Designing, evaluating, and shipping autonomous AI agents.
7673 posts
IA na Prática: LLM, RAG, MCP, Agents, Function Calling, Multimodal, TTS/STT e mais
CVE ingestion + enrichment pipeline with an MCP server for AI agents.
Security auditor for MCP servers. Purpose-aware scoring, injection testing, compliance checks.
Чтение конфигураций 1С из файловой ИБ (1Cv8.1CD): метаданные, модули BSL, данные БД. Экспорт в Obsidian, MAP.md и RAG. MCP для Cursor, Claud...
Windows-first local MCP stdio server and safety bridge for AI agents connecting to ComfyUI, Blender, AutoCAD/DXF, Photoshop, Illustrator, an...
Semantic, on-demand skill retrieval for Claude Code — replaces the per-turn skill-listing token tax with a vector retriever over full skill...
One endpoint in front of unlimited MCP servers and REST APIs. The agent sees a fixed ~15-tool surface however many you connect, so tool-list...
Spring AI agent engineering project with Java, MCP, RAG, tool calling, multimodal workflows, and UI prototypes.
Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CLI agents, security f...
MCP server + Chrome extension that gives AI agents control of your real browser with existing sessions and logins
Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.
