Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
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...
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.
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.
Open-source, self-hosted CMS platform on AWS serverless (Lambda, DynamoDB, S3). TypeScript framework with multi-tenancy, lifecycle hooks, GraphQL API, and AI-assisted development via MCP server.
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
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.
— build production voice agents with a visual workflow builder, test them in minutes, and let AI coding assistants help design and edit them through MCP.
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more.
A fast coding-agent harness in Go. Tool-use loop, bubbletea TUI, provider-routable models with live catalog discovery, MCP support, background subagents.
Agent Skills
这个仓库源于我使用 Codex 的日常需求。写论文不是单点任务，而是一条从构思、实验、写作、审稿到 rebuttal 的长链路；每一步都需要 AI 有边界、有证据、懂学术表达。因此这个仓库把 组织成当前 7 个模块、27 个可触发 Skills：
Algorithmic Trading in Python with Machine Learning
The Threat Hunter Playbook is a community-driven, open source project focused on before, during, and after a hunt.
A Claude Code of the skills we share at AI Builder Club for building : agents that get triggered on their own, pick up work, ship it, verify it, and log what they learned, so the work compounds...
Expose local http, tcp or websocket connections to the public internet
Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 109 skills, 44 agents, expanded lifecycle hooks, persona presets, experimental opt-in plugin packs, and...
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.
Expert code review skill: SOLID, security, performance, error handling, boundary conditions
"To achieve great things, two things are needed: a plan and not quite enough time." - attributed to Leonard Bernstein
— install as plugins via the 37signals marketplace:
Plugin-skill wrapper around Z4nzu/hackingtool. Runs locally on any OS — native Bash on Linux/macOS, WSL on Windows, or purpose-built Docker images (instrumentisto/nmap, projectdiscovery/nuclei,...