Terminal and CLI agents for coding agents
Agents that run in your terminal: they read files, run commands and propose changes. Of the 517 tools on our writing code page, 114 fit this narrower job. By pricing: 93 open source, 3 source-available, 11 free or freemium, 5 paid, usage-based or enterprise, 2 pricing on the maker's site. The most-starred open repos here are REA (410,375 stars), opencode (223,180 stars), Claude Code (153,919 stars). Most come from the coding (78), agent infra (8), MCP servers (6) categories.
Updated
REA
MCP server and CLI that lets coding agents reverse engineer native binaries, Electron and JavaScript apps, .NET assemblies and live websites, using Ghidra, Hopper or IDA under the hood.
Added
opencode
Open-source terminal coding agent that works with many model providers.
Added
Claude Code
Anthropic's terminal coding agent that edits code, runs commands and handles git.
Added
CC Switch
Desktop manager for Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw and other coding agents that switches API providers in one click and manages MCP servers, skills and prompts.
Added
OpenAI Codex CLI
OpenAI's open-source coding agent for the terminal; also runs in the cloud.
Added
Pi
Minimal, extensible open-source terminal coding agent and agent toolkit from Earendil, with a multi-provider LLM API, TypeScript SDK, RPC mode and installable extensions, skills and themes.
Added
Gemini CLI
Google's open-source terminal agent powered by Gemini.
Added
Understand-Anything
Turns any codebase, knowledge base or docs folder into an interactive knowledge graph you can explore and question, working inside Claude Code, Codex, Cursor, Copilot and Gemini CLI.
Added
rtk
A CLI proxy that sits between coding agents and your shell and trims noisy command output before it reaches the model, cutting token use on everyday commands like tests, builds and git. Free and open source, with an RTK Pro tier for teams.
Added
HyperFrames
HeyGen's open-source framework that renders HTML, CSS and animations into deterministic MP4 videos, usable from a CLI or by coding agents through skills.
Added
Open Interpreter
Terminal coding agent forked from OpenAI's Codex and tuned for low-cost and open-weight models, with switchable harness modes that imitate tools like Claude Code.
Added
Warp
Agentic development environment built from the terminal, now open source, for running coding agents and cloud software factories.
Added
CLI-Anything
Open-source project from HKUDS that generates agent-native command-line interfaces for existing software, codebases and web APIs, with CLI-Hub, a registry of community CLIs that coding agents can install and drive.
Added
Aider
Pair-programming agent in your terminal that commits changes to git.
Added
Open Code Review
Alibaba's AI code review CLI that combines deterministic pipelines with an LLM agent to post line-level comments on Git diffs, using OpenAI or Anthropic models.
Added
Codewhale
Rust agent engine and terminal coding client with model choice, tool approvals and review flows.
Added
skills.sh
Vercel Labs' open-source CLI (npx skills) and directory for finding, installing and sharing agent skills across Claude Code, Codex, Cursor, OpenCode and 75+ other coding agents.
Added
Oh My Pi
Terminal coding agent with IDE features wired in, from Stencil Labs.
Added
Repomix
CLI and web tool that packs an entire repository into a single AI-friendly file (with an MCP server) so coding agents and LLMs get full codebase context.
Added
Crush
Charm's terminal coding agent with a polished TUI, multiple models and MCP support.
Added
Qwen Code
Open-source terminal coding agent from the Qwen team.
Added
Cmux
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability
Added
Kilo Code
Open-source AI coding agent for VS Code, JetBrains, the CLI and the cloud that works with 500+ models at no markup.
Added
Magpie
Free, open-source menu bar app and local gateway that lets any coding agent (Claude Code, Codex, Gemini CLI, OpenCode and 60+ more) use any model provider or subscription, with failover when a quota runs out.
Added
opcode
A desktop app for Claude Code that lets you manage sessions, build custom agents, track usage and browse project history from a GUI instead of the terminal.
Added
NVIDIA OpenShell
Sandboxed runtime for autonomous agents with declarative YAML policies on file, network and credential access.
Added
opencodex
A local provider proxy that lets OpenAI Codex (CLI, app and SDK) and Claude Code run on other model providers such as Claude, Gemini, Grok, DeepSeek or local Ollama models.
Added
Botpress
Platform for building and deploying LLM-powered chatbots and agents, with a visual studio, integrations hub, CLI and SDK.
Added
ai-memory
Fabio Akita's open-source long-term memory layer for coding agents: one Rust binary that keeps plain-markdown project memory and typed handoffs shared across 20+ harnesses such as Claude Code, Codex, Cursor and Gemini CLI, so you can switch agents, machines or teammates without re-explaining the project.
Added
CloudCLI
A web and mobile interface for Claude Code, Codex and Gemini CLI, so you can run and steer coding sessions from a browser or phone. Self-host free or use the hosted CloudCLI service.
Added
MiMo Code
Xiaomi's terminal coding agent with persistent project memory across sessions; works with any major model provider and is tuned for Xiaomi's MiMo models.
Added
Qodo
AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge.
Added
Loop Engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny).
Added
Hunk
Review-first terminal diff viewer for checking what coding agents changed.
Added
Worktrunk
CLI for managing Git worktrees so several AI agents can work in parallel.
Added
Terax
Lightweight terminal-first AI development environment.
Added
Munder Difflin
Free, open-source harness that runs Claude Code, Codex, Gemini CLI and other terminal agents together like an office.
Added
mini-SWE-agent
Tiny 100-line agent that solves GitHub issues or helps on the command line, from the SWE-agent team.
Added
ZCode
ZCode is Z.ai's open-source AI coding workspace and official harness for GLM-5.3, with a desktop app, web interface and terminal agent that run multiple agents on long goals, plus control from WeChat, Feishu or Telegram.
Added
OpenSquilla
An open-source microkernel AI agent built for token efficiency, with a CLI, a web UI and chat-channel front ends. The team has published a technical report on its agentic routing.
Added
coucou
Mac notch and phone companion that monitors your Claude Code, Codex, Cursor and Gemini CLI sessions and lets you approve permissions on the go.
Added
ANUS
A free coding agent in your terminal. It runs on the smartest free model that is up today
Added
MobileBuildMCP
Sentry's MCP server and CLI that gives coding agents build, test and run tools for iOS and macOS projects.
Added
ThinkRail
JetBrains' lightweight agentic IDE that pairs you with the pi coding agent, with isolated git-worktree workspaces, editor tabs, terminals and diffs.
Added
AIO Sandbox
All-in-one Docker sandbox for AI agents that combines a browser, shell, files, MCP, VS Code Server and Jupyter in one container.
Added
Agents CLI
Google's CLI and skills that teach coding assistants to build, evaluate and deploy agents on Google Cloud and the Gemini platform.
Added
TUIOS
Terminal window manager with tiling panes, persistent sessions and one inbox where coding agents report their state and message each other.
Added
Tokscale
Tracks token usage across AI coding agents from your terminal.
Added
Fallow
Codebase intelligence for TypeScript and JavaScript in a single Rust binary. It reports health, complexity hotspots, duplication, circular dependencies, architecture boundaries and unused code, and ships as a CLI, a GitHub Action, an LSP, an MCP server and a VS Code extension.
Added
Entire CLI
CLI that captures AI agent sessions alongside your Git commits.
Added
Answer Me with HTML
Agent skill that makes Claude Code, Codex and other coding agents answer hard questions as a readable one-page HTML document with diagrams instead of a wall of text. The model writes only a short Markdown draft and a bundled Node CLI renders the SVG, CSS and layout in about 50 ms, which the project's benchmark shows cuts output tokens about 8x and response time about 2.6x versus asking for HTML directly. MIT.
Added
OpenKnowledge
OpenKnowledge is a free, local-first markdown editor and knowledge base built for working alongside AI agents. It looks and feels like a Notion-style WYSIWYG editor, with callouts, tabs, Mermaid diagrams and media blocks, but every page stays a plain markdown file on your disk. Coding agents such as Claude Code, Codex, Cursor, Gemini CLI and dozens of others can read and write the same files through its integrations, so specs, team wikis and LLM wikis stay in one place that both people and agents keep up to date. It ships as a desktop app plus a web UI and CLI.
Added
AutoDev
Multi-agent development platform built on Kotlin Multiplatform for research, coding, review and data queries across IntelliJ, VS Code, CLI and more.
Added
gptme
Terminal agent with local tools that writes code, runs commands, browses the web and uses vision.
Added
OmniRush
OmniRush is a desktop coding agent for Windows, macOS and Linux, with a terminal CLI as well. It works through the files of your own projects, reading code, making edits and running commands, and gives free access to frontier models from a model picker, with GPT 6 Astra as the default. Builds for each platform are published on its releases page.
Added
Agentic Resource Registry
A self-hosted registry where teams share and discover coding-agent resources across Claude Code, Kiro, Cursor, Codex and Pi, used through the observal CLI.
Added
CodeGraphContext
MCP server and CLI that index local code into a graph database so AI assistants can query code relationships.
Added
Container Use
Dagger's MCP server and CLI that gives each coding agent its own containerized environment so several can work in parallel safely.
Added
Grok CLI
Open-source coding agent for the Grok API.
Added
Toad
A terminal front end from Will McGugan (creator of Rich and Textual) for running AI coding agents like Claude Code, Gemini CLI and Codex through one polished, fast interface.
Added
Open Terminal
Self-hosted terminal service from the Open WebUI team that gives AI agents an API to run commands, manage files and execute code.
Added
CyberStrike
Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM.
Added
FuXi
A terminal AI coding agent that edits code, runs commands and works across 30+ model families, with parallel multi-provider inference and cost-aware model routing.
Added
Jevgrep
CLI that finds relevant repo files and excerpts from natural-language questions for coding agents; claims ~40% cheaper agent runs.
Added
OpenGAP
Framework-agnostic, git-native standard and CLI for defining AI agents so a repository becomes a runnable agent.
Added
Compozy
Operating system for AI agents that turns Claude Code, Codex, Gemini CLI and Cursor into a team with task handoff, loops, jobs and shared memory.
Added
Nanocoder
Community-built open coding agent for your terminal.
Added
ripwire
Zero-dependency CLI and MCP server that gives coding agents a ranked call graph, blast radius and tests-to-run before and after edits.
Added
Gemini MCP Tool
MCP server that lets Claude and other assistants call the Gemini CLI to analyze large files and codebases with its big context window.
Added
nodeterm
A node-based terminal manager for macOS and Linux that shows real terminals and coding agents like Claude Code, Codex and Gemini as live nodes on an infinite canvas you can wire together.
Added
Intelligent Terminal
Experimental fork of Windows Terminal with native integration for ACP-compatible agent CLIs.
Added
Claude Code Tools
Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents
Added
Ante
Self-contained Rust terminal coding agent from Antigma Labs that works with any model and has no runtime dependencies.
Added
Gortex
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate.
Added
Zero
An open-source terminal coding agent written in Go that works with 30+ model providers, supports MCP, skills and subagents, and keeps all sessions on your own disk.
Added
Beautiful Rust
Three Agent Skills plus a drop-in clippy config that teach coding agents to write, review and port idiomatic Rust. rust-best-practices loads whenever an agent writes Rust and steers it toward robust, maintainable code; rust-review produces a prioritised report where each finding cites the rule it breaks and shows the fix; rust-port moves C, C++, Python, Go or JavaScript to Rust by porting the original tests first so behaviour can be proven equal. Distilled from the Google Rust Style Guide, Rust API Guidelines, Effective Rust, Rust Design Patterns and Microsoft's Pragmatic Rust Guidelines; works with Claude Code, Codex, Copilot, Cursor and Gemini CLI. MIT.
Added
Waku
Waku is a native desktop app that gathers your local coding agents in one place. It shows sessions from Amp, Claude Code, Codex, Cursor, OpenCode, Grok and Pi on a single timeline that stays entirely on your machine, so you can follow and switch between agent runs without juggling terminals.
Added
Agmsg
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework
Added
Wake
Wake is a desktop app that collects every coding-agent conversation on your computer into one searchable place. It reads the local history kept by Claude Code, Codex, Cursor, Copilot CLI, Gemini CLI, Antigravity, Devin and other agents, groups sessions by agent and project, and lets you find a past conversation in seconds and resume it in your terminal. It is read-only and nothing leaves your machine. Built in Rust, it runs on macOS, with Linux and Windows in beta.
Added
CLI Agent Orchestrator
AWS Labs tool that coordinates several coding CLIs such as Claude Code, Kiro and Codex as a team, each in its own tmux session.
Added
tty7
A terminal workbench whose shell sessions survive closing the app, built so coding agents can drive other agents' terminals and you can reattach remotely.
Added
Reason Network
A small peer-to-peer daemon that links coding-agent sessions across your team's computers, so Claude Code, Codex, Cursor, Gemini CLI and other agents can see who is working on what and message each other directly, with no server.
Added
Pydantic Deep Agents
Self-hosted terminal AI assistant and Python framework on Pydantic AI, with tool calling, sandboxed execution, multi-agent teams and checkpoints.
Added
Airecon
AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security.
Added
HOL Guard
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
Added
luvus
Mission control for AI coding agents: run, watch, resume and orchestrate Claude Code, Codex, Copilot, opencode and others from one terminal with a live view of each agent.
Added
hax
A minimalist terminal coding agent shipped as a single native C binary using a few MB of RAM, with first-class local models plus OpenAI, Anthropic and OpenRouter support.
Added
Sentry MCP
Sentry's MCP server and CLI that give coding agents access to Sentry issues, errors and traces for debugging.
Added
Libretto
An open-source CLI, debugging agents and browser tools for building and maintaining reliable web integrations, helping coding agents inspect real pages and write automations that keep working.
Added
PiG
PiG is a faithful Go port of Pi, the open-source terminal coding agent, first developed at Hewlett Packard Enterprise. It keeps Pi's behaviour and extension model while shipping as a single fast Go binary, so you can run the same minimal, hackable coding agent without a Node.js runtime.
Added
Concord
Concord lets coding agents message each other and work together in a shared workspace. Agents running in different tools or on different machines can hand off tasks, ask each other questions and review each other's code in real time through its MCP server, so a team of agents can coordinate without you copying messages between terminals.
Added
Pi-Bolt
The Pi terminal coding agent compiled ahead of time into one native executable for Linux, Android (Termux), Apple-silicon macOS and Windows, with no Node.js or Bun needed. It keeps Pi's commands, sessions, providers and extensions while starting about 10x sooner and using far less CPU and memory in the project's published benchmarks. MIT.
Added
agent-manager
agent-manager is a terminal app built on tmux for running many AI coding agents at once. It shows live status for Claude Code, Codex, OpenCode, Gemini, Grok, Cursor and other sessions in a foldable project tree, adds a quick prompt bar, and has a diff reviewer whose line comments are sent straight back to the right agent, on macOS, Linux and Windows.
Added
Pinloop
Terminal job board for coding agents: searches millions of hourly-refreshed postings and has an LLM judge each one against your resume and preferences.
Added
mu
mu is an open-source coding agent with a judgment kernel: a small, fast judge model makes the many routine decisions in each turn so the main model only gets the context it needs. It ships as a command-line tool and a desktop app and aims to keep coding sessions focused and cheap.
Added
Agentic Scientist
Sakana AI's open-source pipeline that turns coding agents such as Claude Code, Codex, Cursor and Gemini CLI into AI scientists: from a task file they propose ideas, run and score experiments and ablations, then write the paper.
Added
Termish
Open source mobile SSH/Mosh terminal for Android and iOS with Herdr integration, SFTP files, remote screen, and native agent chat for Codex-style workflows.
Added
Strands Box
Open source sandbox from the Strands Agents team that pairs OS-level isolation with default-deny Dogwood policies over shell, Python, egress, and MCP calls.
Added
GitKraken MCP
GitKraken's MCP server, via the GitKraken CLI, for managing repos, pull requests and issues across GitHub, GitLab and Bitbucket.
Added
Shipyard
Shipyard, from coss.com, runs Claude Code, Codex and other coding agents on your own dev machines, each task in its own worktree with its own terminals, dev server and live page previews, so agents keep working when your laptop sleeps.
Added
Mirror CLI
Reflection AI's terminal coding agent that reads code, edits files and runs commands in isolated git worktrees, using the open-weight Beam model by default.
Added
Coddo
Desktop app that puts a visual interface and voice input on top of terminal coding agents.
Added
Orke
BOMTOBE's free desktop workspace for Claude Code, Codex and other coding agents: terminal sessions, an in-app browser the agent can use, a Git review window and scheduled AI employees.
Added
Amp
Agentic coding tool for the terminal and editor.
Added
Artil
Artil gives each AI agent its own identity: a real email inbox on Artil's domain or yours, a dedicated US or UK SMS number on the Pro plan, and credential storage for API keys, tokens and 2FA codes it can save from a QR code. Agents use the artil CLI or MCP server to send and read email and texts, sign up for services, handle verification codes and message teammates and other agents on Slack, Telegram and email from one team directory, and Claude Code sessions can be woken by incoming messages. Works with ChatGPT, Claude, Claude Code, Codex, Hermes, OpenClaw and any MCP client; free to start.
Added
CircleCI MCP
CircleCI's MCP servers (hosted and CLI) for diagnosing build failures, inspecting runs and managing CI pipelines from coding agents.
Added
Factory
Agent-native software development platform whose Droids write code, run tests and handle deployments from the IDE, terminal or Slack.
Added
HTML Anything
An agentic HTML editor from the Open Design team. Your local coding-agent CLI (Claude Code, Cursor, Codex, Gemini and others) writes HTML decks, posters, reports and prototypes from 75 skills, shows them in a sandboxed preview, and exports in one click. No API key is needed.
Added
Kilobat CLI
Kilobat CLI is a macOS network diagnostics toolkit with a local stdio MCP server so coding agents can probe DNS, TLS, routes and connectivity from the terminal.
Added
Maeve Social
Maeve Social is a social media management tool with an AI assistant, client approvals and reporting, plus a REST API, CLI and MCP server for automation.
Added
MyShell
Platform to build, share and use AI agents and apps.
Added
NemoClaw
NVIDIA's open-source reference stack for running agents such as OpenClaw, Hermes and LangChain Deep Agents inside NVIDIA OpenShell sandboxes. It adds guided onboarding, managed inference, network policy and lifecycle commands through a CLI.
Added
Pimlico AI
CLI and MCP server that lets coding agents manage a Pimlico smart-account infrastructure account, from balances and logs to sponsorship policies.
Added
Vectoree
Vectoree gives coding agents a backend behind one project key: an OpenAI-compatible model gateway across providers, an MCP tool hub, auth, Postgres and storage, driven by a skill and CLI, pay-as-you-go with no monthly fee.
Added
GitHub repos (103)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| REA ↗ | 410,375 | MIT | 2026-10-30 |
| opencode ↗ | 223,180 | MIT | 2026-10-30 |
| Claude Code ↗ | 153,919 | Proprietary (All rights reserved; Anthropic Commercial Terms of Service) | 2026-10-30 |
| CC Switch ↗ | 150,320 | MIT | 2026-10-30 |
| OpenAI Codex CLI ↗ | 131,661 | Apache License 2.0 | 2026-10-30 |
| Pi ↗ | 118,955 | MIT | 2026-10-30 |
| Gemini CLI ↗ | 108,626 | Apache License 2.0 | 2026-10-29 |
| Understand-Anything ↗ | 88,992 | — | 2026-10-26 |
| rtk ↗ | 85,050 | — | 2026-10-30 |
| HyperFrames ↗ | 75,783 | Apache License 2.0 | 2026-10-30 |
| Open Interpreter ↗ | 68,731 | Apache License 2.0 | 2026-10-11 |
| Warp ↗ | 65,787 | — | 2026-10-29 |
| CLI-Anything ↗ | 57,786 | Apache License 2.0 | 2026-09-22 |
| Aider ↗ | 49,825 | Apache License 2.0 | 2026-05-22 |
| Open Code Review ↗ | 49,071 | Apache License 2.0 | 2026-10-30 |
Top 15 of 103 by stars. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for writing code focused on terminal and CLI agents?
We list 114. The first three by GitHub stars and featured status are REA: MCP server and CLI that lets coding agents reverse engineer native binaries, Electron and JavaScript apps, .NET assemblies and live websites, using Ghidra, Hopper or IDA under the hood.; opencode: Open-source terminal coding agent that works with many model providers.; Claude Code: Anthropic's terminal coding agent that edits code, runs commands and handles git.
Are there free or open-source options?
Yes: 93 open source, 3 source-available, 11 free or freemium, 5 paid, usage-based or enterprise, 2 pricing on the maker's site. Pricing is as each maker states it.
More from writing code
Tools are grouped by what each says it does. Missing one? Submit it free.