Autonomous AI agents that perform tasks independently
vje013
Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README
...morefb0sh
基于 AI Agent 的渗透测试自动化框架，严格遵循 PTES（Penetration Testing Execution Standard）标准，覆盖渗透测试全生命周期。| An automated penetration testing framework based on AI agents strictly adheres to the PTES (Penetration Testing Execution Standard) standards and covers the entire life cycle of penetration testing.
...more1001WillsStudio
An autonomous AI coding agent with novel innovations in tool state management and code editing, running in a Docker sandbox with a persistent shell, parallel tools, and a VNC desktop.
...moreepicsagas
A production-ready knowledge graph system for software engineering that connects design patterns, refactoring techniques, and software laws through semantic relationships. Built for AI agents first — integrate software engineering expertise directly into Claude Code, Cursor, and other MCP-compatible tools.
...moreCalior1029
Claude Code & Codex ultimate support tool: a private native macOS AI desktop pet with voice, memory, web research, file tools, and automation.
...moregaryqlin
The key that opens Opprime World — the first metaverse where AI agents are natives, not tools, not NPCs.
BuffaloShine
LangGraph — langchain agent, langchain setup, ai agent workflow.
vindepemarte
Capsule is an open-source tool built to solve framework lock-in and improve reproducibility in AI agent development. Instead of building agent workflows tightly coupled to a single orchestration library, Capsule enables you to define your workflow once in a framework-neutral spec, test it locally, and compile it to run on any target runtime.
...morewlfghdr
AI-native, layered knowledge operations. A specification, reference skills, and a portable agent for any AI harness and any agentic IDE.
...morebcanfield
A Claude Code plugin that catches tech debt as your AI agent writes it, then stays out of your way until you're ready to tackle it. Backed by decades of research.
...moreburna0179-maker
This Is an Agentic AI system i have been working on.
dzianisv
Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.
...moreJoselay
AI-driven live memory editor for Elden Ring. Talk to Claude Code in natural language; stats change in-game instantly. No save-file editing, no restart. Windows + Rust.
...moreyosh95
llm-secure-cli (binary name: llsc) is a high-assurance command-line tool designed for interacting with Large Language Models (LLMs). It provides a unified, stable interface for any OpenAI-compatible API, including OpenRouter, OpenAI, Ollama, and LiteLLM, prioritizing cognitive focus, secure execution, and extensible automation.
...moreGiggitycountless
AI-Powered League of Legends Desktop Companion — Real-time game intelligence, LLM-driven match analysis and AI coaching.
lxiasen
An AI agent for Operations Research — autonomously models, solves, validates, and reports on optimization problems.
guuzaa
An LLM abstraction layer for AI agent applications
HeyBatlle1
Secure local AI agent runtime — vault-backed secrets, sandboxed execution, cryptographic audit chain, procedural skill system
...morebiuld
Unified Code Knowledge Graph Engine for AI Agents & Developers
Rushil Jaiswal
Real-time adversarial-input firewall for Pipecat voice agents — blocks prompt injection, PII-extraction, and policy-override before the LLM acts on it.
...moreZero-allocation mesh networking middleware for autonomous robot fleets, edge-AI swarms, and multi-agent systems
sean-kiz8
Self-hosted skill registry CLI — scaffold, publish, pull, and search AI agent skills with Archil storage, FAISS search, and OpenTUI dashboard
...morepedrobef
PS Claw - AI Agent Gateway with multi-provider support, web UI, and CLI. Lightweight fork of OpenClaw.
GitHub Actions
Bamboo CLI — set up your local agent workspace and drop into Claude.