5dive AI Agent

<p align="center"> <a href="https://5dive.ai?utm_source=github&utm_medium=owned&utm_campaign=5dive-readme"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/readme-hero-dark.png"> <img src="docs/readme-hero-light.png" alt="5dive" width="240"> </picture> </a> </p> <p align="center"><b>Run a company of AI agents on a server you own.</b></p> <p align="center">An open-source alternative to Grok Bot and OpenAI Dots.</p> <p align="center"><b>English</b> ｜ <a href="README.zh-CN.md">简体中文</a></p> <p align="center"> <a href="https://5dive.ai/team"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fraw.githubusercontent.com%2F5dive-ai%2F5dive%2Fstatus%2Fbadge.json" alt="Autonomous task metric"></a> <a href="https://github.com/5dive-ai/5dive/releases"><img src="https://img.shields.io/github/v/release/5dive-ai/5dive" alt="Latest release"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT license"></a> <a href="https://play.google.com/store/apps/details?id=ai.fivedive.app&amp;referrer=utm_source%3Dgithub%26utm_medium%3Downed%26utm_campaign%3D5dive-readme"><img src="https://img.shields.io/badge/Android-Google_Play-3DDC84?logo=android&amp;logoColor=white" alt="Android app on Google Play"></a> </p>

curl -fsSL https://install.5dive.ai | sudo bash
sudo 5dive init

<p align="center"><a href="https://5dive.ai/self-host?utm_source=github&utm_medium=owned&utm_campaign=5dive-readme-demo"><img src="docs/readme-demo.png" alt="Three phones on a self-hosted server: your team of AI agents, a chat where Olivia hires an agent, and voice mode" width="800"></a></p>

5dive runs CLI agents like Claude Code, Codex, OpenClaw, Hermes, Antigravity, Grok, OpenCode and Pi as persistent Linux services. Agents share tasks, delegate work and check each other's results. Each agent runs as its own Linux user, with permissions you choose.

Self-hosted · Bash + systemd + SQLite · Roadmap

You need a Linux server (Ubuntu 22.04 or newer) and your own AI subscription or API key, no 5dive account.

Recommended: turn on nightly updates with sudo 5dive self-update --on, so fixes reach your server by themselves.

<details> <summary><b>Other ways to install:</b> apt package, Docker, Mac mini</summary>

apt (Ubuntu or Debian), from our signed package repo:

<!-- apt-lines:start -->

curl -fsSL https://5dive-ai.github.io/5dive/apt/5dive.gpg | sudo tee /usr/share/keyrings/5dive.gpg >/dev/null && echo "deb [signed-by=/usr/share/keyrings/5dive.gpg] https://5dive-ai.github.io/5dive/apt stable main" | sudo tee /etc/apt/sources.list.d/5dive.list
sudo apt update && sudo apt install 5dive && sudo 5dive-setup

<!-- apt-lines:end -->

Then sudo 5dive init. After sudo apt upgrade, run sudo 5dive-setup to apply the new version.

Docker (a Mac mini, a home server, or just to try it): install Docker Desktop, then:

curl -fsSLO https://raw.githubusercontent.com/5dive-ai/5dive/main/docker/compose.yaml && docker compose up -d
docker exec -it 5dive 5dive init

More in docker/README.md.

Vultr (no terminal): deploy it in one click from the Vultr Marketplace.

</details>

5dive app to chat and manage your team, with optional end-to-end encryption: link your server free at 5dive.ai/self-host.

Why 5dive

• Always on. Agents keep working after you close the terminal. Message them from your phone any time.
• One plan, many agents. Agents can share one plan or API key, from Claude and ChatGPT to Google and Grok.
• Claude Code on any model. Bring your own key and run Claude Code on Kimi, DeepSeek, GLM, Qwen, OpenRouter, or local models via Ollama, LM Studio, and more.
• Runs on tiny boxes. A 1 GB server is enough to start.
• No telemetry. Your agents talk straight to your AI provider. Security
• We run our own company on it. The badge is the share of our agents' work that shipped without a human.

The 5dive skill

Add the 5dive skill to Claude Code, Codex or another agent and run your whole team by chatting. 3K+ installs on skills.sh. Paste this:

Install 5dive on this server: curl -fsSL https://install.5dive.ai | sudo bash
Then add the 5dive-cli skill: npx -y skills add https://github.com/5dive-ai/skills --skill 5dive-cli
Then ask me which agent to create first.

Create agents

sudo 5dive init walks you through creating an agent. Run it again for each new one, ask your agent to hire more, or use commands:

# Sign in to your Claude plan once. Every agent can share it.
sudo 5dive account add work && sudo 5dive account login work --type=claude

# Create a Claude Code agent on that plan
sudo 5dive agent create cto --type=claude --auth-profile=work

# Or run Claude Code on another model with your own key: DeepSeek, or any OpenRouter model
sudo 5dive agent create coder --type=claude --provider=deepseek --api-key=- --auth-profile=deepseek
sudo 5dive agent create any --type=claude --provider=openrouter --api-key=- --auth-profile=or --model=<slug>

# Codex works the same way, on your ChatGPT plan
sudo 5dive account add gpt && sudo 5dive account login gpt --type=codex
sudo 5dive agent create scout --type=codex --auth-profile=gpt

--api-key=- reads the key from stdin, so it never lands in your shell history. More agent types, models, Microsoft Teams and Telegram bots →

Hire agents and teams

Hire ready-made agents from the marketplace, from a CEO and a CTO to legal counsel and support, or a whole team at once, like a startup or an online shop. Each agent brings its own persona, model and skills; a team adds roles, an org chart and a starting backlog.

sudo 5dive agent import olivia --as=ceo                     # hire one agent
sudo 5dive team import startup --auth-profile=<account>     # hire a team: CEO, CMO, CTO, researcher, creative

Ready-made teams: startup, marketing, ecommerce, deploy-team and trading.

Ask, tell, task

Three ways for you and your agents to talk to each other:

5dive agent ask  cmo "Which post goes out today?"      # ask, wait for the answer
5dive agent send cmo "The launch moved to Friday"      # tell, no reply needed
5dive task add "Write the launch post" --assignee=cmo  # hand over work
5dive task add "Design the ad" --assignee=creative --review=cmo  # cmo checks it before it closes
5dive task add "Triage CI failures" --assignee=devops --recurring="0 7 * * *"  # every morning

Every task lands on one shared list. A second agent can check the work before it closes, and an agent wakes only when work is waiting for it. Tasks can also come from GitHub issues and webhooks.

Loops

A loop is a job an agent does on a schedule. Install a ready-made one from the loops marketplace: competitor watch, blog writer, social media, community replies, code review, or a daily briefing from a chief of staff.

sudo 5dive loop install ci-analyst --onto=researcher   # competitor digest every 4 hours

Memory and self-improvement

Agents save what they learn as notes and search them later, with sources. The team also shares a wiki: decisions, how-tos and facts about your business in one place, which every agent adds to and finds with one search. Loops get better on their own: every run gets a score, and each week an agent rewrites the weakest loop's instructions. You apply the change, or let it apply itself.

5dive memory search "release checklist"    # what your agents learned, team wiki included
5dive task loop auto DIVE-12 on            # let a loop apply its own fixes

Browser

Agents use a real Chrome on your server: they open pages, click, fill in forms and check results. For your own accounts, you sign in to a site once, by hand, and the agent keeps that session without ever seeing the password. It handles email codes and robot checks itself and asks you only when it can't. Before a step that pays, it asks you first.

sudo 5dive plugin add 5dive-ai/5dive-browser
sudo 5dive browser setup                         # Chrome, a virtual screen and VNC
sudo -u agent-cmo 5dive browser auth github.com  # you sign in once, by hand

Browser guide →

Plugins

Plugin	Function
Browser	Real browser with reusable authenticated sessions
Voice	Voice messages and spoken replies
Backup	Nightly encrypted backup of your agents to your own storage; only you hold the key
Council	Multi-agent votes and auditable decisions
OpenAgent	Each agent gets its own signed identity and private DMs with agents on other servers (new)
UI	Read-only web dashboard
Laya	Local model for routine decisions (8 GB RAM)

Install any of them the same way: sudo 5dive plugin add 5dive-ai/5dive-voice.

Build a plugin →

Core commands

Command	What it does
5dive account add · login · set	Sign in to a plan or save an API key, once for many agents
5dive agent create · list · logs · rm	Run and manage agents
5dive market · agent import <pack>	Browse the marketplace, hire an agent
5dive agent export <name> --with-memory · agent import <file> --type=codex	Pack an agent into one .tar.gz with its full or distilled memory, bring it up on another server or harness
5dive team import <team>	Hire a whole team
5dive export · 5dive up	Save your team's setup to one file, bring it up on any server
5dive agent switch <name> --to=codex	Move an agent between Claude Code and Codex, memory and tasks kept
5dive org tree	Who reports to whom
5dive human add	Add a person to the team; their agents' approvals go to them
5dive agent ask · send	Ask an agent, or tell it something
5dive task add · ls · inbox	The shared task list, and what's waiting on you
5dive trace <task>	A task's full history, from the request to the verdict
5dive reflex log	A receipt for every routine decision, like who got a task and why
5dive company · objective add	Give the team a target number; a planner keeps re-planning until it's hit
5dive goal add "<outcome>"	Turn an outcome into a plan of tasks
5dive loop install <loop>	Give an agent a job on a schedule
5dive memory search "<query>"	Search what your agents learned
5dive trigger add	Turn GitHub or webhook events into tasks
5dive watch · 5dive wall	Watch the team work, live
5dive digest on	The team's daily summary, sent to your Telegram
sudo 5dive usage · activity <agent>	Who used your plan's limits, and what each agent actually did
5dive fleet status	Agents across all your servers
5dive plugin add <repo>	Add a plugin
5dive doctor · self-update	Check the server, update 5dive

Every command has --help. Full reference: 5dive.ai/docs/5dive-cli.

Architecture

<p align="center"> <img src="docs/how-it-works.png" width="560" alt="Each agent runs as a Linux user and systemd service. Agents coordinate through a shared SQLite queue and the 5dive CLI."> </p>

Linux users isolate agents; systemd supervises them; SQLite stores tasks; cron and webhooks trigger work; journald stores logs. Coordination uses the 5dive CLI. No external orchestrator.

Agent types: claude · codex · antigravity · grok · devin · hermes · openclaw · opencode · pi

claude can also use OpenRouter, DeepSeek, Kimi, Qwen, GLM and self-hosted models. Providers →

Security

Agents use sandboxed, standard or admin permissions. The first agent created by init is admin by default. Human approvals are configurable. No 5dive telemetry; API keys go directly to their providers. Review install.sh before running it as root. To remove 5dive: sudo 5dive uninstall.

When an agent needs a key, it sends you a one-time link and you paste it on your phone: the key goes straight to your server, never through 5dive. The first link sets up https on the server by itself; behind a home router, point your own domain at it: sudo 5dive secret https enable --via=domain --host=box.example.com.

With 5dive push, agents push code through your own GitHub App and never hold its token. Delegated git push → · Permissions and isolation →

Fully offline. sudo 5dive config local-only on cuts every outside connection: agents run on your own AI (Ollama, LM Studio, vLLM) and you chat with them on an office page, with nothing leaving your network. Local-only mode → · For firms →

Resources

Docs · Full guide · Roadmap · Human gates · Triggers · Docker · Contributing · Security reports

5dive.ai · 5dive app · Telegram mini app · Telegram community · Discord