A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Orchestrate AI agents to find real vulnerabilities in code.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

LuaN1aoAgent is a fully autonomous AI penetration testing agent driven by graph-based cognitive reasoning, developed by postgraduate researchers from Prof. Lu Hui's Intelligent Offensive and Defens…

Graph-Native Infrastructure for Context and Accountable AI Systems

Clone of OWASP Threat Dragon adding an AI-generated threat report feature

Multiplayer agent harness for work

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

FANDANGO is a language-based fuzzer that leverages formal input specifications (grammars) combined with constraints to generate diverse sets of valid inputs for programs under test.

AI Powered Knowledge Graph Generator

Claude Code RedTeam Skill — Hypothesis-Driven Cognitive Architecture。一个假设-证据驱动的红队skill

AI agents running research on single-GPU nanochat training automatically

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound …

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

Better Harness turns project and session evidence into loop-level insights, prioritized improvements, and verifiable next steps—inside the coding agent you already use.

A library of agent skills for CAD, CAE and CAM

The open-source alternative to Claude Cowork (powered by opencode)

AgentENV (AENV) is a distributed platform for running agent environments at scale.

A Compiler Writing Journey

Removes 20+ patterns of AI slop from any piece of writing.