediate use across various operating systems. This TypeScript-based project aims to provide an "out-of-the-box" solution for AI agent functionalities, supporting platforms like Android, iOS, macOS, and Windows.
Orca: An Agent Development Environment for Parallel AI Agents
Orca is an Agent Development Environment (ADE) designed for managing and orchestrating a fleet of parallel AI agents. It enables users to run various coding agents with their own subscriptions and is available across desktop, mobile, and Virtual Private Server (VPS) platforms. The project has recently seen a fresh release, indicating active development.
jcode: An Intelligent Agent Harness for Code in Rust
jcode is a Rust-based project described as "the most intelligent agent harness for code," designed to facilitate AI-driven coding tasks. It has recently seen a new release, v0.54.4, indicating active development and maintenance. The project integrates with large language models like OpenAI and Claude, offering a command-line interface (CLI) and terminal user interface (TUI) for developers.
artokun/comfyui-mcp: A Local-First, Agent-Native Control Plane for ComfyUI
The `artokun/comfyui-mcp` project introduces a local-first, agent-native control plane for ComfyUI, integrating an MCP server with a Claude Code plugin. It offers 108 tools and 29 AI skills, enabling users to author and run workflows, edit live graphs using natural language, and manage models and custom nodes. The project supports local, LAN, VPS, or Comfy Cloud deployments.
nexu-io/open-design: An Open-Source, Local-First AI Design Engine
The `nexu-io/open-design` project offers an open-source, local-first desktop application designed as an alternative to proprietary AI design tools. It enables coding agents to generate various design assets, including prototypes, landing pages, dashboards, slides, images, and video, with export options to HTML, PDF, PPTX, and MP4.
PageIndex: Vectorless, Reasoning-based RAG Document Index
PageIndex is a Python-based document indexing system designed for vectorless, reasoning-based Retrieval-Augmented Generation (RAG). It focuses on enhancing information retrieval for AI agents.
FailproofAI: Runtime Failure Resolution for Coding Agents
FailproofAI is a TypeScript-based npm package designed to provide runtime failure resolution for coding agents. It aims to catch loops, dangerous actions, and secret leaks before they cause incidents, operating with zero latency and running locally.
Moltis: A Secure, Self-Hosted Personal Agent Server in Rust
Moltis is a secure, persistent personal agent server built in Rust. It offers sandboxed execution, supports multiple LLM providers, and integrates with various communication platforms like Telegram, WhatsApp, and Discord. Designed for self-hosting on user hardware, it emphasizes security and ease of deployment with a single binary.
Deuz-SDK: TypeScript Framework for Production AI Agents
Deuz-AI has released Deuz-SDK, a zero-dependency TypeScript framework designed for building production-ready AI agents. It offers features like durable execution, long-term memory, hybrid RAG, and a unified streaming API for multiple LLMs.
CowAgent: Open-Source AI Assistant and Agent Harness
CowAgent is an open-source AI assistant and agent harness designed for planning tasks, running tools, and self-evolving with memory. It supports multiple models and channels, offering a lightweight and extensible solution.
automagik-dev/genie: A CLI Agent for Automated Pull Request Generation
automagik-dev has introduced Genie, a new CLI agent designed to automate the process of generating pull requests. This agent interviews users, plans development tasks, dispatches parallel agents in isolated worktrees, and reviews code before presenting it to the developer. It aims to streamline the development workflow by handling the initial stages of code creation and review.
Home Assistant Generative Agent for Natural Language Interaction
A new AI agent for Home Assistant, `home-generative-agent`, enables users to interact with their smart homes using natural language. It supports creating automations, analyzing camera feeds with face recognition, and receiving proactive anomaly alerts, with options for both cloud LLMs and local processing via Ollama.
Agent-Inspect: Local Execution Trees for TypeScript AI Agents
Agent-Inspect is a new GitHub project designed for TypeScript/Node.js developers to understand and debug AI agent runs locally. It visualizes manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata as readable execution trees directly in the terminal.
DecapodLabs Introduces Decapod: A Repo-Native Governance Kernel for AI Agent Graphs
DecapodLabs has released Decapod, a new repo-native governance kernel designed to translate natural-language intent into structured execution and verifiable work across AI coding agent graphs. Written in Rust, Decapod aims to provide enriched context and bounded execution for AI agents, enhancing their reliability and control within development workflows.
Juspay's Neurolink: A TypeScript Interface for 24+ LLM Providers
Juspay has open-sourced Neurolink, a TypeScript interface designed to simplify integration with over 24 large language model (LLM) providers. It aims to enable developers to swap between different LLM providers without extensive code rewrites, offering features like voice capabilities, RAG, memory, and file processing.
Agentlas-OS: A Local-First Agent Operating System for AI Builders
Agentlas-OS is a newly released GitHub project that provides a local-first operating system for AI agents. It is designed to manage specialist agents within a central hub and dynamically deploy temporary orchestrators for specific tasks, supporting various AI models.
Multi-Agent Investment Research Framework for A-share Market
The `simonlin1212/TradingAgents-astock` repository presents a multi-agent investment research framework specifically adapted for the A-share market. It integrates seven AI analysts that engage in debate and decision-making based on A-share market rules, leveraging data sources such as Dragon Tiger List, institutional investor activities, and解禁 (lifting of trading restrictions). The project is built upon a deep modification of the `TradingAgents` framework, tailored for the Chinese A-share market.
TradingAgents-astock: A Multi-Agent Investment Research Framework for A-share Market
TradingAgents-astock is an open-source multi-agent investment research framework designed for the A-share market. It adapts the original TradingAgents framework to incorporate A-share specific data sources and rules, featuring seven AI analysts that engage in debate and risk assessment for decision-making.
Rampart: An Open-Source Firewall for AI Agents
Rampart is an open-source firewall designed for AI agents, providing a policy engine to audit and control the actions of AI tools like OpenClaw, Claude Code, Cursor, and Codex on a user's machine. Developed in Go, this project aims to enhance the security and control over AI agent operations by enforcing predefined policies.
ECC: Agent Harness Performance Optimization System for AI Code Generation
The `affaan-m/ECC` GitHub repository presents an agent harness performance optimization system designed for AI code generation tools like Claude Code, Codex, Opencode, and Cursor. It focuses on integrating skills, instincts, memory, and security into a research-first development approach. The project has recently seen a new release, indicating active development.