Build

Custom Software DevelopmentSystems built to your process

Web Application DevelopmentReact, Next.js, Rails, Django

Mobile App DevelopmentiOS, Android, React Native

App DevelopmentWeb and mobile apps, end to end

SaaS Product DevelopmentMulti-tenant from day one

MVP DevelopmentFirst release in 6–10 weeks

Enterprise SoftwareSSO, audit trails, scale

Connect & operate

API Development & IntegrationREST, GraphQL, webhooks

Cloud & DevOps EngineeringAWS, GCP, Azure, Terraform

QA & Software TestingAutomated suites, load, E2E

Legacy ModernizationStrangler-fig migrations

Cybersecurity EngineeringHardening and remediation

Data EngineeringPipelines, warehouses, reporting

Design & teams

UI/UX DesignInterfaces people finish tasks in

Prototyping & DiscoveryScope before you spend

Staff AugmentationSenior engineers on your team

Dedicated Dev TeamsA full pod, one contract

White-Label DevelopmentEngineering under your brand

Technology ArchitectureDecide once, correctly

Project ManagementDelivery you can audit

Start hereScope a build in one callBring a spec, a wireframe, or a paragraph. You leave with an architecture, a timeline, and a number.Book a scoping call

All software development services →How we price work →Talk to an engineer →

AI software

AI Application DevelopmentFull-stack AI products

AI Agent DevelopmentMulti-step autonomous agents

AI SaaS DevelopmentMulti-tenant AI products

Workflow AutomationReplace manual ops

Custom LLM AppsBranded internal assistants

LLM & data systems

Private LLM DevelopmentSelf-hosted Llama, Mistral, Qwen

RAG DevelopmentCited answers over your docs

MCP & WebMCPMake your systems agent-callable

Vector Database Setuppgvector, Pinecone, Qdrant

Document IntelligenceOCR and extraction pipelines

Vibe coding

AI-Assisted BuildsFast, with senior review

Rapid PrototypingClickable in days

Concept to CodeIdea to working software

Code Review & CleanupMake AI output shippable

Fractional AI TeamOngoing build capacity

Ready to ship?Put AI where the work isAgents, RAG, and private LLMs wired into the systems your team already uses — not a chatbot bolted to a homepage.Discuss an AI project

AI development services →AI readiness checklist →AI vs. traditional development →

Commercial

Financial Services

eCommerce & Retail

Marketing Agencies

Real Estate

Automotive

Regulated

Healthcare & HIPAA

Legal

Government

Education

Banking

By company size

Startups & MVPs

Small Business

Enterprise

Agriculture

Domain firstWe learn your workflow before we model itRegulated, operational, or high-volume — the constraints belong in the schema, not in a training doc.Talk about your domain

Selected workSoftware we own and operateMost agencies show screenshots. We run the products — the same stack, uptime, and on-call we hand to clients.View the portfolio

The DEV.co product network

AI ERP with agents inside the systems you run

AI phone and voice agents for real calls

LLM.coPrivate, self-hosted LLM deployments

Legal AI infrastructure for firms

AI RFP discovery and response drafting

Automatic.coBusiness process automation

CyberAttack.aiThreat detection and defense

Secure AI virtual data rooms

Compare

Custom Software vs. SaaS

In-House vs. Outsourced

MVP vs. Full Product

AI vs. Traditional Development

Tools & reading

Software Cost Calculator

Project Scope Template

Engineering Blog

Open Source

Plan smarterEstimate before you commitCost ranges, scope templates, and the questions we ask in discovery — free, no form.Open the cost calculator

DEV.co

About

Careers

Locations

Contact

Real conversationsTalk with a technical leadNo SDR, no discovery gauntlet. The person on the call is the one who scopes the build.Book a call

AI Frameworks · friuns2

codex-mobile

codex-mobile is a lightweight Node.js web bridge that exposes a Codex AI assistant UI in the browser, running on Linux, Windows, or Android (via Termux). It provides one-command setup with optional Cloudflare tunneling, voice dictation, project import/export, and an optional Telegram bot bridge for chat integration.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/friuns2/codex-mobile

751

GitHub stars

147

Forks

TypeScript

Primary language

MIT

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	friuns2/codex-mobile
Owner	friuns2
Primary language	TypeScript
License	MIT — OSI-approved
Stars	751
Forks	147
Open issues	28
Latest release	v514 (2026-05-17)
Last updated	2026-05-26
Source	https://github.com/friuns2/codex-mobile

What codex-mobile is

TypeScript-based Express + Vue application that acts as a gateway between browser clients and a local Codex app-server instance. Supports WebSocket communication, project ZIP streaming with backpressure handling, and optional Telegram Bot API integration for message routing into mapped Codex threads.

Quickstart

Get the codex-mobile source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/friuns2/codex-mobile.git2cd codex-mobile3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Cross-device Codex access without desktop app

Run Codex UI from browser on Linux/Windows/Android without installing platform-specific desktop clients. Useful for keeping the coding agent in a web context alongside other browser tools.

Headless/remote server workflows

Deploy Codex on a remote box or VM and access the UI from a client device over LAN or tunneled connection. Supports reverse proxies and Tailscale Serve for private HTTPS access (e.g., iPhone Safari).

Mobile-first AI coding on Android

Run Codex in Termux on Android with persistent background support. Enables on-device code generation and AI assistance via hold-to-dictate voice input and mobile-optimized UI.

Implementation considerations

Requires Node.js 18+ and a working Codex app-server install with valid LLM provider credentials (OpenAI, Claude, DeepSeek, Gemini, etc.). No bundled backend; assumes user has Codex environment set up.
Default port is 18923; optional `--no-tunnel` disables Cloudflare tunnel, `--port` flag allows custom binding. Tailscale Serve recommended for private HTTPS access on mobile.
Voice dictation requires microphone permission and browser support (tested on desktop and iOS Safari). On Android Termux, requires persistent background session and battery optimization disabled.
Project export/import handled via ZIP streaming for large projects; imports still buffer once in browser. Chats are rewritten to destination `CODEX_HOME`, project path, and selected model provider.
Telegram bot bridge optional; requires `TELEGRAM_BOT_TOKEN`, `TELEGRAM_ALLOWED_USER_IDS` env vars. Only allowlisted Telegram user IDs can access; bot maps messages to Codex threads.

When to avoid it — and what to weigh

You need offline or air-gapped operation — codex-mobile requires a running Codex app-server and connectivity to upstream LLM providers (OpenAI, Claude, DeepSeek, etc.). No local-only mode is documented.
You require production-grade security infrastructure — No detailed security audit, WAF, rate limiting, or RBAC is documented. Default tunnel uses Cloudflare; authentication relies on Codex app-server layer. Requires careful network isolation for sensitive code.
Your team needs Windows-only or macOS desktop app experience — This is a web UI bridge, not a feature-parity replacement for native Codex desktop apps. Some UX differences and mobile Safari CSS issues are acknowledged.
You need enterprise SLA, support, or compliance guarantees — Project is community-maintained. No commercial support, security certifications, or formal SLAs are documented. Suitable for individual or small-team use only.

License & commercial use

MIT License. Permissive OSI-approved license; allows commercial use, modification, and redistribution with no warranty and minimal attribution requirement.

MIT permits commercial use. However, note that codex-mobile itself is community-maintained with no commercial support or SLAs. If Codex app-server or upstream LLM services require commercial licenses, those must be obtained separately. Recommend legal review of entire stack (Codex app-server + LLM provider terms + codex-mobile) before commercial deployment.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Strong
License clarity	Clear
Deployment complexity	Low
DEV.co fit	Good
Assessment confidence	High

Security considerations

No formal security audit documented. Default Cloudflare tunnel exposes local service to internet with printed password; suitable for personal use but not sensitive code. Codex app-server authentication layer is assumed to be in place. Running in browser via HTTP on localhost is suitable for LAN/single-device use; HTTPS (via Tailscale Serve or reverse proxy) recommended for remote access. Microphone and file upload permissions required; no explicit encryption of project data at rest.

Alternatives to consider

Codex Desktop App (native)

Official Windows/macOS desktop clients with full feature parity, native performance, and official support. Trade-off: platform-specific, requires local install, no cross-device web access.

GitHub Copilot (VS Code extension / Web)

Alternative AI coding agent with IDE integration and web access. Trade-off: different model/provider, less project-centric UI, separate auth/billing.

Cursor IDE or Windsurf

IDE-first AI coding environments with native integration. Trade-off: not browser-based, platform-specific, different UX model.

Software development agency

Build on codex-mobile with DEV.co software developers

Start with `npx codexapp` (requires Node.js 18+ and Codex app-server). For remote or mobile access, consider Tailscale Serve or Cloudflare tunnel. Review security requirements for your use case.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

open-codex-computer-use hermes-desktop langgraphjs

Related on DEV.co

Explore the category and the services that help you build with it.

AI Frameworks AI Development Services AI-powered application development Custom API development with AI assistance Web app development with AI coding tools Talk to DEV.co

codex-mobile FAQ

Do I need to install Codex app-server separately?

Yes. codex-mobile is a UI bridge only. You must have Codex app-server installed and running, with valid credentials for at least one LLM provider (OpenAI, Claude, DeepSeek, etc.).

Can I use codex-mobile on iPhone without Tailscale?

Technically yes if you expose the port via Cloudflare tunnel (`--no-tunnel` is off by default) or custom reverse proxy. However, iOS Safari requires HTTPS for secure context and dictation support, so Tailscale Serve or HTTPS reverse proxy is recommended.

Is the Telegram bot bridge required?

No, it is optional. Set `TELEGRAM_BOT_TOKEN` and `TELEGRAM_ALLOWED_USER_IDS` env vars only if you want Telegram integration. Otherwise, use the browser UI directly.

What happens if Codex app-server crashes?

codex-mobile will fail to communicate with the backend. Restart both Codex app-server and `npx codexapp`. Project state is persisted by Codex app-server; codex-mobile does not store data.

Build it with a software development company

Pairing codex-mobile with the rest of your stack is where most ai frameworks projects stall. DEV.co is a software development agency that does the integration work — plus AI development when models are in scope.

Ready to run Codex in your browser?

Start with `npx codexapp` (requires Node.js 18+ and Codex app-server). For remote or mobile access, consider Tailscale Serve or Cloudflare tunnel. Review security requirements for your use case.

Talk to DEV.co Schedule a Consultation