Simulate Before Reality.

Effortlessly secure your AI agents and AI-powered workflows — from prototype to production. Get easy-to-use identity, credential, and access management built for fast-moving AI developers.

Fast Sandbox is a Kubernetes-based high-performance sandbox management system. The core objective is to provide millisecond-scale container startup latency for scenarios sensitive to startup delay,…

Multiplayer agent harness for work.

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

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

🐚 Hermit manages isolated, self-bootstrapping sets of tools in software projects.

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thre…

Light, fluffy, and always free - The AWS Local Emulator alternative

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

Build terminal UI in Kotlin using Jetpack Compose

A Kanban that lives inside your repo. Ordna is a local-first, git-based task board you run from your terminal or your browser.

AgentBOX — edge-AI appliance monorepo (MailBOX pipeline + Hermes agent + gBrain on Jetson); custom UI/features live in agentbox-sidecar

The zero-infra coordination substrate for fleets of coding agents — your entire work graph is a git repository.

Simple, unified interface to multiple Generative AI providers

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

Plain Python conversion of the code from Antonio Gulli's 'Agentic Design Patterns'. This project refactors the original book notebooks into executable .py scripts, enabling easier integration and p…

A hive mind communication platform

Specification and documentation for the Model Context Protocol

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Visualize your Claude Code harness — agents by model tier, hooks across the session lifecycle, orchestrator routing, and the review pipeline — as an interactive page

🌈 React for interactive command-line apps

Cost-efficient and pluggable Infrastructure components for GenAI inference

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. S…

A component library that ships its own printing press. Every surface is printed, not painted — halftone screens pressed onto canvas. One file, zero dependencies.

Public, reproducible GitHub Actions benchmark for comparing AI coding-agent harnesses through constrained chess agents.

Ephor — a governed agent organization: a technology company where every operational role is an AI agent, run under a human board and enforced by infrastructure, not prompts. (formerly Optimus)

Terminalhire — Claude Code plugin (public distribution mirror). Local-first developer job matching, surfaced in the spinner.