The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent (Claude Code, Cursor, Codex, OpenClaw) through MCP and skills.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

A secure and scalable Git MCP server enabling AI agents to perform comprehensive Git version control operations via STDIO and Streamable HTTP.

DSH 上的类 VSCode 编码体验：Monaco 编辑器（文件页签/QuickOpen/状态栏，可驻 DSH 0.1.5+ 官方右侧 Sidebar 与对话同屏）+ 命令栏（Ctrl+Shift+P）与可扩展指令系统 + VS Code 兼容代码片段（.code-snippets 全局/项目，IntelliSense 展开）+ Agent 编辑差异审查（整文件差异/采纳/拒绝/归档/回滚）+ SVN 集成（侧栏变更面板/日志弹窗/并排差异）+ 语言服务器（LSP）智能（跳转定义/引用/hover/大纲

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.

The deterministic agent-integrity gate. One ruleset, evaluated on the actual diff/commands as a verdict, enforced everywhere a change can be made.

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

Smart code reading for humans and AI agents. Definitions, callers, dependencies and function-level diffs from tree-sitter. One binary, no index. MCP server + CLI. Install: cargo install tilth or npx tilth

Run different Claude Code providers in different terminals. 支持同时在不同终端窗口用不同 API Key 跑 Claude Code，互不影响