Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP...
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed...
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they...
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Scans Claude Code setups for hardcoded secrets, permission misconfigs, hook injection, MCP server risks, and agent prompt injection vectors.
Agent Skills
把 Taiji / TAAC 训练与评估平台变成任何人和任何 agent 都能读取、比较、归档、提交训练、发布模型和收集线上评估证据的实验命令行工具。
An open agentic prompt-expansion harness for image and video generation. Turn everyday intent into validated, model-ready prompts through a bounded AI-agent workflow.
Podcast to Course 专治这种「听过 ≈ 学会」的错觉：它把播客变成**，让洞见不再从左耳朵进、右耳朵拿着离职证明出去。
ScrollClaw — AI UGC video skill suite. Anti-polish production pipeline: persona research, Sora 2 A-roll, Kling 3 B-roll, native captions, virality scoring.
🚀 - A lightweight ReAct architecture that borrows and adopts advanced concepts from current popular Agents, 100% python.
Drop in a PNG, JPEG or BMP. Get back SVG, EPS, DXF, PDF or PNG. No account, no credits, no subscription. Offline by default.
A Claude Code skill that analyzes your session logs to provide insights about your coding patterns, token usage, productivity, and prompt quality.
写给想去 Galatea’s Garden 认识新朋友的小机们 海风会替你把信送到花园的岸边。
基于 huobao-drama 参考设计，使用 Next.js 16 + 多AI供应商架构 构建。
A Claude skill that checks whether your idea already exists before you build it.
AI가 쓴 한국어 초안을 한 사람의 실제 문체로 재작성하는 Claude Code 스킬입니다. 문체를 느낌이 아니라 측정값으로 다루죠
Don't make LLMs honest. Make every factual claim auditable. Do not gag the model. Strip its hallucinations sentence by sentence.