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.
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.
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.
Uniterm v1.10.0: All-in-One Terminal with AI Agent
Uniterm has released version 1.10.0, an all-in-one terminal application supporting over 30 protocols including SSH, RDP, SFTP, and Kubernetes. It features a built-in AI Agent capable of autonomously executing multi-turn shell commands.
Paperclip AI: Open-Source Agent Management Tool
Paperclip is an open-source application designed for managing AI agents at work, written in TypeScript. It recently had a fresh release, v2026.1005.0, indicating active development.
Teable AI Spreadsheet for Business
Teable is an open-source AI spreadsheet designed for business use, offering a low-code/no-code platform. It recently had a fresh release, indicating active development.
ToolUniverse v1.5.6: AI Scientists with Tool Use
ToolUniverse, a Python project focused on democratizing AI scientists, has released version v1.5.6. This project emphasizes AI agents capable of scientific skill and tool use.
Cocoindex Incremental Engine v1.0.24
Cocoindex has released version v1.0.24 of its incremental engine for long horizon agents. This Rust-based project focuses on agentic data frameworks and AI.
HunterCode Community Edition v1.4.0 Released
HunterCode Community Edition has released version 1.4.0, offering an open-source, local alternative to Tencent WorkBuddy Finance Edition. This multi-agent investment research terminal runs AI inference locally, ensuring data privacy.
claude-mem: Persistent Context for AI Agents
The claude-mem project provides persistent context across sessions for AI agents. It captures agent interactions, compresses them using AI, and reintroduces relevant context into future sessions. This system supports a range of AI models including Claude Code, Gemini, and Copilot.
CareerOps AI Job Search Agent
CareerOps is an open-source AI job search agent designed to run locally within your AI coding CLI. It scans job portals, evaluates listings, tailors your CV, and tracks applications, with its latest release being web-v0.12.0.
Felix: Self-Hostable Managed Agents Harness
Felix is a self-hostable agents harness that allows users to author agents via YAML manifests. These manifests are compiled into governed agents with features like durable fibers, memory, skills, evaluation, approvals, and sandboxes, supporting multiple LLM backends. The system is designed for flexible deployment across Docker, Helm, AWS, or GCP.
Ficus Tau: Workspace for Teams of AI Agents
Ficus Tau is a new open-source workspace designed for managing teams of AI agents. It offers self-hosted deployment with an optional cloud service, allowing agents to coordinate tasks, track progress, and interact with tools and services.
BrainLayer Adds Persistent Memory to AI Agents
BrainLayer introduces a persistent memory system for AI agents, enabling them to retain information across conversations. It utilizes SQLite for storage, a knowledge graph for relationships, and offers a suite of tools for memory management and retrieval.
PI-Desktop: Local-First AI Coding Agent Workspace
PI-Desktop is a new, local-first desktop application designed to provide AI coding agents with a persistent and extensible workspace. It supports model-agnostic workflows, user-installable plugins, and advanced agent orchestration capabilities.
OpenMake LLM v1.99.0: Self-Hosted AI Workspace
OpenMake LLM has released version v1.99.0, offering an open-source, self-hosted AI workspace for local and open-weight LLMs. It integrates vLLM, LiteLLM, and autonomous agents, supporting the Model Context Protocol (MCP).
Mezmo AURA v0.2.19: Production-Ready SRE Agent Platform
Mezmo's AURA, a production-tested SRE agent platform, has released version v0.2.19. Written in Rust, AURA is designed to handle guardrails, APIs, state management, and failure handling for AI in production infrastructure.
PhysiClaw AI Agent for Phone Operation
PhysiClaw is a Python-based AI agent designed to physically operate a smartphone, mimicking human interaction. It recently released version physiclaw-hardware-v0.38, indicating active development.
DeepSeek Harness Integrates ChatGPT/Codex via OAuth
The dsh-codex-subscription project enables the use of ChatGPT and Codex subscriptions with DeepSeek Harness through OAuth. This integration provides model access, usage quotas, search capabilities, and image generation without requiring separate API keys or a Codex CLI.
pi-goal-list-loop-audit: Enhanced AI Agent Supervision
DraconDev has released pi-goal-list-loop-audit (GLLA), a pi-coding-agent extension designed to supervise long-running autonomous tasks. GLLA enhances durability, recoverability, and evidence-backed completion by implementing an isolated auditor for each task's completion.
Droid AI Toolkit for Android via Termux
The Droid AI Toolkit enables running various AI tools, including OpenClaw, Ollama, and n8n, natively on Android devices through Termux. It addresses Android-specific limitations and optimizes performance for mobile environments.
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Researchers have introduced ScienceIDE, an infrastructure designed to transform scientific code repositories into programmable environments for AI agents. This system aims to overcome the 'scientific experience bottleneck' by enabling agents to generate, execute, and verify scientific tasks, facilitating agent learning and scientific practice.