Best tools for Terminal Agents

Multi-agent orchestration layer for OpenAI Codex CLI

Oh My Codex (OMX) transforms OpenAI Codex CLI into a coordinated multi-agent system. It layers workflow orchestration, persistent memory, team-based parallel execution via tmux worktrees, and a live HUD dashboard on top of standard Codex. OMX provides 30+ role-specialized agents and 40+ workflow skills covering planning, execution, verification, TDD, security review, and autonomous research loops.

Persistent memory plugin for Claude Code with automatic context injection

Claude-Mem is a persistent memory plugin for Claude Code with 44,000+ GitHub stars that captures session context and injects it into future sessions. It features progressive disclosure with token cost visibility, automatic compression, and privacy controls with private tags to manage what gets remembered across coding sessions.

Transparent AI agent framework with 100+ skills and real-time visibility

Agent Zero is an open-source general-purpose AI agent framework with 16,700+ GitHub stars that uses the computer itself as a tool. Unlike structured orchestration frameworks, it provides full transparency where every thought, action, and tool call is visible and editable in real time, supporting 100+ extensible skills.

Meta-prompting and context engineering system for Claude Code agents

GSD is a meta-prompting, context engineering, and spec-driven development system designed for Claude Code and compatible AI coding agents. With over 46,000 GitHub stars, it implements a structured four-phase workflow of Discuss, Plan, Execute, and Verify to combat context rot in long AI coding sessions. The system uses multi-agent orchestration with persistent file-based memory.

The 5MB open-source agent daemon that hides nothing

CrabTalk is a lightweight five-megabyte daemon that streams every AI agent event to your client in real time including text deltas, tool calls, and thinking steps. It provides complete transparency into agent operations with one-curl installation and bring-your-own-model support. Designed as the observable alternative to opaque agent runtimes where you cannot see what the AI is actually doing.

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.

Beautiful terminal AI coding agent from the Charmbracelet team

crush is an AI-powered coding agent for the terminal built by Charmbracelet, the team behind Bubble Tea, Glow, and other beloved CLI tools. It brings the same attention to terminal UX design to AI-assisted development with features for code generation, refactoring, file editing, and shell command execution. With over 22,000 GitHub stars and the Charmbracelet design philosophy, crush delivers an agentic coding experience that feels native to the terminal workflow developers already use.

Desktop app for running AI coding agents in parallel

Baton is a desktop application for orchestrating multiple AI coding agents — Claude Code, Codex CLI, OpenCode, Gemini CLI — simultaneously in isolated git worktrees. Each agent gets its own branch to prevent merge conflicts, with a Monaco diff viewer for reviewing changes, automatic PR creation, and an MCP server that lets agents spawn sub-agents for complex tasks.

Multi-agent orchestration plugin for Claude Code

Oh My ClaudeCode (OMC) is a plugin for Claude Code that adds multi-agent orchestration with 32 specialized agents, smart model routing between Haiku and Opus, and five execution modes including fully autonomous Autopilot and parallel Ultrapilot. It provides 40+ skills, a real-time HUD statusline, and lifecycle hooks — transforming Claude Code into a coordinated AI development team with zero configuration required.

Fullstack MCP framework connecting any LLM to MCP servers

mcp-use is an open-source framework that enables any LLM to interact with MCP servers through a unified client interface. It bridges the gap between models that lack native MCP support and the growing ecosystem of MCP tools by providing automatic tool discovery, execution management, and multi-server orchestration. Supports both direct LLM connections and agent-based workflows. Over 9,000 GitHub stars.

Pipe terminal output to LLMs with beautiful markdown rendering

Mods by Charmbracelet is an AI-powered CLI tool that lets you pipe any shell output directly to LLMs with beautiful markdown rendering in the terminal. It follows Unix philosophy — composable with existing tools via stdin/stdout pipes. Supports OpenAI, Anthropic, Ollama, and other providers with bring-your-own-key model. 9,800+ GitHub stars, MIT license. Part of the Charm ecosystem known for gorgeous terminal UIs including Bubble Tea, Lip Gloss, and Glow.

Memory-first coding agent that learns over time

Letta Code is a memory-first CLI coding agent that persists across sessions and improves over time. Unlike stateless tools like Claude Code or Codex, it works with long-lived agents remembering your codebase, preferences, and past interactions. Model-agnostic supporting Claude, GPT, Gemini, and more. Features git-backed context repositories, skill learning from experience, sleep-time reflection, and subagent orchestration. #1 model-agnostic OSS harness on Terminal-Bench.

Terminal dashboard for Kubernetes

K9s is an open-source terminal UI with 28K+ GitHub stars for managing Kubernetes clusters interactively. Provides a real-time dashboard with resource navigation, log tailing, shell access to pods, port forwarding, and RBAC visualization — all from the terminal without kubectl commands. Features Vim-style navigation, custom resource views, plugin system, cluster metrics, and multi-cluster support. Dramatically reduces the complexity of daily Kubernetes operations for developers and SREs.

A prompt theme engine for any shell

A cross-platform prompt theme engine that works with any shell including PowerShell, Bash, Zsh, and Fish. Customize your terminal prompt with rich themes, dynamic segments, and real-time information from Git repos, Kubernetes clusters, cloud providers, battery status, and execution time. The most versatile prompt customization tool available, with hundreds of community themes and a visual config editor.

The minimal, blazing-fast shell prompt

Open-source Firebase alternative providing a full backend-as-a-service on PostgreSQL. Auto-generated REST and GraphQL APIs from your schema, real-time subscriptions, built-in auth with 20+ social providers and Row Level Security, S3-compatible file storage with CDN, and Deno-powered Edge Functions. Visual dashboard with SQL editor and table editor. Supports vector embeddings via pgvector for AI apps. Self-hostable or managed with a generous free tier. 75K+ GitHub stars.

The modern terminal with AI

GPU-accelerated terminal built in Rust, now evolved into an Agentic Development Environment (ADE) used by 700K+ developers. Features block-based output navigation, AI command suggestions via the Oz orchestration engine, multi-line editing with syntax highlighting, and a built-in code editor with LSP support. Available on macOS, Linux, and Windows. Includes Warp Drive for sharing workflows, real-time session collaboration, and BYOK support for OpenAI, Anthropic, and Google API keys.

Fast, native terminal emulator

GPU-accelerated terminal emulator written in Zig by Mitchell Hashimoto (HashiCorp co-founder). Native UI rendering on macOS and Linux. Supports ligatures, true color, Kitty graphics protocol, and splits/tabs. Configurable via a simple key-value file with sensible defaults. Open-source with 20K+ GitHub stars and a focus on correctness, speed, and minimal resource usage. Growing as a modern alternative to iTerm2, Alacritty, and WezTerm.

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.

Terminal AI chatbot — no API key required

Open-source AI gateway and proxy that routes requests across multiple LLM providers. Load balance between OpenAI, Anthropic, Google, and local models with automatic failover, rate limiting, and cost tracking. Provides a unified API interface so teams can switch providers or add redundancy without changing application code.

AI-powered command-line productivity tool

AI-powered database query tool that lets you ask questions in plain English and get SQL results. Connects to PostgreSQL, MySQL, and BigQuery. Ideal for non-technical team members who need data insights without learning SQL, and for developers who want to speed up exploratory queries and ad-hoc reporting.

AI-native open-source terminal for modern developers

Cross-platform terminal with built-in AI chat, inline file previews, and durable SSH sessions. Supports OpenAI, Claude, Gemini, and Ollama for in-terminal AI assistance. With 18k+ GitHub stars, it combines modern terminal UX with AI-powered command suggestions, making remote development and server management faster and more intuitive.

All-in-one LLM CLI tool with shell assistant, RAG, and function calling

AI coding agent focused on autonomous test generation and quality assurance. Analyzes your codebase to identify untested paths, generate comprehensive test suites, and suggest edge cases you might have missed. Integrates with existing CI pipelines to continuously improve test coverage, helping teams ship more reliable code without the manual overhead of writing every test by hand.