Windows 上给 agent 一个真正的 Git Bash 命令工具:私有 Git Bash 执行器实例(官方 PowerShell 执行器原样保留),统一 MSYS 盘根路径方言,官方 pwsh 工具默认隐藏可开关,物化四个内置预设的 Git Bash 变体,侧栏终端接管可开关。· Give agents a real Git Bash tool on Windows: a private Git Bash executor instance (the official PowerShell exe

Opt-in, token-authenticated MCP server built into the Shelly Android terminal app: read-only tools for terminal output, git status, registered agents and repos on the phone, plus off-by-default run_command and write_file that need an on-device approval tap per call.

Enables AI agents to execute commands and read files or directories on pre-registered, fingerprint-verified SSH hosts by alias or IP, while keeping encrypted passwords local and inaccessible to the agent.

Whatshell: a Rust WhatsApp Web CLI for coding agents

Enables LLM to use a cli environment.

Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception

Shell and coding agent on mcp clients

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

Workspace mux and local context runtime for coding agents

The World's First Virtual Terminal for AI Agents

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

Software architecture diagramming tool. Includes a modern easy to use Frontend + Backend + CLI to enable managing diagrams from the shell or in CI.

Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.

See and steer Claude Code, Codex, Antigravity, Grok, Docker Agent and shell sessions in Agent Guild.

Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.

Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.

Blocks AI agents from bypassing git hooks: --no-verify, core.hooksPath overrides, hook-manager disable env vars, and the same hidden in git aliases or shell wrappers.

Enables agents to inspect, control, and debug Android devices over ADB using named device profiles, with read-only defaults and gated write/shell operations across UI, apps, logs, files, and system diagnostics.

dsh web GUI skill hub: browse/search all local skills, per-skill/group toggles, install-time audit (hidden chars, pipe-to-shell), GitHub market with commit pins, local-edit detection, cross-agent import, restorable trash.

Workit Claude Code plugin — session and per-turn task context, branch policy on git shell commands, workit method skills, and verifier/reviewer/implementer agents

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, ag