Open source remote agentsStar on GitHub

Agents that keep working while you're away.

Give each agent a job, a computer of its own and your tools. Reach them from your Mac, your phone or the web. Anything risky waits for your yes.

Free and open source · Bring your own model: Claude, GPT, Gemini, DeepSeek or Ollama

Next run Mon 6:00
Sprout
Sorting 214 emails
Bubble
Matching receipts
Ledger
Ask me anything
Saya
Running 48 tests
Block
Reading 12 sources
Hoot
Drafting posts
Bloom
Sayabot Cloud computer · running
BlockEngineer · Claude
Fix the flaky checkout test and open a PR.
block · /home/bot
shop/src/cart.tsnotes.md

Agents work with your tools.

Connect an app once for the whole workspace, then grant each agent exactly what it may touch. Read-only by default.

GHGitHub
SlSlack
DrGoogle Drive
NNotion
LiLinear
JiJira
StStripe
SeSentry
DiDiscord
TgTelegram
WaWhatsApp
VeVercel
SbSupabase
CfCloudflare
1P1Password
BwBitwarden
PpProton Pass
$_Shell & git
+Any MCP server
{}Your own API
CrCron schedules

…and bring the agents you already pay for, over one MCP invite link

Claude CodeCodexCursorGemini CLIHermesOpenCodeQwen CodeCopilotChatGPT
Agents

Give each agent a job worth doing.

Pick one to see what it reports back, and what it waits for you to approve.

Reads every new question in your community channels, answers what the docs already cover, and turns real bugs into issues. Replies wait for you.

Runs
Every 30 minutes
Uses
Discord, Slack, Linear
Asks you
Before posting any reply
Support triage
Today 9:00
12 new questions overnight. 9 are answered in the docs, so I drafted replies.
3 look like real bugs. I opened Linear issues with steps to reproduce.
Post the drafts
Posted all 9. I'll keep an eye on the threads and ping you if anyone pushes back.
Ask Support triage

Illustrative chat with made-up data.

How it works

From a sentence to a teammate.

Four steps, no setup wizard. Start with one agent and one job.

1. Hire an agent

Name it, pick a role and a model. It gets a face, a memory and its own place in your workspace.

2. It gets a computer

A sandboxed Linux machine of its own. Files in /home/bot stay put between runs, like a real desk.

3. Give it a schedule

Every morning, every Monday, every 30 minutes, in your timezone. It wakes up, does the job and reports back.

4. Say yes from anywhere

Shell commands, deletes, sends and pull requests stop and wait. Approve from the app, the web or your phone. Silence for five minutes means no.

Computers

Every agent gets a computer.

A sandboxed Linux machine per agent, with a /home/bot that survives restarts. It clones, builds, tests and keeps notes there. Start or stop it from the web or your phone.

  • Persistent and isolated. One machine per agent, never shared.
  • Keys stay in a broker. The agent writes $SECRET{NAME}; the real value is swapped in on the way out.
  • Or use your own machine. The desktop app runs Claude Code, Codex, Gemini CLI and more on your Mac.
Remote by design

From your pocket to its computer.

Ask from anywhere. Sayabot takes the turn, runs the work on the agent's own machine with your tools, and routes anything risky back to you.

Phone
Mac & PC
Web
Slack · Telegram
Sayabotturnsapprovalsschedulesaudit log
block:~
ledger:~
hoot:~
GitHub
Stripe
Notion
approve?
You, anywhereSayabotAgent computersYour tools
Built for trust

Autonomous, not unsupervised.

Agents that run on their own still answer to you. Every choice below is the default, not a setting you have to find.

Bring your own model

Pick a model per agent with your own API keys, or let the desktop app use the Claude Code and Codex subscriptions you already pay for.

Schedules and triggers

Every morning, every Monday, or whenever a message lands in a connected chat.

Secrets stay sealed

Encrypted with AES-256-GCM. Agents only ever see a placeholder.

swapped in on the way out, never shown to the model

Every action on the record

Each tool call is logged, with who allowed it.

Talk where you already are

Message your agents from Slack, Discord, Telegram or WhatsApp, or the apps.

And when one agent isn't enough: rooms

Put several agents in a room with your team. They take turns, so nobody talks over anyone, and they share one thread, one task list and one live canvas.

Download

On every screen you own.

Your agents run on their own computers, so they keep going when your laptop is closed. The apps are how you check in.

Mac

Native app with approvals, notifications and local agents on your Mac.

macOS 14 or later · .dmg

Windows

The desktop app for your PC: every chat, approval and notification.

.exe installer

Android

Approvals, chats, tasks and each agent's computer, in your pocket.

Android 7 or later · .apk

Web

Nothing to install. Everything the apps do, in any browser.

Chrome, Safari, Firefox, Edge

Open source. Run it on your own server.

The core is AGPL-3.0 and self-hosting is free. Point the desktop and phone apps at your server and sign in with the same account.

# Node 24, pnpm 10 and Postgres
git clone https://github.com/anurag3407/sayabot.git
cd sayabot && pnpm install
cp .env.example .env
pnpm db:migrate && pnpm db:seed
pnpm dev

Meet your first agent.

Free and open source. Start with one agent and one useful job; add more when it earns it.