47,133 repositories indexed
1–10 of 10 · Most stars
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Translated🚀 A basic development platform built on Vite+Vue3+Gin with AI assistance, an enterprise-level business AI+ development solution, with a built-in MCP assistance service and built-in skills management, supporting mixed use of TS and JS. It integrates essential development features such as JWT authentication, permission management, dynamic routing, controllable show/hide components, pagination encapsulation, multi-point login interception, resource permissions, upload and download, a code generator, a form generator, and configurable import and export.
TranslatedThe official Lark/飞书 (Feishu) CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.
The container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️
Tiny local-first AI harness: any model, MCP and Agent Skills, natural-language CLI. Zero dependencies. MIT.
Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks, skills, and tracing.
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.
Package manager for MCP servers, Agent Skills (SKILL.md), and Claude Code commands, hooks, subagents, and output styles. Installs into Claude Code, Cursor, Codex, Gemini CLI, Copilot, and Cline.
Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.