Showing 30 of 3,398 · Category: CLI Tools
A SQL client written in HTML & Rust for the terminal
Reverse-engineer closed-source desktop software into CLI tools for AI agents. Verified CapCut, Axure RP and Shapr3D workflows.
keyboard-first terminal client for watching and acting on github actions runs
Turn your error messages into collectible monsters. A terminal bestiary for developers. | 把錯誤訊息變成可收集的怪物
CLI for ecommerce product research, comparison reports, and access to Nexscope image and video tools via MCP.
LinkedIn CLI for AI agents (Claude Code, Codex, Cursor): read LinkedIn DMs, search your network, enrich profiles and draft messages you send.
Command-line login for Sharif University Wi-Fi.
把每张图片精确压进指定字节预算的本地工具：网申材料 200KB 压缩，离线批处理，分辨率优先，含 CLI 与 GUI
Local code review hub for AI coding agents (Claude Code, Codex, Cursor, opencode). Agents submit with one CLI, you review files ranked by importance, feedback flows back. GitHub or plain git.
Run a three.ws agent on your own machine or VPS: a terminal UI with slash commands, streaming tool output, local file and shell tools in a resource-limited sandbox, the three.ws MCP tools and agent wallet, SQLite sessions with full-text search, parallel subagents, natural-language cron, and a Telegram gateway.
Share files, folders and localhost through a temporary URL, or receive files straight to your computer. Served from your machine: no cloud, no account, the link expires. Free ngrok, WeTransfer and Send Anywhere alternative.
一台电脑，多个微信用户，AI 任务同时运行。分别扫码使用本机 Codex / Claude Code，独立会话、工作区与审批；支持截图、音视频、PDF/Office 和网页分析。Multi-user, parallel coding agents in WeChat.
Records what AI coding agents like Claude Code and Codex do on your Mac: commands, files, secrets and network. CLI and menu bar app.
Local-first, privacy-focused workspace for coding agents: session history, knowledge, code activity replay, usage insights, and Skills & MCP management.
Learn a writer's voice from their own samples and score coding-agent drafts against it: flags AI tells and invented facts until the draft sounds like you. Local-only.
Record Android UI flows and turn them into durable, declarative tests. Zero-code via ADB/UIAutomator, or instrumented via an optional debug-only agent. No AI/IDE needed at test runtime.
WorkBuddy 同步助手：在多台机器之间通过任意共享目录（OneDrive/坚果云/U盘/网盘）双向同步 WorkBuddy 的全部个人资产（对话/任务/空间/技能/记忆），自带本地 Web 面板
self-hosted persistent Linux workspaces. open-source alternative to boat.dev
Xiaomi Smart Storage (MINAS) WebDAV control toolkit — CLI, probe, local proxy, agent skill & MCP server (Apache-2.0)
Storybook for APIs. Open any OpenAPI or Swagger spec and get a runnable explorer: mocks from the first request, live calls from your browser, flows and share links.
Pigtail is an evidence-first research tool that reverse-engineers how an open-source repo or product grew using public evidences: star history with Show HN / Product Hunt / release markers, launches, metrics, tactics — every fact linked to its source.
A coding agent that runs entirely on your own machine: open-weight models, up to 256K context, NVIDIA GPU or Apple Silicon Mac, via Ollama.
Compress and decompress Nintendo Switch NSP, XCI and SuperNSP files to NSZ and XCZ: one program for Windows, macOS and Linux, with a window and a command line compatible with nsz.
The Open Agent OS & Sandbox Environment. Arch/kata-based Linux with git-like snapshot trees, CRIU memory restore, and per-window GUI streaming for Computer Use agents.
Diagnose why a video will not play and fix it in one command. ffmpeg-based, macOS + Linux.
Security news for your stack: an agent skill and the CLI it relies on. Ask your AI agent "anything today?" and get a straight answer.
Spend intelligence where it matters. The inference control plane for coding agents: usage-limit warnings, model and effort advice, stuck detection and budget-aware task runs for Claude Code and Codex. 100 percent local.
Cross-device live sessions for AI coding agents (Claude / Codex / Pi). Master + join code. Website: https://skepagent.com
A tmux-backed supervisor and dashboard for persistent AI coding sessions. Keeps one claude/codex agent per project moving toward its goal, and pulls you in only when a decision needs a human.