Designing, evaluating, and shipping autonomous AI agents.
7677 posts
The testing standard for MCP servers. Lint (14 rules), test, and fuzz over real stdio/SSE/HTTP transport. 18 assertion types in YAML. Found...
Open-source, self-hosted Zero Trust policy enforcement layer for MCP servers.
梨园 Liyuan — 以 AI Agent 为主体的角色扮演应用：记忆账本、决策卡、自建面板、世界线，兼容角色卡/世界书
Give an LLM a URL and a goal — it drives a real browser, fills forms, and returns structured data. The browser that scripts itself.
Plug your AI agent into 50+ messengers (WhatsApp, iMessage, Signal, Telegram, Slack…) through one MCP endpoint. Two modes: a self-contained...
Agent-driven Adobe After Effects automation. MCP server + CEP plugin enabling Codex/Cursor/Claude Code to drive AE through 30 ae.* tools.
Runtime governance for coding agents and tool-using agents. Allow/review/block MCP, shell, SQL, GitHub, and HTTP actions. Mint scoped creden...
Context-sharing MCP Gateway on Cloudflare
A chef's palate for AI agent memory; Un-mix any day's work into its exact projects, and detect workstreams nobody has named yet. Hyperdime...
🐦⬛ SMTP for AI agents. No middleman.
A powerful command-line interface for Redmine, enhanced with first-class AI agent capabilities via Skills and MCP integration.
Local agent infrastructure in one stdlib-only Go binary
