CorX Labs
Android app Version 1.9.15 Free APK download Free AI models, no key Speaks Patois Made in Jamaica

Automa

Your AI company, in your pocket. Hire AI agents, chat with them like teammates, hand them tasks, let them build apps, draw pictures and search the web, and approve anything that matters. On free AI models with no key, no account and no card, or on your own Claude, GPT, Gemini, DeepSeek and Grok keys.

Version 1.9.15 · Android 8.0 or newer · Signed APK, 25.3 MB · Made in Jamaica by Nathan, CorX Labs

Automa home screen: free models saved $0.30, Working late with two things that need you, and the Needs you list
HomeWhat needs you, who is working late, and what the free models saved.
Moan answering in Jamaican Patois with a checklist for registering a small bakery in Kingston with the Companies Office of Jamaica
Moan, in PatoisAsked in Patois how to register a bakery, Moan answers in Patois.
Pixel's reply with a generated flat-style logo of a golden Jamaican beef patty for Yaad Bites
A drawn logoThe paired image model draws a logo from a description.

What Automa is

Automa is an Android app from CorX Labs, made in Jamaica, that runs a whole company of AI agents for you. You create an organization with a goal, hire agents into an org chart, give them work in plain words, and watch them plan it, do it and check in when they need you. Every task traces back to the organization’s goal, hires, budgets and plans wait for your approval, and every token is counted against a budget with a hard stop.

The agents work on an Automa server you control: your computer, a cloud machine, or the phone itself inside the free Termux app. Nothing sits in the middle: no Automa cloud account, no ads, no tracking. And it runs on free AI models with no key, no account and no card, including Moan, Automa’s own Jamaican model that talks Patois.

Automa 1.9.15 is here to download. Get the signed APK from this page: 25.3 MB, for Android 8.0 or newer. It has also been submitted to APKPure, and will be released there once APKPure finishes its review. Download and install.

Latest version
1.9.15 · 22 Nov 2026
First version
1.0.0 · 27 Sep 2026
Platform
Android 8.0 or newer
Storage
About 100 MB
Free AI models
20+ chat, 2 image · no key
Your own models
Claude, GPT, Gemini, DeepSeek, Grok, Kimi & more
Server
Your computer, a cloud VM, or this phone
Account
None: no Automa cloud
Package
com.corxlabs.automa
Download
APK here · APKPure pending review

The titles Automa holds

What Automa is, in the words people search for, each one something the app can back up.

One of Jamaica’s first AI agent apps

An Android app built in Jamaica for running a whole company of AI agents (hiring them, giving them work, and approving what they do) from a phone. A Jamaican AI agent platform that fits in your pocket.

Made in Jamaica, by a 14-year-old

Designed, built and shipped by Nathan Lyttle, the 14-year-old founder of CorX Labs, working alone in Jamaica.

From the lab behind Jamaica’s first open-weight LLM

CorX Labs also built CorX3.8-27B, Jamaica’s first large open-weight language model, and the NatureV1 hurricane model.

A Jamaican AI that speaks Patois

Moan answers in Patois first, and reads Jamaican news, law and government sources into a live index so every reply cites source, date and link. Meet Moan

A whole AI company on one phone

The server the agents work on can run on the phone itself, in Termux: no computer and no cloud bill. How

Free AI with no key, account or card

Twenty-plus free chat models and two free image models, ready the moment the app opens. The list

An app studio in your pocket

Build, run and share apps in 69 languages with an AI pair or an AI team, from the phone. App Studio

36 versions in eight weeks

From 1.0.0 on 27 September 2026 to 1.9.15 on 22 November 2026. Every release

Security-checked in 16 areas

Version 1.9.6 was a full audit of the app across 16 areas, with every confirmed finding fixed. Security

Automa by the numbers

Free chat models
20+
Free image models
2
App Studio languages
69
Versions in 6 weeks
25+
Areas audited
16
Free AI calls at once
10
APK size
22.9 MB
Android
8.0+

What Automa does, in one minute

  • Hire AI agents with a role, a title, a manager and a model, a whole team in one tap from the teams catalog, or one agent at a time.
  • Chat with them like teammates: replies stream in, their thinking shows in a panel, they search the web and cite sources, read your attachments, draw pictures, and make real Excel, PowerPoint and Word files.
  • Give them tasks. Every task has one owner, a plan, a history and a cost. Agents ask you questions right in the task when they need a decision.
  • Approve what matters. Hires, budgets, plans and anything an agent gets stuck on wait for your yes in the Inbox. Agents never spend or hire on their own.
  • Build apps on the phone. App Studio writes, runs, previews and shares apps in 69 languages, with an AI pair or an AI team, and undo for every change.
  • Use free models. Twenty-plus chat models and two image models that need no key, including Moan, which talks Patois and knows Jamaica’s news, law and government.
  • Bring your own models too: Claude, GPT, Gemini, DeepSeek, Grok, Kimi, Cursor, Codex, Gemini CLI, OpenCode and any OpenAI-compatible endpoint.
  • Run coding terminals (Claude Code, Codex, Gemini CLI) on the device, and take apps apart with App Inspector.
  • Count every token. Costs by agent, by task and by month, hard budget stops, and what the free work would have cost at paid prices.
  • Keep it yours. Organizations, chats and files live on your own server, which can be the phone in your hand.

Every kind of AI work, from one phone

Automa is not one chatbot. It is a team of agents that each have a job, and between them they cover most of the AI work a small business, a student or a developer does in a week.

Research with sources

Agents search the web across many results, read and crawl pages, and answer with tables and linked sources. Chats

Writing and marketing

Launch posts, Instagram and WhatsApp captions, emails and plans: written as tasks you can read and approve. Tasks

Spreadsheets, decks, documents

Real Excel files with formulas, PowerPoint decks with charts and pictures, and Word documents, and they read the ones you attach. Free models

Pictures and logos

A paired image model draws from a description, or redraws an attached photo with the change you ask for. Pictures

Apps and websites

App Studio builds, runs and shares apps in 69 languages, with an AI that sees the page and fixes what breaks. App Studio

Coding terminals

Claude Code, Codex, Gemini CLI and OpenCode in their full terminal UI, on the phone. Terminals

Running the work

Projects, goals, routines on a schedule, approvals and budgets, the plumbing of a company, run by agents. Projects

Jamaican knowledge

Moan answers in Patois and knows Jamaica’s news, government, courts and statutes, with source, date and link. Moan

Who Automa is for

Small businesses

A shop, a bakery, a salon: agents check prices against the market, write the posts, draw the logo and work out how to register the business. An example

Students

Research with sources, spreadsheets, decks and documents, and an app studio to learn to code in, on free models, with no card.

Creators and marketers

Captions, launch posts, pictures and logos, and routines that run the weekly work on a schedule.

Developers

Claude Code, Codex and Gemini CLI in a terminal on the phone, App Studio, App Inspector, and any OpenAI-compatible endpoint. Terminals

Made in Jamaica, ready for the Caribbean

Most AI tools assume a US-dollar credit card, a desktop computer and an English that is not the one spoken at home. Automa was built in Jamaica, and it shows in three places.

No card, no key

The free models need no key, no account and no card. A first agent can start on them with one tap, Skip for now: start on the free models, and you add paid keys later only if you want them.

One phone is enough

The Automa server can run on the phone itself, inside Termux. No computer, no cloud bill: the app, the agents’ server and your data all live on one Android phone.

An AI that talks like home

Moan speaks Patois first and switches to Standard Jamaican English for formal documents and code. It knows Jamaica’s history, government, courts, statutes, economy and culture.

Moan, Automa’s Jamaican model

Moan runs on Nemotron 3 Ultra with a Jamaica primer and a living knowledge index. While Moan is in use, Automa keeps reading Jamaican sources (the Gleaner, the Observer, JIS, the Office of the Prime Minister, Parliament, the Bank of Jamaica and the Laws of Jamaica) into a local, searchable index. Every reply gets the passages that match the question plus the newest news, with source, date and link.

Elsewhere in the Caribbean, the same agents search and read the web with sources, so a question about Trinidad and Tobago, Barbados, Guyana or the Bahamas gets a researched, linked answer too. Moan’s built-in index is the Jamaica-specific part.

A Kingston bakery, run by three agents

The screenshots on this page come from a sample organization: Yaad Bites, a family bakery in Kingston selling patties and hardo bread, with the goal Grow Yaad Bites online. It runs three agents. Moan is the Jamaican assistant, and answered a Patois question about registering the business. Nova, the marketing lead, checked patty and bread prices against the market and wrote the launch post for the order page. Pixel, the brand designer, drew the logo.

Moan answering in Jamaican Patois with a checklist for registering a small bakery in Kingston with the Companies Office of Jamaica
Moan, in PatoisAsked in Patois how to register a bakery, Moan answers in Patois.
Nova answering a request for popular Kingston bakeries with a table of bakeries, popular items and typical prices
Web searchAn agent searches the web and answers with a table.
Nova's finished reply on a task: two caption options for Instagram and WhatsApp
Finished workThe agent's reply lands on the task, ready to approve.
Pixel's reply with a generated flat-style logo of a golden Jamaican beef patty for Yaad Bites
A drawn logoThe paired image model draws a logo from a description.
Organization settings for Yaad Bites, a family bakery in Kingston
SettingsName, goal, logo, budget and governance.

More AI built in Jamaica: CorX3.8-27B, a 27B Jamaican Patois assistant and the island’s first large open-weight language model, and NatureV1, a research model for Caribbean hurricanes.

Get started

  1. Install the APK: see Download and install.
  2. Connect. Enter a server address such as http://192.168.1.20:3100, or tap Run Automa on this phone and the app sets up a server inside Termux, with a progress bar for each step. A computer can also be linked over a USB cable or Wireless debugging.
  3. Create an organization with a name and a goal.
  4. Hire your first agent. Pick a name, a role and a model, or tap Skip for now: start on the free models.
  5. Say what you want done in Chats. The agent plans, creates tasks and asks when it needs you.
  6. Take the tour. One card per section, with Skip at every step; run it again any time from your profile.
Automa's connect screen: a server address field, Connect, and Run Automa on this phone through Termux
ConnectPoint the app at a server, or run one on this phone.
Meet your next agent: the hiring wizard asking for an agent name
Hire an agentA short wizard: a name first, then the engine.
Organizations list with Fox Studio and Yaad Bites
OrganizationsMore than one company on one server.
Welcome to Automa: the first card of the 16-card feature tour
The tourOne card per section, skippable at every step.

Getting around

A bottom tab bar (Home, Chats, +, Tasks, Files) stays in thumb reach, a sidebar holds every section and the organization switcher, the bell opens the Inbox, and your avatar opens the account sheet. Long-press the app icon for shortcuts: New chat, New task, App Studio, Change server, Files. Every screen is edge-to-edge, keyboard-aware, and works in portrait and landscape on phones, tablets, foldables and Chromebooks. Destructive actions come with Undo, not “are you sure?” dialogs.

Home is your day at a glance: what needs you, who is working right now, what the free models saved, and live run activity.

Automa home screen: free models saved $0.30, Working late with two things that need you, and the Needs you list
HomeWhat needs you, who is working late, and what the free models saved.
Live agent runs list with Nova's finished runs on the launch post task
Live agent runsEvery run, active first, then the most recent.

Chats with your agents

Talk to an agent like a teammate. Replies stream token by token; the model’s thinking streams into its own panel and folds away when the answer starts. Tables wider than the screen scroll sideways. Source links show the site’s favicon. When a reply fails, the chat says why in plain words, and you can switch model and send again.

Chats screen listing three agents, Moan, Nova and Pixel, each with its model, and a Hire an agent button
ChatsEvery agent in one list, with its model and what it is doing.
Nova answering a request for popular Kingston bakeries with a table of bakeries, popular items and typical prices
Web searchAn agent searches the web and answers with a table.
A wide comparison table in a chat reply, scrolling sideways
Sourced answersWide tables scroll sideways; sources show their favicon.
Moan answering in Jamaican Patois with a checklist for registering a small bakery in Kingston with the Companies Office of Jamaica
Moan, in PatoisAsked in Patois how to register a bakery, Moan answers in Patois.

Pictures. Ask any free chat model for a picture and its paired image model draws it. Attach a photo and say what to change, and the model redraws it. Tap a picture to see it full size or Download it to the phone; Draw again asks for a fresh take.

The model switcher in the chat header lists every provider with its key status and the maker’s logo, a Free filter, thinking depth (Auto, Quick, Balanced, Deep, Deeper, Max), and switches for what a free agent may do: web search & reading, files & commands, teammates & tasks, connected apps. A paired image model gives a chat model the power to draw; a small “Bonded” mark shows the two makers’ logos together.

Pixel's reply with a generated flat-style logo of a golden Jamaican beef patty for Yaad Bites
A drawn logoThe paired image model draws a logo from a description.
Model switcher sheet showing thinking depth, the agent's tool switches and SDXL Lightning bonded as the paired image model
Model switcherThinking depth, tool switches and a paired image model.
Free models list in the model switcher: Nemotron, DeepSeek V4.1 Flash, Gemma 4 and Qwen 3.8, each marked Free
Free modelsThe free list, each model marked Free with its status.

Messages. Copy, retry, delete and thumbs up or down on the newest reply; press and hold any other message for the same menu. Attach photos, screenshots, PDFs or any file with +. Unsent drafts survive leaving the chat. ⋯ on a chat pins, moves or deletes it.

Slash commands: /plan (plan first; nothing runs until you say so), /ask (answers only, no changes), /auto, /model, /think deep, /context, /stop, /clear, /skills, /help, /new.

Notifications. When an agent finishes a reply, or an App Studio job ends, while you are outside the app, a notification says so. Tap it to jump straight to that chat, task or project.

Free AI models: no key, no account, no card

Pick a free model in the switcher and the agent runs on it; your other models stay where they are. Every model stays listed and says how it is doing: ready, busy, at today’s free limit and when it is back, or closed by its provider. Nothing is hidden. On 17 November ten free versions were offline at their providers, DeepSeek V4.1 Flash’s among them. From 1.9.15, Check on Terminals and in the chat’s model picker asks every free model for one word and marks the ones closed at their provider.

The free models in Automa 1.9.15
KindModels
Chat Moan (Jamaican, on Nemotron 3 Ultra) · Nemotron 3 Ultra 550B · Nemotron 3 Super 120B · Nemotron 3 Nano Omni 30B Reasoning · Nemotron 3.5 Lightning · Nemotron 3.5 Super VL · Nemotron 3.5 Content Safety · DeepSeek V4.1 Flash · Gemma 4 31B · Gemma 4 26B A4B · Qwen 3.8 27B · Qwen 3.8 27B Abliterated Cyber · Inkling · Inkling Small · Flint v1.0 · North Mini Code · Atria Dawn Preview · Apodex 1.1 Mini · LFM 2.5 2.6B · Xing 4.0 29B A4B · Ternary Bonsai 27B · Ling 3.2 Flash · ERNIE 5.5 Flash Preview · Particle 1 · LFM3 1.7B · Free Router, which sends each question to an available free model
Image SDXL Lightning (fast, the default pairing) · SDXL Base 1.0

What a free agent can do

Search the web across many results, read pages, crawl a site and download files; read, write, edit and search files and run commands in its workspace; make real Excel spreadsheets with formulas, PowerPoint decks with charts and pictures and Word documents, and read the spreadsheets, documents, decks, PDFs and CSVs you attach; draw with its paired image model; message teammates, hand off work, and create and update tasks; and request the connected apps it needs. It knows its role, its teammates and your name, and it keeps going through busy providers and dropped connections without ever switching models behind your back.

The Que engine sits under every free-model call: up to ten calls at once, at most two at a time on any one model, a pool of app IDs that grows on rate limits, retries on busy answers, a five-minute answer cache, conversations and batches. Many questions at once all get answered instead of some failing.

Tasks, approvals and the Inbox

Everything the agents are doing, each one a thread you can read, steer and approve. A task has one assignee, a parent and sub-tasks, blockers, comments with @mentions, a plan document, attachments and work products, labels, a priority and a status : backlog, to do, in progress, in review, blocked, done. The task page shows the live run with the agent’s thinking and tools, its cost and its full history. An agent can ask you a question with options right in the task; pick one and it carries on. When it finishes, it asks you to approve the result: approve to mark the task done, or send it back with what to change.

Task list with to do, working, review and done counts and three tasks for the bakery
TasksCounts by status, filters, and every task with its owner.
Task page for writing the launch post for the order page, with the brief and Nova's reply
A task's threadThe brief, the agent's work and the full history.
Nova's finished reply on a task: two caption options for Instagram and WhatsApp
Finished workThe agent's reply lands on the task, ready to approve.
New task sheet with title, assignee, project and description fields and a Create Task button
New taskTitle, assignee, project and a description.

Inbox and approvals. Decisions waiting on you: hires, budgets, plans, join requests, failed runs and anything an agent got stuck on. Approve, decline or retry from the phone. The bell shows the count and clears when tapped. The Decisions page keeps the record of every automated and governed decision.

Inbox listing tasks that need attention, including one that needs recovery
InboxWhat needs you, with Retry on a run that failed.
Decisions screen listing a recovery and a blocked dependency for today
DecisionsThe record of every automated and governed decision.

Agents and the org chart

Each agent has a role and title, an engine and model with the maker’s logo, a system prompt and instructions, a budget, skills, tools and a manager. The agent page shows its live runs, logs, progress, instructions and tools. Pause, change or offboard an agent any time. New agent is a short wizard; the teams catalog installs a whole team, a CEO with executives and engineers, in one go.

Engines: Claude Code · Anthropic API · Codex · Cursor (local and cloud) · Gemini CLI · Grok · Hermes · Kimi · OpenCode · OpenClaw gateway · Pi · Free models · metered API engines · a REST or webhook engine for an agent you host elsewhere. On a phone, a Claude agent answers through the Anthropic API with Claude Code’s own tools running in Termux.

Agents list with Moan, Nova and Pixel and counts of agents working, paused and needing attention
AgentsYour team, with who is working, paused or needs you.
Nova's agent page: latest run succeeded, role CMO, title Marketing lead, reporting to the board
An agent's pageLatest run, identity, role and runtime.
Org chart for the organization with Moan, Nova and Pixel
Org chartWho reports to whom, as a tree or a chart.

Projects, goals and routines

Projects group tasks under one goal and keep their own workspace. Goals are the top of the task tree, the “why” every task hangs from. Routines run work on a schedule, a daily summary, a weekly review, and each run is a task you can read. Pipelines chain stages of work, cases collect related work into one file, and workspaces show where an agent’s run happens, with its live service ports.

Projects list with Launch the order page in progress
ProjectsTasks grouped under one goal.
The Launch the order page project with its three tasks
A projectIts tasks, with filters and recovery flags.
Goals screen with the company goal Grow Yaad Bites online marked active
GoalsThe top of the task tree.
Routines screen with a weekly orders summary routine
RoutinesRecurring work that turns into auditable tasks.

Artifacts and your phone’s files

Artifacts are every file the agents produced, grouped by task, with a viewer for text, images and code. Downloads go to Downloads/Automa.

Files shares one folder on the phone with your agents. With auto-send on, a file an agent asks for is sent without asking; otherwise the request waits for you to pick a file or decline. Agents can send files back. Use Share to Automa from any app’s share sheet and the file waits on the Files page until you confirm.

Auto-send removes you from the loop, that is the feature and the risk. With it off, every file leaves the phone because you tapped Send. With it on, anything inside the shared folder can leave without a decision at the moment it happens. Share a folder that exists for this, not your whole Documents tree.

Artifacts screen showing the generated Yaad Bites logo
ArtifactsEvery file an agent made, grouped by task.
Files screen: connect this browser, file requests from agents, and Send a file
FilesAgents ask your phone for files; you approve or auto-send.

Skills and connectors

Skills are what agents know how to do. Install them from the catalog or build one in Skill Studio; a new skill is available from the agent’s next run. Connectors are the apps agents can reach: GitHub, Slack, Gmail, Notion and more. You choose which agents get access, which accounts they use and which actions they may take : three choices, not one switch. Connecting an app stays inside Automa.

Installed skills list including AgentMail and First task
SkillsWhat agents know how to do.
Connectors screen: give your agents the access they need, with Airtable and Anthropic connectors
ConnectorsGmail, GitHub, Notion, Slack and more, scoped per agent.

App Studio: build apps from your phone

Build, run and share apps with an AI pair, or a whole AI team, that writes the code and fixes what breaks. No key needed: the free models work in the AI panel and for the editor’s code suggestions.

  • 69 languages in 11 groups, with quick starts for a website, Python, a full-stack app, React, Flask, Go, Rust, a mobile app and TypeScript.
  • Describe your app in plain words and the assistant builds it from the first message, or clone from GitHub by pasting a link.
  • On a phone each part is a tab: Files, Code, Console, Preview, AI, Stats, Team. The editor saves on its own and suggests code as you type.
  • Preview runs the app inside Automa, sandboxed. One tap opens a public link anyone can open. Missing toolchains install on the device with progress.
App Studio home with quick starts for a website, Python and a full-stack app
App StudioBuild, run and share apps in 69 languages.
App Studio file tree with index.html, script.js and style.css
Project filesThe file tree with each file's kind, size and age.
App Studio code editor showing index.html with AI suggest on
The editorCode with AI suggestions as you type.
App Studio preview running Hello, world with a Set up public links button
PreviewThe app runs inside Automa; one tap makes a public link.

The AI assistant reads and searches the files, writes and edits code, runs commands and tests, starts and stops the app, reads the console, searches the web, and keeps going until the job is done. It sees the page like you do: it opens the running page at phone or desktop size, reads what is on screen, the console errors and the layout trouble, fixes what it found and looks again.

AI teams. Pick teammates in the model sheet and the lead model hands them work: several at once, each with a role and the files it owns, talking to each other while they work. The Stats tab shows a running clock, steps, files changed and every model at work with live tokens, then the totals and what the free work would have cost.

Undo and safety. Undo any change the assistant made, step by step. Checkpoints are saved before every AI message, Stop is instant, and nothing is ever written outside the project folder. Build together: invite people with a join code or link, for an hour up to no limit. Guests see your code as you type, chat, send files and suggest changes you review as a diff; they can’t save files or reach the rest of Automa.

App Studio AI panel on a free model with thinking modes and suggested prompts
The AI panelDescribe what to build; it writes, runs and fixes it.
App Studio Stats tab while the AI works: models, tokens, cost and steps
Stats, liveA team of models at work, with live tokens.
App Studio Stats totals with tokens per model and the latest moves
Stats, totalsTokens per model and what the work would have cost.
Build together sheet for inviting people to an App Studio project
Build togetherInvite friends by code or link to watch and suggest.

Terminals and App Inspector

Terminals give you a real coding terminal on the device: Claude Code, Codex, Gemini CLI, OpenCode and others in their full terminal UI, on a Debian layer the page sets up for you. Wire a terminal to an agent so it works with that agent’s key, pick a model per tool, or open the free models chat with nothing to install.

App Inspector takes an app on your phone, or any APK, apart: it decodes the manifest, resources and code, shows the code as Java, lets you search, edit and ask Claude to explain any file, and rebuilds a signed APK to your Downloads. It is for apps you made or are allowed to analyze.

Terminals screen with a free models chat, Claude Code ready, Codex and Gemini CLI
TerminalsClaude Code, Codex and Gemini CLI on the device.
App Inspector with an APK button and the list of apps on the phone
App InspectorDecode an app, read it as Java, rebuild it.

Costs, budgets and usage limits

Every token is counted: agent runs, chats, App Studio replies and code suggestions land on Costs by agent, by task and by month. The organization and each agent have a budget, and a hard stop pauses spending at the limit. The usage limits card shows how much of the free models’ monthly allowance is used and when it renews, each free model’s daily limit with a countdown, and Claude’s session and weekly limits when Claude Code is signed in. The free models card on Home and Costs shows what the free work would have cost at paid prices.

Costs screen with free models saved and month-to-date filters
CostsEvery token counted, by agent, task and month.
Usage limits card: monthly allowance for the free models and per-model availability
Usage limitsThe free allowance and each model's daily limit.

Search, audit and the timeline

Search finds tasks, comments, plan documents, artifacts, agents and projects in one place. Audit holds the log of everything that happened, who did it and when, with the runs, costs and budgets behind it. The work timeline shows every agent’s runs side by side.

Search screen: type to search organization memory
SearchTasks, comments, plans, artifacts and agents in one search.
Audit screen with activity filters for agents, users, actions and dates
AuditEverything that happened, who did it and when.
Work timeline with runs, agents and run time
Work timelineEvery agent's runs side by side.

Settings and your profile

Organization settings: general (name, goal, logo, budget), members and access (invites, roles, join requests), API keys (one place for the keys agents, chats and App Studio run on, with a monthly spending limit) secrets, adapters, environments, plugins and Experimental switches. The account sheet shows your profile, your API balance, the tour, the dark theme and sign-out, and About Automa keeps the full version history.

Organization settings for Yaad Bites, a family bakery in Kingston
SettingsName, goal, logo, budget and governance.
API keys settings with a monthly spending limit and Add a key for Anthropic and OpenAI
API keysOne place for your keys, with a monthly limit.
Experimental settings with Agent Chat switched on
ExperimentalOpt into features still being evaluated.
Account sheet with the board profile, balance and the Yaad Bites organization
AccountYour profile, balance and the organization sheet.

Automa words, explained

The terms Automa uses, and what each one means
TermWhat it means
AI agentAn AI model given a job, tools and the freedom to take steps on its own. In Automa every agent is an employee: a role, a title, a manager, a model, a system prompt, a budget and skills.
OrganizationOne company: a goal, agents, tasks, a budget and settings. One server can host several, and every page is scoped to the current one.
AdapterHow an agent runs: Claude Code, Codex, Gemini CLI, Grok, Hermes, Kimi, OpenCode, Pi, the free models, a metered API, or a REST or webhook adapter for an agent hosted elsewhere.
TaskA unit of work with one assignee, a parent, sub-tasks, blockers, comments, a plan document, attachments and work products, and a status that moves through review and approval.
ChatA conversation with one agent: technically a task in conversation mode, so it keeps the same history, attachments and cost tracking.
ApprovalA governed action waiting on you: a hire, a budget, a plan, or anything an agent got stuck on. Agents never spend or hire without a yes.
RoutineWork that runs on a schedule, such as a daily summary or a weekly review. Each run is a task you can read.
Project and goalProjects group tasks under one goal; goals are the “why” the whole task tree hangs from.
ConnectorAn app agents can reach, such as GitHub, Slack, Gmail or Notion, with per-agent access and per-action permissions.
SkillSomething agents know how to do, installed from the catalog or written in Skill Studio.
WorkspaceThe checkout or sandbox where an agent’s run happens, which can expose live services such as a dev server.
ArtifactA file an agent produced, attached to a task and downloadable from Artifacts.

How it is wired

Three parts, and it matters which one is where. The phone holds the app and one shared folder, the whole board UI ships inside the APK, so the layout is the same whatever server it talks to. The server holds the agents, their tasks and their routines, and does the work. The connections are how the server reaches services that are not yours to host. Solid lines carry work outward; dashed lines are the three things that come back to you.

How Automa is wired: phone, agent server, and scoped connections On the left, the phone runs the Automa app and shares one folder. It connects to an Automa server on port 3100, which is either that same phone running in Termux or a computer or cloud machine. The server holds the agents, the task list and the routines, and reaches outward through per-agent scoped connections to services such as Gmail, GitHub, Notion, Slack and provider-hosted MCP endpoints. Three things flow back to the phone along dashed lines: approvals that need a human decision, file requests against the shared folder, and inbox messages. The company runs here Comes back to you Your phone Automa Home · Chats · + · Tasks · Files one shared folder Sees what needs a human. Does not run the agents. Automa server Port 3100 Either: • this phone, in Termux • a computer or cloud VM Holds the agents, the tasks and the routines. Agents Named roles Moan: Jamaican assistant Nova: Marketing lead Pixel: Brand designer free models or your own keys Work Tasks one unit, one owner, one state Routines fire, and materialise a task scoped Connections What agents may touch Gmail GitHub Notion Slack Airtable: provider-hosted MCP Three choices per connection which agents, which account, which actions. Needs a decision Approvals hires, budgets, plans nothing proceeds until you say Needs a file File requests against the one shared folder you send, or auto-send does Needs reading Inbox what the agents finished, and what they could not raises The shared folder never leaves the phone. A file does, one request at a time, and that is the one place where turning a switch on removes you from the loop.
Work going out Coming back to you The phone is the control surface, not the runtime
How Automa is wired. The app connects to an Automa server on port 3100, which may be the phone itself, in Termux. The server holds the agents and their work and reaches outward through connections you scope per agent. Three things come back: approvals, file requests, and the inbox.

Running Automa on the phone

No computer needed. Install Termux from F-Droid, tap Run Automa on this phone in the app, and paste the command Termux is given. The installer sets up Node.js and PostgreSQL, the server and an automa command, then starts Automa on 127.0.0.1:3100, locked to the app. The first install downloads a few hundred packages and takes 10 to 45 minutes; updates are much faster.

Automa commands in Termux
CommandWhat it does
automa runRun in the foreground, restarting the server if it stops
automa start · stop · statusRun in the background, stop it, check it
automa updateUpdate the server; it backs up the database first
automa backup · restoreSave a database backup now, or put one back
automa linkHand the app key to the Automa app again
automa adb linkLet agents drive the phone over adb: tap, type, screenshot

The app starts Automa for you when it isn’t running and shows Automa is starting over your page while the server comes up. Backups are made every hour while Automa runs and before every update, and a restore never loses the database. Set Termux’s battery use to Unrestricted; with Termux:Boot, Automa starts when the phone boots.

Security and privacy

  • Your data stays with you. Organizations, tasks, chats and files live on your own Automa server. The app talks to the server you connect it to, and to Google only for sign-in and push notifications when those are set up. Free-model requests go from your server to the free AI service Automa uses, and agents’ web searches go to DuckDuckGo, or to Bing when DuckDuckGo refuses.
  • Locked to the app. On a phone, Automa answers only the Automa app, with a key the installer makes; the app proves the server holds that key before ever sending it, and never sends it to another program on the phone.
  • Agents see only what they should. Agents and terminals never see the server’s database password or sign-in secret, every organization’s data is kept separate, and keys saved in App Studio are encrypted on your server.
  • Sandboxed previews. App Studio previews can’t act as you or reach the rest of Automa, and free agents’ web tools never reach private or local addresses.
  • Governed by you. Hires, budgets and plans wait for your approval; budgets stop spending; invites can’t give more than the person who made them has.
  • Hard to tamper with. Release builds are signed and obfuscated, and signing keys never ship in the APK.

Download and install

You need Android 8.0 or newer, about 100 MB of storage, and internet for the AI features.

Signed APK · 25.3 MB · Android 8.0 or newer · package com.corxlabs.automa · version code 37

SHA-256 e6acca41e926446a7331c56787b5438bc9276b4511f21bb895c1ced84c2faa7d

APKPure listing pending review. Automa has also been submitted to APKPure. Once APKPure is done reviewing it, it will be released there too, so updates can arrive on their own. Until then, this page is the download. There is no Automa cloud account to create, ever. Follow @corxlabs on X to hear when it goes live there.

  1. Download the APK with the button above, on the phone itself, or on a computer and then copy it across.
  2. Open the downloaded file. If Android asks, allow Install unknown apps for the app you opened it with.
  3. Tap Install, or Update. Every release from 1.8.2 on is signed with the same key, so a new version installs over the old one and keeps your sign-in, settings and data.
  4. If your server runs on the phone, run automa update in Termux after updating the app so the server matches it.

What’s new

1.9.15, 22 November 2026. IMY comes to Terminals. IMY (Imagenery) is a strict compiler for code you write your own way: the first line says what you are building, in a header such as # ("adds two numbers and shows the sum"), and under it you write each step in a syntax you make up. IMY checks it, turns it into another programming language and runs it, and never changes your file. It converts as you type: each line you enter is checked at once, and the result appears above the line you are typing. A second menu on the IMY tile picks the language your code becomes: Python, JavaScript, Ruby, Rust, C, Go, Assembly and thirteen more. IMY knows 48 languages, and builds and runs 42 of them when the language’s own tool is installed. :import takes in a project you already have, at most 25 files of up to 40 kB each, so your code can use its functions and variables by name; Python files are read on the device, other languages by the model with every answer checked against the file, and none of the project’s code is run. A program its own build tool refuses goes back to the model to be corrected before anything runs. IMY stops and names the lines at an English request in place of code, at anything used before the line that defines it, and at a line it cannot be sure about. The first tap on the IMY tile installs it (inside the Linux layer on a phone); the next opens its console, with nine ready programs to start from. It works with Automa’s free models with no key, and the model you pick is the one used: one that is not being served says so instead of quietly using another. Your own Anthropic, OpenAI or Gemini key works too, and anyone can install IMY on a computer with pip. A Check button on Terminals and in the chat’s model picker asks every free model for one word and marks the ones closed at their provider; one that was only busy is counted apart and left unmarked. One more free model, LFM3 1.7B. Fixed: a terminal starts at the width your screen shows, so a tool’s first lines no longer break mid-word on a phone; Running now lists only terminals still running (one whose program had ended stayed there for a minute); a tool that finishes installing in the background turns Ready by itself; the installer’s messages fold between words on a narrow screen. It installs over 1.9.14 and keeps your data; the APK is 25.3 MB, up from 25.1 MB. Checks before release: IMY’s 570 tests, the board’s 7,399, and the APK’s own server bundle installed the way a phone installs it and walked through at phone size from an account that never had IMY. The free models’ key is readable in none of the APK’s 16,853 files.

1.9.14, 18 November 2026. Automa in your language. Account, Language offers Auto and 40 languages. Auto follows your phone’s or browser’s language and finds your country from its time zone, with nothing looked up online; dates, numbers and times follow your language and country, and 23 formats stay in US English on purpose, such as dollar amounts and chart axes. The main screens’ 210 strings are built in for every language; the rest of the board is translated by Automa’s free models the first time a screen opens, and kept on your server for everyone on it. Only Automa’s own wording is sent for that, never your chats, tasks, names or files, and your own words are never translated. Arabic, Persian, Hebrew and Urdu read right to left. Agents write to you in your language, and answer in another one if you write in it; Moan keeps Patois for English. The app follows the choice too: the whole connect screen in every language, and on Android 13 and newer the app’s own notices, shortcuts and notification channel. The choice is saved to your account, so every phone and browser you sign in on uses it. Fixed on the way: dates already on screen change format as soon as you switch language, and App Studio no longer leaves errors behind for a project that is gone or a dropped connection. It installs over 1.9.13 and keeps your data; the APK is 25.1 MB, up from 23.9 MB. Before release every test in the repository ran, 28,950 in 2,024 files; each failure was fixed, or came from the test machine (an older Node or Rust, or a busy moment) and passes without it.

1.9.13, 17 November 2026. Model lists that keep themselves current. An agent’s model choice, App Studio’s providers, the Terminals menus and the chat’s Newest models now follow a public catalog of the major makers’ models, newest first, so a model released after this version shows up without an update, and App Studio marks the last 30 days’ as New. Added now: Claude Fable 5.2, Gemini 4 Carbon and Gemini 4 Hydrogen, and Qwen 4 Max on OpenRouter. Three new free models, Ling 3.2 Flash, ERNIE 5.5 Flash Preview and Particle 1, each answered and called a tool in a live test. A free agent with no model picked now runs on Nemotron 3 Ultra: it was trying DeepSeek V4.1 Flash, whose free version is offline. Security: the key Automa uses for the free models is stored scrambled (1.9.12 kept it in readable pieces), and every build checks that it is readable nowhere in the app; a phone running Automa can still recover it. Your phone’s database password and app key are locked to Termux on every install; sign-in tries are counted per real caller, so a made-up address for each guess no longer gets around the limit; and other websites can no longer show the board inside a frame. On the phone, PostgreSQL 18 runs 4 helper processes instead of 7 and the server no longer runs git every few seconds, so Android has less reason to close Termux. Fixes from a review of 1.9.12: Troubleshoot and Safe start each get their own answer from Termux (two at once used to share one), Troubleshoot waits while a Safe start runs, and after Restart normally the safe mode banner keeps checking past its 3-minute wait. It installs over 1.9.12 and keeps your data. The release checks ran 8,047 tests in the board and shared projects and 225 in the server files it touches; one test failed once on a busy machine and now waits for what it checks.

1.9.12, 17 November 2026. Staying up on the phone. When Termux closes with “[Process completed (signal 9)]”, Android has ended its processes: Android 12 and newer do that once all apps together run more than 32 in the background, and every Android does it when memory runs low. The database on the phone now runs fewer processes and uses less memory, and the server keeps 6 database connections at most. The new automa keep-alive lifts Android’s process limit over Wireless debugging, once (it stays after a restart), and takes Termux off battery optimisation. When Automa stops, Termux says why and keeps a record (automa logs). After three stops in a row within five minutes of starting, Automa starts in safe mode by itself: the board opens with agents, schedules and plugins off, and a banner says why, with Restart normally and Troubleshoot. automa troubleshoot, or Troubleshoot in the app, checks Termux, storage, memory, the database and Automa, fixes what it safely can (a lock left behind, an update cut short, a stopped database) and never touches your data or backups. A Refresh button in the header loads the page again and reconnects live updates. It installs over 1.9.11 and keeps your data. 61 tests are new; of 28,099 in the full run, 3 failed the first time and pass after their fixes.

1.9.11, 16 November 2026. Fixes from a scan of the whole app. Saving your name or photo while the connection drops now says “Can’t reach Automa right now”, and the App Studio page an invited collaborator uses says it can’t reach the session; both showed “Failed to fetch”, and the change is not sent twice. An agent’s settings page loads the extra settings some AI connections add (Codex, Gemini and others) by itself once Automa answers again, where they stayed missing until the app was reopened. After a reconnect, pages you had already left stop asking the server every 10 seconds. The command-line tool packs a 64 MB company folder for import in milliseconds, where that step took several seconds. It installs over 1.9.10 and keeps your data. Checked by opening 112 pages in a browser at phone size and running 28,210 tests; 10 of them failed on the first run and pass after their fixes.

1.9.10, 12 November 2026. Starting up and reconnecting. While Automa is still starting on the phone, the connect screen now shows which step it is on, how long it has waited and “step x of y”, instead of waiting with no end in sight. When the connection drops and comes back (the network returns, or you reopen the app), the board reconnects by itself, where before it showed “Failed to fetch” until the app was reopened, and a dropped connection no longer sends you back to sign-in. In Termux, automa run follows the start step by step and opens the app when it is ready. It installs over 1.9.9 and keeps your data. Checked on the server and the board; not yet on a phone.

1.9.9, 9 November 2026. Fixes from a scan of every page and a live run of the app. When the free AI service asks Automa to slow down, Automa now waits the minute it asks for, once for all agents, and carries on, instead of retrying four times in 25 seconds and failing the reply. Home no longer shows “Task unavailable” cards for chats and tasks you deleted, and deleting a chat or task also cancels the retries still waiting for it, so its agent isn’t left “still working” for hours. The bring-your-own and Vercel connect pages no longer open with a sidebar for a connection that doesn’t exist.

Automa release history
VersionDateHighlights
1.9.1522 Nov 2026IMY in Terminals: code in your own syntax becomes one of 48 languages as you type, and 42 of them build and run where their tool is installed; a check of which free models answer; one more free model, LFM3 1.7B
1.9.1418 Nov 2026Automa in your language: Auto and 40 languages for the board, the connect screen and the app; right to left for Arabic, Persian, Hebrew and Urdu; agents write to you in your language
1.9.1317 Nov 2026Model lists that keep themselves current, with Claude Fable 5.2, Gemini 4 Carbon and Hydrogen and Qwen 4 Max; three new free models; the free models’ key stored scrambled and sign-in limits per real caller; fewer processes on the phone
1.9.1217 Nov 2026Fewer database processes on the phone and automa keep-alive for Android’s process limit; safe start after three quick stops; automa troubleshoot; Refresh in the header
1.9.1116 Nov 2026Two more places say “Can’t reach Automa” instead of “Failed to fetch”; an agent’s settings load by themselves after a reconnect; company import packs in milliseconds
1.9.1012 Nov 2026The connect screen shows each startup step; the board reconnects by itself instead of “Failed to fetch”; a dropped connection no longer signs you out
1.9.99 Nov 2026Waits out the free AI service’s slow-down instead of failing the reply; no dead cards on Home; deleting a chat cancels its waiting retries
1.9.88 Nov 2026Starts even when an old queued run can’t be verified; no 30-second stall; web search falls back to Bing
1.9.73 Nov 2026Stays on your page when you come back; deleting a chat stops a reply at once
1.9.62 Nov 2026A full audit of 16 areas with every confirmed finding fixed: the app proves the server holds its key, agents never see server secrets, connectors sign in inside the app, agent budgets enforced
1.9.530 Oct 2026Notifications when a reply or App Studio job finishes while you’re away; live Stats tab; the AI looks at the page like you do
1.9.430 Oct 2026App Studio teams with a shared team chat and per-model token shares
1.9.330 Oct 2026A growing pool spreads free-model requests, so many people asking at once all get answers
1.9.229 Oct 2026Server updates on the phone switch over only when complete; a failed update leaves Automa running
1.9.128 Oct 2026Usage limits on Costs; failed replies say why; Moan’s facts brought up to date
1.9.028 Oct 2026The Que engine under every free-model call; App Studio with no key
1.8.827 Oct 2026Moan, the Jamaican model; free agents make spreadsheets, decks and documents
1.8.727 Oct 2026Free agents keep their model and recover in place; maker logos on agents
1.8.626 Oct 2026Free chat agents paired with SDXL Lightning, and draw when asked
1.8.526 Oct 2026Start on the free models without a key; a database backup before every update
1.8.426 Oct 2026Free models in chat that stream, think, search, use tools and draw
1.8.2–1.8.326 Oct 2026Ask Claude from any app; automa update; one signing key from here on
1.8.0–1.8.124 Oct 2026Terminals, App Inspector and your API balance
1.7.024 Oct 2026Claude agents with Claude Code’s tools on phones; thinking modes
1.6.x22 Oct 2026Live replies with visible thinking; token and cost counts everywhere
1.5.021 Oct 2026Slash commands, app shortcuts, the offline sheet
1.4.x10 Oct 2026App Studio; the app locked to its own Automa; the tour
1.3.029 Sep 2026Run Automa on the phone; drag-to-connect org chart
1.1.0–1.2.028 Sep 2026Continue with Google, push notifications, the org chart on phones
1.0.027 Sep 2026The first Automa for Android

Limits

  • Android only. Android 8.0 or newer, on phones, tablets, foldables and Chromebooks. There is no iPhone build.
  • The AI needs internet. With the server on the phone, Automa itself keeps working offline; the AI features do not.
  • Free models have limits. Each has a daily limit, they share a monthly allowance, and a provider can be busy or close a model. Automa shows which, and when it is back.
  • Some engines can’t run on a phone. Codex agents can’t, and say so; other runtimes must be installed in Termux. Claude Code’s desktop engine doesn’t run in Termux, so on a phone Claude agents use the Anthropic API with Claude Code’s tools.
  • Moan’s index is Jamaican. For the rest of the Caribbean, agents research the web instead.
  • App Inspector is for apps you made or are authorized to analyze.

Questions people ask

What is Automa?

Automa is an Android app, made in Jamaica by Nathan at CorX Labs, that runs a whole company of AI agents for you. You hire agents, give them roles, chat with them like teammates, hand them tasks, let them build and run apps, draw pictures, search the web and work with your files, and you approve anything that matters. The agents work on an Automa server you control: your computer, a cloud machine, or the phone itself inside the free Termux app.

Is Automa Jamaica's first AI app?

Automa is one of the first AI agent apps built in Jamaica. It was made by Nathan, the 14-year-old founder of CorX Labs, the lab behind CorX3.8-27B: Jamaica’s first large open-weight language model. Jamaica’s AI scene grew quickly in 2026, with other platforms launching too, so CorX Labs does not claim Automa was the very first; it is the one that puts a whole company of AI agents, a Patois-speaking model and an app studio on one Android phone.

Is Automa an AI platform?

Yes, a Jamaican AI agent platform that fits on a phone. Where most AI apps give you one assistant, Automa gives you the pieces of a platform: agents with roles and budgets, tasks and approvals, projects and goals, an app studio, coding terminals, files, skills and connectors, all running on an Automa server you control.

What is an AI agent?

An AI agent is an AI model given a job, tools and the freedom to take steps on its own (searching, reading, writing files, running code) instead of only answering one message. In Automa every agent is an employee with a role, a title, a manager, a model and a budget, and anything that matters waits for your approval.

How is Automa different from a chatbot app?

A chatbot is one assistant in one conversation. Automa is a team: several agents with roles, an org chart, tasks with owners and plans, approvals, budgets, schedules and files, all on a server you control. You can still just chat with any agent, and the chat keeps its history and cost.

Who is Automa for?

Small businesses that want help with research, marketing, logos and paperwork; students who want research, documents and a place to learn to code without a card; creators who need captions, posts and pictures; and developers who want Claude Code, Codex and Gemini CLI on a phone.

Can I run Claude Code on an Android phone?

Yes, with Automa’s Terminals: Claude Code, Codex, Gemini CLI and OpenCode run in their full terminal UI on a Debian layer the app sets up for you, with Automa running on the phone in Termux. On a phone, Claude agents answer through the Anthropic API with Claude Code’s own tools.

Do I need an API key or a credit card?

No. Pick a free model and start: Automa’s free models need no key, no account and no card. Add keys later under Settings → API keys if you want Claude, GPT, Gemini or another paid model, and set a monthly spending limit so nothing overspends.

Do I need a computer?

No. Tap Run Automa on this phone and the server runs inside Termux on the phone. A computer, a virtual machine or a cloud machine works too, and is what you want if the agents should keep working while the phone sleeps.

Is there an AI that speaks Jamaican Patois?

Yes. Moan is Automa’s own Jamaican model, free with no key. It answers in Patois first and in Standard Jamaican English for formal documents and code, carries a primer on Jamaica’s history, government, courts, statutes, economy and culture, and keeps a living index of Jamaican sources (the Gleaner, the Observer, JIS, the Office of the Prime Minister, Parliament, the Bank of Jamaica and the Laws of Jamaica) so its replies cite source, date and link.

Can I use Automa elsewhere in the Caribbean?

Automa itself is not tied to Jamaica: you install the APK yourself and the agents run on a server you control. Free agents search and read the web with sources, so research about Trinidad and Tobago, Barbados, Guyana, the Bahamas or anywhere else works the same way. Moan’s built-in knowledge index is the Jamaica-specific part.

Which AI models does Automa work with?

Twenty-plus free chat models and two free image models with no key, including Moan, Nemotron 3 Ultra, Gemma 4, Qwen 3.8 and Ling 3.2 Flash, plus SDXL Lightning and SDXL Base for pictures. With your own keys or subscriptions it runs Claude, GPT, Gemini, DeepSeek, Grok and Kimi, and engines such as Claude Code, Codex, Cursor, Gemini CLI, OpenCode and any OpenAI-compatible endpoint.

Can Automa make pictures, spreadsheets and documents?

Yes. A free chat model paired with an image model draws pictures and logos, and redraws an attached photo with the change you ask for. Free agents also make real Excel spreadsheets with formulas, PowerPoint decks with charts and pictures, and Word documents, and read the files you attach.

Can I build apps on my phone with Automa?

Yes, in App Studio: 69 languages, an AI pair or a whole AI team that writes the code and fixes what breaks, a sandboxed preview, a public link in one tap, undo for every AI change, and friends invited by code or link. It works on the free models with no key.

What happens offline?

With the server on the phone, Automa itself keeps working offline. The AI features need internet. When the phone loses the network, a sheet says so and counts down to the next try, and what you typed is kept.

Is there an account, and where is my data?

There is no Automa cloud account. Your organizations, tasks, chats and files live on your own Automa server, and sign-in exists only on that server, when you turn it on. Free-model requests go from your server to the free AI service Automa uses.

Can other people use my organization?

Yes. Invite members with roles; an invite can’t give more than the person who made it has. App Studio projects can be shared with friends by join code or link.

Is there an iPhone version?

No. Automa is for Android 8.0 or newer, on phones, tablets, foldables and Chromebooks.

How do I download Automa?

Tap Download Automa 1.9.15 (APK) on this page, open the file on an Android phone, and allow Install unknown apps if Android asks. The APK is 25.3 MB and signed. Automa has also been submitted to APKPure, and once APKPure finishes its review it will be released there too, so updates can arrive on their own. Every release from 1.8.2 on installs over the previous one and keeps your data.

Who made Automa?

Nathan, the 14-year-old founder of CorX Labs in Jamaica, who also built the CorX language models and NatureV1. Automa builds on an MIT-licensed open-source control plane for AI agents.

Automa 1.9.15

Your AI company, in your pocket.

Hire agents, hand them work and approve what matters, on free models with no key, from one Android phone. Made in Jamaica by CorX Labs.