Local Claude Code Router gateway with CLI and web management UI.

Model router for DeepSeek Harness: keep a pool of models and every step is routed to one of them with its reasoning effort set — a click-only composer panel, three authorization scopes (a manual pick only counts in the scope that owns it, and effort scope

An AI-enabled NAT Router/Firewall for the ESP32

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

Claude Code hooks that auto-switch model tier based on task complexity

Omni - a reliability and orchestration control plane for DeepSeek Harness, designed to turn fast models into dependable long-horizon software-engineering agents.

Model Router and GALGame plugin for DeepSeek Harness

Master Next.js 14+ App Router with Server Components, streaming, parallel routes, and advanced data fetching. Use when building Next.js applications, implementing SSR/SSG, or optimizing React Server Components.

dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).

Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity, Kimi and any model OpenRouter routes to over API; codex, antigravity, grok, kimi and cursor CLIs on subscription auth; ollama locally. Codex specialists take coding tasks on their own branch (experimental).

Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).

Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cursor over MCP. Every answer cites its page; when the vault does not know, it says so. Imports your past sessions on install.

DSH Web 插件：实时显示模型供应商额度与用量（DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + 自定义适配器）

PostMCP core engine - OpenAPI parser, Token Diet, JIT router, and MCP protocol server

My Claude Code (MCC): a local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents, with 57 providers, fallback routing, credential health, a native web-search tool proxy, and ana

Enables travelers and agents to route destination crowds in real time by dispersing visitors and reducing queue waits with queuing-theory and dynamic heatmap guidance.

Enables agents to optimize real-time attraction visitor dispersion and queueing wait times using queuing-theory models and dynamic heatmap routing.

An intelligent Model Context Protocol (MCP) Server that acts as an AI model advisor. Compare LLM and media pricing, features, and quality across 1,000+ models from OpenRouter, fal.ai, Together AI, Replicate, and Fireworks AI. Deeply compatible with Claude

Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.

Professional AI research tool for Zotero: chat with PDFs, whole-library search, Literature Radar, AutoPilot. 30+ LLMs or local models; built-in MCP server.

Self-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers.

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM