Designing, evaluating, and shipping autonomous AI agents.
7631 posts
Let your AI agent drive your real, logged-in Chrome — browser automation for LLMs via MCP.
MCP server for BusPirate 6 hardware security testing. Exposes UART, power supply, GPIO, and flash-dump operations as Model Context Protocol...
Graph-aware code context for CLI and MCP workflows
Minimal, secure personal AI agent — Claude Agent SDK + Telegram + MCP
台灣工作日計算引擎 · Taiwan Workday Engine — 補班調移授權資料 + 連假偵測 + 請假最佳化 + MCP server for AI agents
Open-source API key firewall for AI agents. Proxy gateway with per-token rate limits, budget caps, model restrictions, and instant kill swit...
Structured AI memory layer. A single source of truth for what your agent knows across conversations. :)
A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.
Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.
The trust layer for agent-to-agent commerce — cryptographic identity, enforced transaction rules, verifiable reputation. Connect via MCP.
Claude Code Skill and MCP Server for GeminiWatermarkTool — let AI agents remove Gemini watermarks automatically
