👤 Written & Reviewed by Bill (Lead Editor) • Aug 30, 2026 • ai-code

Devx Review 2026: A fast terminal AI coding agent for Termux, Windows, macOS, and Linux

Devx is an ultra-fast terminal AI coding agent with dual PLAN/AGENT modes, multimodal vision, a live web server, self-healing diagnostics, and snapshot rollback. Runs on Android Termux, Windows, macOS, and Linux.

Devx

What Devx Does

Devx (Termux-Dev) is an autonomous AI pair-programmer and vibe-coding terminal agent built for Android Termux, Windows, macOS, and Linux. It toggles between a safe PLAN mode (architect and requirements planner) and an AGENT mode (autonomous file edits, terminal commands, auto-installer), with multimodal vision, a built-in live web server, diagnostics, and rollback.

Key Features

Dual-brain PLAN / AGENT modes with one-click plan approval ([🚀 Go / ✏️ Other])
Multimodal vision — paste screenshots from clipboard with smart duplicate badges
Self-healing diagnostics for TypeScript, JavaScript, Python, and Rust, with auto-fix before finishing a turn
Snapshot rollback via /undo reverts the last AI turn cleanly
Universal providers: OpenRouter, Gemini, DeepSeek, Groq, Mistral, OpenAI, Anthropic, Ollama, LM Studio
Project memory bank (.devx/memory.md) and rich slash commands (/serve, /commit, /diff)

Who Should Use Devx

Developers who live in the terminal — especially on Android via Termux — and anyone who wants a lightweight, provider-agnostic coding agent without a heavy IDE. Good for quick fixes, CI one-shot runs, and mobile coding.

Pros and Cons

Pros

Plan/agent split keeps big changes safe while staying fast
Multimodal and self-healing reduce round-trips
Broad provider support and MIT licensing

Cons

Android/Termux-first heritage shows in the defaults
Needs an API key for any model
Terminal workflow has a learning curve

Pricing

Free and open source under MIT. You pay only for the model provider’s API usage.

FAQ

Can it run headless in CI?

Yes — devx -p "fix build errors" --yolo runs one-shot for scripts and CI/CD.

Which OSes are supported?

Android (Termux), Windows, macOS, and Linux via npm-style or source install.

Explore the best AI Coding tools

All AI Coding rankings → Cursor Lobsteady Cate OpenAI Codex

Aether Review 2026: Turn Your AI Subscription Into a Fleet of Devboxes

Aether (runaether.dev) turns the AI subscription you already pay for into parallel cloud devboxes where an agent streams every command, opens a PR, and another agent reviews and fixes it until the code holds up. We review the loop, the receipts, and the pricing.

agent-run Review 2026: Run Coding Agents in a Tiny Sandbox That Catches Mistakes Before They Spread

In-depth review of agent-run — a sub-1MB standalone binary that sandboxes coding agents (Claude Code, Codex, OpenCode, pi) inside a Bubblewrap container. Host filesystem is read-only by default. Built to catch agent mistakes, not malware.

Best AI Agent Tools in 2026: From Coding Assistants to Autonomous Workers

Complete guide to AI agent tools in 2026 — Claude Code, Codex, Cursor, Manus, and more. Which agents actually deliver on the promise of autonomous work?

Faultsense Review 2026: The expect() Without the Page

Faultsense is a zero-dependency browser agent that runs end-to-end assertions against real user sessions in production. We review how fs-* attributes work, RUM-style testing, and who should adopt it.

Subscribe to the 9bests weekly — get the full list free

Hand-picked AI tool reviews and updates every week. Subscribe to receive this full list + 7 more quick-reference sheets (writing / image / video / audio / chat models / data / API cost).

Subscribe free & get it →

Independent reviews — ratings aren't influenced by vendor payments · double opt-in · unsubscribe anytime