Search

OS-agnostic, model-agnostic desktop automation server. Gives any AI agent eyes, hands, and ground-truth verification on Windows, macOS, and Linux.

Always up-to-date open-source mirror of Claude Code with GPT-5.4 support. Run Claude Code from source with Claude or GPT models via ChatGPT subscription. 18 deep-dive architecture articles included. For educational and reference purposes only.

Most tools give AI access to the codebase. Archon gives AI access to the change itself. Structural Analysis tool intergrated for AI planning and review workflow both for ai and human ( Claude Code, Codex, OpenCode and Others).

Fast and minimalist agentic AI framework in TypeScript

OpenTrade Pro 2026: AI Trading Bots & HFT Tools 🚀

Proactive developer agent with tape memory, tool orchestration, and multi-channel interfaces

Multi-agent OS with 3D office visualization, dynamic org generation, and real Docker execution

An open-source framework that grants AI agents continuous digital life by transforming idle time into self-driven evolutionary loops.

Hands-on workshop to build, test, and deploy single-agent and multi-agent Hosted Agents to Microsoft Foundry from VS Code using Foundry Toolkit and Agent Framework (Python)

Team-shared Agent Harness Builder to configure MCP Servers, Skills and AGENTS.md / CLAUDE.md for your team with cross-agent setups.

Orchestrating Agents: From Hard Guards to Soft Constraints — A systematic guide to AI Agent orchestration

AgentRX diagnoses AI tool-chain failures and prescribes the next best action. Covers skills, MCP servers, plugins, built-in tools, agents, workflows, and hooks. Task-first, not tool-first.

Build production-ready AI agents in Java with Spring AI and Amazon Bedrock. Features RAG via Bedrock Knowledge Base, tool calling, streaming chat, and persistent conversation memory — powered by Claude Sonnet 4.

Markdown Action Notation for pages, actions, and agent-friendly interactions.

Solana meme-coin auto-trading bot with MiniMax M2.7 LLM exit advisor, Jupiter Ultra swaps, Telegram control, and a Pepe-on-Moon dashboard

Welcome to the Blue Lock of Logic. If you can't see all 14 million possibilities at T=0, you don't belong here.

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with canonicalization, contradiction tracking, recency ranking, and explainable recall.

给Agent完全自由的环境，让它和人类“平等”——Agent-Human Interface

Extensible fraud detection framework with multi-agent AI

Transparent AI agent tracing