Coding agents & developer tools
Terminal & shell assistants
1,347 agents · most starred first
Terminal & shell assistants, page 7 of 14
An open-source AI agent that brings the power of all models of Ai directly into your terminal.
Lightweight, untracked, and self-evolving terminal AI companion. Zero telemetry, durable memory, bidirectional synergy, and native TUI.
QoderWork CN + QoderCN 设备ID重置工具。仅替换本地设备标识序列,不删除文件,不丢失账号信息。跨平台支持 macOS Shell 和 Windows PowerShell。
🦈 Terminal-only AI assistant with an animated neon voice orb, hands-free voice chat, neural TTS, and a safe agent toolset. Providers: DeepSeek, OpenAI, Claude, Gemini, Ollama.
Mouse-driven ASCII diagram canvas for herdr agents - draw in the TUI, share structured JSON, and let AI edit it.
Multi-account manager for AI CLIs (Codex, Claude Code)
Terminal dashboard and CLI for Claude Code and Codex accounts, their quota, and work a usage limit stopped
Terminal-visible chart toolkit — 29 chart types (incl. image/video via chafa+ffmpeg) + live animation rendered directly in the CLI. No browser, no files. Works with Claude Code, Codex, Gemini CLI.
Dynamic CLI generator for OpenAPI specifications designed for AI agents and automation
🚂 Make terminal great again, chat to creation and action, power by chat-llm and langChain.
Transform your terminal into an intelligent AI workspace with autonomous tool-calling and multi-step workflow execution, real-time streaming responses, persistent chat history, and comprehensive MCP (Model Context Protocol) client functionality for seamless tool integration.
A CLI for talking to ChatGPT, saving conversation logs, and turning code blocks (language agnostic) from it's responses into executable shell commands.
Lockhart is an AI-powered Python library that generates elegant and efficient code, much like the charming and deceiving wizard Gilderoy Lockhart. It allows developers to effortlessly create impressive code and deceive others with their skills, just as Gilderoy Lockhart deceives others with his charm and wizardry.
tokdu (Token Disk Usage) is a terminal-based utility that helps you analyze and visualize token usage in your codebase. Similar to the classic du (disk usage) command, tokdu shows you how many tokens your files and directories consume, which is essential when working with Large Language Models (LLMs) that have token limits.
Command line (CLI) application of OpenAI python client library
Open-source AI agent to safely kill stray dev servers & free blocked ports in Google Antigravity IDE (and similar agentic IDEs like Cursor). Slash commands: /killservers /listports /nukeports. Intelligent, safe, portable
CLI for managing LuLu macOS firewall rules. Designed for AI agents.
🤖 一个基于本地 Ollama 模型的代码助手 CLI 工具。集成 LangChain.js,使用模型原生 tool calling 能力实现可靠的工具调用。
pyWhat LLM version | Answer "What is it?" on the command line with the power of large language models
A conversational AI CLI that brings MiniMax's intelligence directly to your terminal. Edit files, run commands, and manage projects through natural language with lightning-fast code editing
Unix like `ls` for Google Drive
cli for doing awesome claude / codex work
A Unix-friendly CLI for LLM chat and text generation. One interface for Anthropic Claude, OpenAI, Groq, and Cerebras — pipe stdin, reference files with `@path`, and stream responses right in your terminal.
Send prompts to Claude.ai directly from your command line!
AI-CMD-X turns plain English into real Windows commands — making the terminal smarter, faster, and incredibly beginner-friendly. Master your machine with the power of AI!
A modern, feature-rich SSH terminal application built with Electron and React. KEMENT combines traditional SSH functionality with AI-powered assistance to enhance productivity and streamline remote server management.
Terminal UI harness tool for Salesforce. Orchestrator + 6 persona subagents, jsforce + sf CLI, qmd RAG. Powered by Claude Opus 4.7.
Set up remote terminal access for AI agent workflows in minutes
An AI agent based on the Ollama large model, capable of executing Linux commands through natural language and invoking kernel hooks to delve into the underlying system.
Control Mautic from the command line or any AI coding agent.
The tiniest Claude Code CLI - ask, pipe, chat
A collection of PowerShell productivity scripts for Windows developers. Streamline your workflow with SSH tunneling, project management, AI integration, and 30+ developer commands.
Vimeflow is a coding agent TUI view park(manager) built with libghostty in MacOS and Xterm in Linux
Worktree-centric libghostty-based terminal multiplexer for macOS, iOS & iPadOS
Maximize your macOS setup
Free, lightweight desktop API client and native Postman alternative built on Tauri. Collections, environments, auth helpers, scripts, collection runner, Postman/OpenAPI/cURL import.
Terminal picker for Claude Code, Codex and OpenCode: harness, provider, model, system prompts, launch.
AI-powered desktop client for JumpServer (open-source PAM/bastion): tabbed SSH, RDP and SFTP sessions with split views, plus an AI assistant that turns plain language into commands, explains errors and alarms, and writes snippets and alarm rules. Works with Claude, OpenAI, Gemini, Azure OpenAI and local Ollama models.
Agent subscription usage: a pluggable CLI for humans and agents
safe command execution with great management
The App Store for AI Agents — discover, install, and manage 100+ CLI tools via structured JSON.
interact with AI to write and run C# code! This console tool sends your text prompts to Google's Gemini AI, gets back executable C# scripts, and runs them instantly in your terminal.
A Mac-native terminal workspace for running many AI agents at once.
Telegram bridges for running Codex CLI and Gemini CLI from a single authorized chat
A cross-platform CLI tool for managing AI project artifacts.
Your AI agents are waiting for you
LoweCLI - AI Powered Command Line Tool
"unitmux" — Unifies your AI coding sessions into a single floating interface.
⚠️ ARCHIVED — Legacy C++ CLI. Superseded by https://github.com/Roberdan/convergio
NoShell
A tool to send requests to OpenAI in the form of natural language, get responses, interact, save prompts, use custom data and more
AI-Powered Terminal Assistant - Open-source alternative to Claude Code Skills with cost savings. Supports DeepSeek/Qwen/Ollama & offline mode
DeepShell4 is an AI-powered terminal assistant for Linux that helps you write, fix, and understand shell commands
AI in command line, powered by OpenAI
An extensible command-line utility powered by ChatGPT, designed to enhance your productivity.
AITerminal is an automation tool for the command line interface (CLI) that interacts with OpenAI's API to execute commands based on a given task.
A C++ OpenAI CLI interface! I use this as my day-to-day toolkit for working with OpenAI products.
Command-line tool for AI-powered text and code generation using Gemini AI, OpenAI and GPT4ALL APIs.
A package manager for Go
🧠 NSH - Control your terminal using natural language
Zonix is a command line interface integrated with the OpenAI artificial intelligence API to help you with your tasks quickly and easily.
This repository contains a collection of tools to interact with the OpenAI API.
Waldo is a command-line AI assistant that wraps around local LLMs, Google's Gemini models and OpenAI's GPT models
AI Agent CLI for developers. Multi-LLM, context injection, ReAct & MCP
Bgpt is a customizable AI-powered shell assistant. It converts natural-language requests into shell commands, applies safety checks, and executes commands with confirmation and timeout controls.
AI-powered log file viewer and analyzer — handles 14M+ lines with virtual scrolling, MCP agent integration, live serial/logcat/SSH/Datadog connections, pattern correlation, diff view, and built-in terminal
AI Local Interactive Cross-device Engine. Same AI session, anywhere. Terminal ↔ Feishu for CLI agents (OpenCode/DeepSeek V4, Codex, Claude, Gemini, Kimi).
AetherShell is an AI-native Linux shell assistant powered by local LLMs. It converts natural language into secure, offline shell commands using Mistral and llama.cpp — ideal for developers, sysadmins, and automation enthusiasts.
Ollama Code is a CLI tool for AI-powered programming assistance using local Ollama models. The project provides full control over code and data, working completely offline.
Open-source terminal AI agent for Korean public-service workflows with a Claude Code-style tool loop, K-EXAONE, and civic adapters.
A CLI Python REPL, written in Rust, that embeds an LLM agent that can inspect and modify Python runtime state
Convert natural language to terminal commands using AI. Simply AI helper in the Terminal
AI command palette for your terminal. OpenAI, Anthropic, Ollama, DeepSeek, Kimi, Xiaomi MiMo and any OpenAI-compatible provider.
A minimal Python tool to monitor multiple log files simultaneously in a single terminal window via tail. With Claude Code integration to automatically discover relevant log files from your recent experiments.
Helix: AI-powered CLI with RAG intelligence that converts natural language to commands using 450+ system commands. Features local AI, cross-platform package management, Git workflows, syntax highlighting, and multi-layer safety with directory sandboxing.
Full OpenMeteo API from your terminal
Terminal AI agent with ReAct pattern - execute shell commands, run Python, analyze images. Supports Gemini, OpenAI, Ollama.
A fully local AI CLI agent powered by Ollama. Rebranded from Gemini CLI as gmol.
A fast, scriptable CLI for SABnzbd - built for AI coding agents like Claude Code, Cursor, and Codex. Control downloads, manage queues, and automate workflows from your terminal.
terminal runtime for working with multiple coding agents
An agentic shell that runs AI coding agents (Claude Code, Codex, Gemini) as governed, audited Unix jobs.
Abundio is a GPU-accelerated, project-centric terminal workspace for AI-assisted development. Run your shells, coding agents, editor, git, and notes side by side — without leaving your project.
Gemma CLI is a high-performance, extensible terminal workstation designed for Google's Gemma 4 model family built with Google free/paid tiers AI API's — no subscription required. It brings a sophisticated, tool-aware agent directly into your PowerShell console, enabling AI-driven system administration, web research, and workflow automation.
The SSH client your AI agent has been waiting for.
Wrap a command in a PTY and control it from the outside — read output, screenshot the screen, send input, attach/detach. Handy for scripts and AI coding agents.
vMux is the Windows-native cmux/tmux alternative for AI coding agents. Run Claude Code, Codex and others side by side with tmux-style splits, git worktree isolation, ConPTY terminals, MCP support and built-in localhost preview. Built on Electron and React.
Universal finder for local AI agent conversations (Codex, Claude Code, OpenCode, Hermes)
Local AI Linux terminal assistant written in Bash. Explain commands, analyze files and logs, and use local LLMs or OpenAI-compatible APIs.
Token-optimized middleware for LLM coding agents — 30–90% fewer tokens on the shell commands your agent runs all day. A single Go binary.
Terminal AI command center for Pi with Superpowers modes, 9Router model autodetection, and SumoPod-ready endpoint routing.
Run Aulthium AI Agent instantly in Termux, Linux, or any terminal with a single command.
A macOS-native terminal workspace designed for AI-driven development
SupSub 的命令行工具 —— 在终端里管理订阅源、关注点、分组与全站搜索,内置 Claude Code skills
One stable CLI and daemon for SSH, local PTY sessions, file transfer, and remote editing — built for AI agents and humans alike.
Self-hosted remote workbench for your projects — agent terminals, files, git, kanban, mindmap and scheduling, reachable from anywhere.
Privacy-first iOS SSH terminal — agent- & multiplexer-agnostic (tmux, zellij, screen; Claude Code, Codex, aider, Hermes…). On-device dictation, Live Activities, zero data collection.
Run your own LLM inside Warp — local adapter for any OpenAI-compatible provider
A lightweight CLI AI agent that can read files, write files, and list directories.
Local AI Workstation CLI for LM Studio/Ollama. SysAdmin, NetAdmin, and Senior Dev in your terminal. Maps codebases, previews edits, autonomous build recovery. Deep-kernel health, crash logs, and network stack. 54-voice TTS + Hybrid BM25/Semantic search with PageRank graph and heat-weighted memory. Windows-first. One Rust binary. No cloud. No API.