Search

Structured execution traces for LLM debugging – lets AI coding tools see runtime behavior instead of guessing

simple blender MCP tool for agents to create 3d models in blender with screen shot support

Voice-driven AI Agent gateway framework | 声音驱动的 AI Agent 语音网关框架

Bert is designed as a reliable CLI Framework for you to use the sharpest Decoder models In this 2026.

Native MCP client plugin for OpenClaw — connect to any MCP server and use its tools natively

Create VS Code Chat participants (agents) with LangChain/LangGraph: tool-calling and streaming bridge for LanguageModelChat.

✨ AI-powered Obsidian plugin — 20 tools, Magic Write, agentic loops, vault diagnostics. Claude actually touches your vault.

Human-on-the-Loop AI Automation Framework - AI agents with 70-90% autonomy and human escalation for edge cases

Build a minimal Claude-style AI agent from scratch that processes messages, interacts with tools, and generates dynamic responses.

🛠️ Build a collaborative framework for pricing strategies using AI, enhancing decision-making through real-time data analysis and human insight.

A powerful and efficient AI virtual co-worker framework built on top of BitNet's 1-bit quantized language models.

🌳 Graduated AI assistance framework for Claude Code - prevents skill atrophy while coding with AI through 4 levels of structured collaboration

Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.

An AI-powered tool that fetches and summarizes the latest financial news for any public company using AI Agent

Terminal coding agent in Rust — single binary, any LLM, offline-capable. MCP support, 11 built-in tools, session resume.

AI-Native CLI design spec — 98 rules for building CLI tools that AI agents can safely use. Agent Skills compatible.

Agent-ready PHP component framework for admin dashboards. Zero dependencies, Material Design 3, AJAX-first. 17+ components, 1 CSS + 1 JS file.

AI companion framework with persistent memory, inner life, and continuity. 58 phases of proof that it works on a gaming PC.

🔒 Automate detection and exploitation of Agent-Specific Injection vulnerabilities using the OWASP Top 10 framework for AI agent security testing.

Prototype of an intelligent research agent capable of literature retrieval, summarization, and contextual reasoning — a foundation for scientific automation tools.