Answer me with HTML v0.4.7 Released
The "Answer me with HTML" agent skill, version v0.4.7, has been released. This JavaScript project aims to answer complex questions using a single-page HTML document.
Rome OS: Compounding Agent OS
Rome OS is a compounding agent operating system designed for recursive agents. It positions itself as an open-source alternative to platforms like Grok Bot and Meta's Muse, built with TypeScript.
Hippo Memory v1.57.0: AI Agent Memory with Self-Correction
Hippo Memory v1.57.0 introduces an AI agent memory system that learns from errors, preventing repetition. It utilizes a local SQLite store and MCP server for persistence and integrates with various AI coding tools.
Loopx Project Releases Latest Version
The Loopx project has released its latest version, featuring a control plane with a durable state kernel designed for long-horizon agents and teams. This update aims to maintain workflow progress and improvement across sessions with reduced human oversight.
BrowserOS: Open-Source Agentic Browser
BrowserOS is an open-source agentic browser designed as an alternative to platforms like ChatGPT Atlas and Perplexity Comet. It supports multiple operating systems and integrates with various LLM providers.
Vestige v4.1.0: AI Agent Memory and Security Kernel
Vestige, a Rust-based project, has released version 4.1.0, introducing its memory and security kernel for AI agents. The update focuses on Strata, a signed append-only log, and Operator Lite, a GuardFall-proof gate.
DSPy Framework for TypeScript - Latest Release
The ax-llm/ax repository provides the DSPy framework for TypeScript, with its latest release, version 24.0.24, published on September 27, 2026. This framework is designed for building AI applications using large language models.
Motita: Pure Go Autonomous CLI Agent with Deterministic Validation
Motita is a new autonomous CLI agent built entirely in Go, featuring a unique three-layer architecture that separates task proposal, execution, and validation. This design ensures that tasks are only declared complete after a deterministic anchor, implemented by the user's code, verifies the outcome.
new-acad: AI Agent for AutoCAD/Civil 3D
The new-acad project introduces an in-app AI agent for AutoCAD and Civil 3D, integrating LLM capabilities directly into the CAD environment. It offers a palette for natural language interaction and provides access to over 270 MCP tools and 390+ plugin methods for complex engineering tasks.
Open Source AI Radar: AI Project Intelligence Platform
Open Source AI Radar is a new intelligence platform designed to discover and analyze emerging open-source AI projects on GitHub. It utilizes a three-axis scoring system (Impact, Velocity, Health) to identify projects gaining importance, moving beyond simple star counts.
Servosity Releases Open-Source MSP AI Skills Toolkit
Servosity has released msp-skills, an open-source toolkit enabling AI models like Claude and ChatGPT to interact with Managed Service Provider (MSP) tools. The toolkit offers local-first data processing and includes connectors for PSA, RMM, backup, and M365 applications.
kernelCAD v0.17.0: Agent-Native CAD with Editable Source
kernelCAD has released version 0.17.0, introducing an agent-native CAD system where designs are defined by editable TypeScript source code. This approach emphasizes a source-first workflow, enabling deterministic validation and revision processes.
DSH Blender Plugin v2.1.0 Realtime AI Integration
The DSH x Blender direct realtime plugin has been updated to v2.1.0, enabling an AI to drive Blender via a direct TCP channel. This integration offers 16 tools, 28 families, and 186 operations, including viewport frames and click-to-pick functionality.
Harn v0.10.167: AI Agent Programming Language & Runtime
Harn has released version v0.10.167, introducing updates to its programming language and runtime specifically designed for building AI agents. This Rust-based project aims to provide developers with a dedicated environment for agent development.
Apache Maka v0.2.1-dev.85.20261014 Released
Apache Maka, an incubating Apache project, has released version v0.2.1-dev.85.20261014. This high-performance agent workspace is built with TypeScript and focuses on maintaining a complete record of agent actions.
Tiangong: Rust + Tauri AI Desktop Terminal
Tiangong is a desktop AI terminal built with Rust and Tauri. It features an embedded browser for human-computer collaboration, multi-agent coordination, long-term memory, scheduled tasks, and a plugin ecosystem supporting WASM, TypeScript, and pure UI. The terminal can be remotely controlled via WeChat, QQ, and Lark.
SwarmAI Agent OS v2.3.0 Released
SwarmAI, a self-evolving Agent OS, has released version 2.3.0. This Python-based project focuses on self-evolution, persistent cognition, and proprioception for AI agents, with human direction and AI delivery.
Dodaios AI Assistant v3.2.0 Released
Dodaios, an open-source AI assistant designed for the agentic era, has released version 3.2.0. This local assistant supports Windows, macOS, and Linux, enabling users to interact with agents, coding CLIs, browsers, and applications via voice commands.
Buddy Android: Floating Chat Bubble for AI Phone Control
Buddy Android is a floating chat bubble application that enables AI models like Claude Code, Codex, or OpenCode to interact with and control an Android phone. It operates directly within the app, supporting both paid and free AI models without requiring ADB, a PC, or root access.
Moli v1.1.17: Headless Browser for AI Agents
Moli, a Rust-based headless browser, has released version v1.1.17. It is designed for AI agents, emphasizing a lightweight, fast, and highly compatible approach. The project has garnered significant attention with over 18,000 stars on GitHub.
alookai/alook: Rooms for People and Agents
The alookai/alook repository provides a framework for creating "rooms" designed for collaboration between people and AI agents. It is built using TypeScript and has recently seen a new release, v0.1.51.
Unmute: Voice Agents in YAML
Unmute is a Go-based project that allows developers to define voice agents using YAML. These definitions are then compiled into production-ready code for platforms like Pipecat or LiveKit, enabling deployment anywhere.
Spec-Kitty v4.0.0rc6: Spec-Driven AI Agent Development
Spec-Kitty has released v4.0.0rc6, a Python project focused on spec-driven development for AI agents. It aims to enforce organizational governance and consistent engineering standards through git-native missions and enforceable workflows.
Happy: Orchestrate Claude, Codex, Grok
Happy is an open-source application designed to orchestrate AI models like Claude, Codex, and Grok. It allows users to leverage existing subscriptions for these services. The project recently released version cli-1.2.6-beta.1.