AI CLI Agents

Anthropic's agentic coding CLI

Anthropic's agentic CLI coding tool that delegates complex tasks to Claude directly from the terminal. Understands entire codebases via automatic context gathering, edits multiple files, runs shell commands, and manages Git workflows autonomously. Supports CLAUDE.md for persistent project instructions, integrates with VS Code and JetBrains, and uses Claude Opus/Sonnet with extended thinking for complex architectural decisions. Built for terminal-first developers.

Minimal terminal coding harness

Pi is an open-source minimalist coding agent built by Mario Zechner that runs in the terminal with an intentionally lean design — just four core tools (read, write, edit, bash) and a ~300-word system prompt. It treats the context window as scarce, omits sub-agents and MCP by default, and pushes extensibility to TypeScript extensions, skills, and prompt templates developers build for their own needs. A radical counterpoint to bloated AI coding tools.

Enterprise-grade AI coding agent system by Factory

System of specialized AI Droids — Code, Knowledge, Reliability, and Product — each optimized for specific development tasks. Ranked #1 on Terminal-Bench with 58.75% score. BYOK model with support for Anthropic and OpenAI models. Enterprise-focused approach that treats AI coding as a team of specialized agents rather than a single general-purpose assistant.

Open-source AI coding agent for the terminal

Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.

Agentic coding tool by Sourcegraph (formerly Cody)

Frontier coding agent from Sourcegraph that runs in the terminal and as IDE extensions for VS Code, Cursor, Windsurf, and JetBrains. Amp wields the strongest available models — Claude, GPT, and Gemini frontier tiers — with no token caps or context window throttling. Built around full-fidelity tool use, multi-file edits, oracle-style planning subagents, and team-shared threads. Token-based pricing with no subscription tier; pay only for the model usage you trigger.

OpenAI's agentic coding CLI and cloud sandbox

OpenAI's cloud-based AI coding agent powered by codex-1 (a version of o3 optimized for software engineering). Autonomously writes features, fixes bugs, and proposes pull requests, with each task running in its own sandboxed environment preloaded with your repository. Teams can deploy multiple agents in parallel to work on independent tasks, with MCP integration and AGENTS.md for repo-specific instructions.

MCP, ACP and Skills support for building production coding agents — interactive or automated.

fast-agent is an Apache-licensed Python framework for building and running LLM agents with full MCP (Model Context Protocol) and ACP support. It ships with an interactive shell mode, Skills management, and multi-model routing — making it a practical platform for coding agents, workflow automation, and agent evaluation across Claude, Codex, HuggingFace, and local models.

Cut Claude Code token costs by up to 50% with a local plugin that never uploads your code.

WOZCODE is a Claude Code plugin that reduces token consumption by 25–55% using smarter context reads, batched file edits, AST truncation, and Haiku subagents. It installs in seconds with two CLI commands, runs entirely locally with no code upload, and requires no account sign-up. Developers report finishing the same tasks in fewer tokens without changing their existing editor or workflow.

Self-evolving local computer agent with a reusable skill tree

GenericAgent is a minimal, self-evolving autonomous agent in roughly 3K lines of Python that gives LLMs system-level control of a local computer. It writes files, runs shell commands, and browses the web, but its defining feature is skill crystallization: successful task runs are saved as reusable skills inside a growing skill tree that cuts token cost on repeats.

Personal AI agent in your terminal with local tool access

gptme is one of the earliest terminal-based AI agent CLIs, launched in spring 2023. It equips a personal AI agent with local tools to run shell commands, write and edit code, browse the web via Playwright, and use vision capabilities. Supports MCP integration and an extensible plugin system for building persistent autonomous agents. The reference agent Bob has completed over 1700 sessions.

ByteDance's open-source LLM coding agent with multi-provider support

Trae Agent is ByteDance's open-source software engineering agent that autonomously resolves GitHub issues, fixes bugs, and implements features using any LLM provider. It supports OpenAI, Anthropic, Doubao, Azure, Ollama, and Gemini backends, making it one of the most provider-flexible coding agents available. With over 11,000 GitHub stars and a modular research-friendly architecture, it offers a strong alternative to Western-centric coding agents.

One-command local coding agent that auto-detects your hardware and picks the best model

hf-agents is a Hugging Face CLI extension that detects your hardware, recommends the best GGUF model using llmfit, and launches a local coding agent in a single command. It collapses the multi-step local LLM setup into hf agents run pi, automatically handling hardware profiling, model download, inference server startup, and coding agent activation.

Google's proactive coding agent for async repository maintenance

Jules is Google's coding agent that proactively scans repositories for TODO comments, bug patterns, and improvement opportunities, proposing code changes without explicit user requests. Built on Gemini models, it operates asynchronously in the background, completing over 140,000 code improvements. Handles routine maintenance tasks like dependency updates, code cleanup, and follow-on work from completed features.

GitHub Copilot in your terminal

Brings GitHub Copilot to the terminal, giving developers AI assistance for shell commands, error explanations, and code generation directly from the command line. Supports natural language queries to generate complex shell commands, explains error messages in plain English, and integrates with the broader GitHub Copilot ecosystem including model selection and premium request management.

Natural language interface for running code on your computer

Open-source AI coding assistant with a focus on privacy and local-first execution. Runs models on your machine using Ollama or connects to cloud providers when needed. Supports VS Code with code completion, chat, and inline editing. Targets developers who want full AI coding capabilities without sharing proprietary code with third-party services, offering complete data sovereignty.

Multi-agent CLI pair programmer with FORGE, MUSE, and SAGE agents

Model-agnostic terminal coding tool with 3 specialized agents: FORGE for code editing, MUSE for planning and review, and SAGE for research. Supports 100+ LLM providers with local-first privacy and conversational Git integration. Apache 2.0 licensed. A thoughtfully designed multi-agent approach that separates concerns between coding, thinking, and information gathering for more reliable results.

Open-source AI coding agent for large projects and real-world tasks

Terminal-based coding engine that breaks complex tasks into subtasks with support for 2M token context windows, diff review sandboxes, and both autonomous and manual modes. Multi-model pipelines work with Anthropic, OpenAI, and Google. With 15k+ GitHub stars, Plandex is a mature open-source option for developers tackling large, multi-step development tasks from the command line.

AWS AI assistant for terminal and code

Amazon Q Developer CLI is an agentic AI assistant from AWS that enhances the terminal experience with deep AWS integration, code generation, and natural-language command translation. Completes multi-step development tasks, troubleshoots AWS services, writes infrastructure code, and handles documentation lookups directly from the shell. Included with AWS accounts and integrates with existing AWS credentials.

Google's official CLI agent for coding with Gemini

Gemini CLI is an open-source AI agent from Google that brings the power of Gemini language models directly into the terminal for coding, debugging, and shipping applications. Provides the most direct path from a prompt to Google's Gemini models, with built-in tools for file operations, shell command execution, web fetching, and Google Search grounding. Free tier for individuals with generous usage limits.

AI pair programming in your terminal

Terminal-based AI pair programmer with deep git integration. Auto-commits changes with meaningful messages and creates repository maps for navigating large codebases. Works with Claude, GPT, DeepSeek, and local models. One of the most popular open-source AI coding tools, known for its reliability, broad model support, and seamless command-line workflow.

AI coding assistant with full codebase understanding

Open-source AI coding assistant that runs in your terminal, letting developers chat naturally with an LLM that has full project context. Mentat coordinates multi-file edits across entire codebases — refactoring, feature implementation, bug fixing — with Git integration for review and revert. Requires GPT-4 API access, installs via pip; eliminates copy-paste friction of web AI tools.

Princeton's autonomous coding agent for GitHub issues

Open-source AI software engineering agent from Princeton and Stanford researchers that takes GitHub issues and automatically fixes them with your choice of LLM. SWE-agent's custom agent-computer interface offers simple file view/search/edit actions with guardrails — achieved state-of-the-art 12.5% SWE-bench pass rate plus EnIGMA mode for cybersecurity capture-the-flag challenges.

Open-source autonomous agent with persistent memory by Nous Research

Hermes Agent is an open-source, self-improving AI assistant from Nous Research featuring persistent cross-session memory and a skills system that learns and refines reusable capabilities over time. It ships with 40+ built-in tools and runs across terminal, Telegram, Discord, Slack, WhatsApp, Signal, and email. Bridges the gap between stateless AI chat and truly persistent AI teammates that grow more capable and personalized through continued use.

Autonomous LLM-powered terminal coding agent

Autohand is an AI platform for adaptive continuous engineering and autonomous code evolution, giving teams infrastructure to coordinate multiple AI agents inside sandboxed execution environments. Its open-source Commander tool builds command interfaces that orchestrate multi-agent workflows, while the broader platform lets agents iteratively write, test, and evolve code safely. Aimed at engineering teams pushing beyond simple code generation toward continuous AI-driven software improvement.