#cli-tool
GitHub repositories that have self-applied the topic "cli-tool" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #cli-tool (top 17 by stars)
基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理,复杂任务智能拆解与多 Agent 并行执行。
UniverseKing4/Wool🐑 Ultra-lightweight CLI AI Agent — pure REPL, zero TUI, Linux-native
mugwork/mugMug is an AI automation platform for building deployed agents, real code workflows, & headless web surfaces for everyday business, integrated with any API, and accessed via email, SMS, & Slack — all built locally using Claude Code, Codex, & Cursor.
Joaquin-web/kernel-gaze-agent2026 Ultimate Podman AI Coding Agent – Zero-Trace, MIT Licensed GitHub Repo
RudrenduPaul/evolveguardRegression-testing CI gate for self-edited Claude Agent Skills (SKILL.md, MEMORY.md) -- golden-transcript record/replay, zero hosted infra.
gtbwpkwjnb-alt/skills-summarize-audit-skillSkills Audit — 技能审查·画像·评分·优化 / Universal agent tool auditor — profile, score, optimize
All-The-Vibes/ATV-PaperBoardCross-harness HTML artifact toolkit for AI coding agents. Native plugins for Claude Code, Codex CLI, and GitHub Copilot CLI + GitHub Actions recipe for the Copilot Coding Agent. One Python core, four pillars: Enforce, Render, Persist, Compound. Apache-2.0.
leerhadz/moai-forgeSPEC-First AI DevKit for Agentic Code 2026 — 24 Agents, 52 Skills, TDD/DDD Gates
ManuelG4/claude-code-explorer-essentialsBuild Your Own Claude Code Engine 2026 – Learn, Run, Route Models
TomSOhm/claude-session-portPortable single-session export for Claude Code - list, export, import, and delete one session by UUID and resume it on another machine. No cloud, no account, just a zip.
devShakers/ai-usage-evaluatorsh-eval — a local-first CLI that scans your projects and machine to map your AI setup (tiers T0–T7 → Setup Levels) and certify your skills. Nothing leaves your machine without consent.
moisesvalero/agentcheckerFix contradictions between AI agent instruction files
spearchucker667/Skill-HQEHQE (/HQE) is a portable, production-grade agent skill that equips AI coding agents with the rigor, skepticism, and methodical precision of a Principal Staff Software Engineer and Principal Security Auditor.
Reedtrullz/ClankerOSLocal-first agent operating system for durable AI coding: task graphs, deterministic context packs, executable delegation, verification evidence, and approval gates.
AlexFloyd13/questlineA tiny ASCII pet for your Claude Code status line
xydadada/api-probeLocal multi-protocol LLM API tester for OpenAI-compatible, Anthropic & Gemini endpoints · 本地多协议 API 测活工具
p-w-g/ratHaving fun with agents writing rust. 🦀
RELATED Other topics · full topics ranking →
#claude-code
1,564#ai-agents
1,160#llm
1,071#claude
943#python
806#ai
741#developer-tools
728#mcp
727#codex
521Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology