Nakama

Documentation · Demo · Managed hosting

Your next hire will still be human. Nakama runs the agents. Your team keeps the important work.

Nakama is an AI agent platform for your team. You chat in a dashboard that feels like ChatGPT. Behind that, each agent can use tools, skills, memory, and channels (Telegram, WhatsApp, Discord) — with its own identity and permissions.

It was built for teams from day one: one server, many orgs, invites and roles, agents isolated from each other. Set it up in the browser — demo, managed cloud, or one Docker container.

Coming from OpenClaw or Hermes Agent? Same class of capability, without the setup maze, and not limited to one operator on one machine.

Thirty seconds, unedited: pick the agent, ask it something, see the soul that shapes how it answers, then the schedule that runs the job on Monday without you. Running on a local model through Ollama, no API key, nothing to pay.

Open ARCHITECTURE.md for the system design. Open the docs site for the full guide.

Quick start

Try the demo

Open the live demo at https://demo.getnakama.cloud.

• Username: demo@getnakama.cloud
• Password: demo1234

Managed hosting

Use Nakama Cloud to try Nakama with the least work.

1. Create an account.
2. Provision an instance.
3. Complete the first-time setup wizard in the browser.

You do not need Bun, Docker, or a VPS.

Run locally

You need Bun.

# Install dependencies
bun install

# Start the web (starts the server automatically if needed)
bun run dev:web

Open the web dashboard: http://localhost:3003

Or start the server alone:

bun run dev:server

Docker

You can also run Nakama with Docker.

Prebuilt image (fastest):

# Pull and run the latest image
docker pull ghcr.io/ahmadrosid/nakama:latest
docker run -d -p 4310:4310 -v nakama-data:/nakama/data --name nakama ghcr.io/ahmadrosid/nakama:latest

Build from source:

./scripts/docker-build-run.sh

Fresh start:

./scripts/docker-destroy.sh
./scripts/docker-build-run.sh

Open the dashboard at http://localhost:4310.

The image carries omni, which shortens bash and read_file output before it reaches the model. It is on by default; switch it off under Integrations, or with NAKAMA_OMNI=0. Build with --build-arg OMNI_VERSION= to leave the binary out; the server then downloads it, checksum verified, the first time the toggle is switched on. Set NAKAMA_OMNI_AUTO_INSTALL=0 to forbid that download.

Integrations

Nakama connects to Telegram, WhatsApp, and Composio. With Composio, you can connect to more than 1,000 external apps. Enable them in the web app under Integrations.

On the first run, the server asks for a provider and an API key if none is configured. The server saves settings to ~/.nakama/config.ini.

The server listens on http://127.0.0.1:4310 by default. Interactive API docs are at http://127.0.0.1:4310/docs.

License

MIT

Contributors

Thanks to everyone who helps make Nakama better.

Star History