GitHub as a knowledge graph for AI agents. Autonomous dev pipeline for Claude Code - investigate, build, review, merge. Issue in, PR out.

数学建模竞赛完整工具链：从拿到赛题到交出论文，一条龙解决。 覆盖 国赛 CUMCM（A/B/C） 和 美赛 MCM/ICM（A-F） 全部题型。

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

Model Context Protocol (MCP) server for SonarQube

AI writing studio for large-scale content.

CAPTCHA proves you're human. HATCHA proves you're not.

Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.

🐕 Self-hosted security-first AI agent · 22 providers · 11 chat channels · WebUI · 3-level memory · cron · heartbeat · skills · MCP

書籍「おい、とりあえず終わらせろ」の5ステップで、内省と次の一歩を支えるClaude Code / Codex向けAgent Skill

A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.

A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know how to ship production code — and want a workflow that keeps the discipline tight without getting in the way.