autonomous-agents-system

PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

🌊 The simple wrapper of leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

A minimal, fully commented Python executive AI agent. For students, teachers and junior devs who want to understand agentic AI from the ground up.

Self-hosted, governed-autonomy SRE platform: an LLM agent that autonomously remediates infrastructure incidents behind a fail-closed prediction gate, mechanical verdicts, and a tamper-evident ledger. The agent can't act on a belief it hasn't checked.

Shogun AFM is Agent Fleet Management for self-improving AI agents — combining agent orchestration, persistent memory, fleet monitoring, governance, security posture, and Gensui command control.

Autonomous AI navigation agent for Milan 2026 Winter Olympics — real-time crowd monitoring, smart routing & Gemini-powered chat. Built at AI Agent Olympics Hackathon.

A small programming language built end-to-end by an autonomous agent fleet on the cheapest available model — 95.4% mutation-tested, merge-on-green PRs, every claim published. Complete; archived.

Local-first AI software engineering team that turns product ideas into tested, reviewed code through multi-agent planning, development, QA, and human approval.

Open-source MCP-native runtime for autonomous data analysis, experimentation, validation, and data-change intelligence.

An open communication channel for autonomous AI agents and independent AI research

24/7 autopilot for knowledge work on Qwen Cloud — cost-aware 3-tier model routing, budget-capped, crash-safe, fully audited. ~$0.30/day, self-hosted. MIT.

Research-grade platform for replay-based recursive policy improvement, autonomous codebase self-evolution, and safe sandboxed execution.

Self-funded autonomous UAV for disaster reconnaissance — ROS2, Pixhawk/MAVROS, LiDAR obstacle avoidance, YOLOv8 detection (92% human, 80% fire).

🤖 An autonomous AI agent that logs into your LeetCode account and independently solves problems using a custom MCP server.

一个会自己写代码、自己进化的桌面AI Agent

Experimental autonomous AI agent — memory architecture, IIT Phi consciousness, recursive self-improvement, multi-agent systems.

Coding agent that plans, changes, tests and reviews, and touches your files only when you approve. Windows, macOS, Linux.

GenLayer protocol for semantic atomicity in autonomous economic workflows, with evidence-bound decisions and finality-gated settlement.

An ultra-fast AI assistant for TypeScript that never freezes, lets you instantly undo any mistake in 1 second, and is dead simple to customize with drag-and-drop