Install the Nenjo harness and the nenpm package manager with the CLI installer, or run the worker with Docker.

Nenjo's hybrid model means the dashboard is hosted for you, but the agent harness runs on your own machine or infrastructure. Installing Nenjo means getting that harness — the nenjo worker and the nenpm package manager — onto your system. There are two ways to do it: the CLI installer for a local machine, or Docker for servers and containers.

CLI installer

The quickest way to install on macOS or Linux:

curl -fsSL https://nenjo.ai/install | bash

This installs three binaries into ~/.nenjo/bin by default:

Binary	Purpose
`nenjo`	The agent worker — `nenjo run` starts the harness and connects to the platform
`nenpm`	The package manager for installing packages and Claude plugins
`nenjoup`	The updater that keeps the binary bundle current

Staying up to date

Both CLIs update through the bundled nenjoup updater:

nenjo update
nenpm update

Nenjo passively notices when an update is available. Set NENJO_NO_UPDATE_CHECK=1 to suppress those notices.

Running the worker

Once installed, start the harness:

nenjo run

It reads NENJO_API_KEY from your environment or ~/.nenjo/config.toml, connects to the platform, and begins processing chat, tasks, schedules, and repository events. See the Harness docs for configuration.

Docker

For servers and containerized deployments, the worker image is published to GitHub Container Registry and runs nenjo run by default:

docker run --rm \
  -e NENJO_API_KEY="$NENJO_API_KEY" \
  -e OPENAI_API_KEY="$OPENAI_API_KEY" \
  -v nenjo-data:/home/nenjo/.nenjo \
  ghcr.io/nenjo-ai/nenjo-worker:latest

Persist /home/nenjo/.nenjo to keep worker config, manifests, package installs, memory, crypto state, and session state across restarts.

To let the worker operate on a specific workspace, mount a host checkout and set the capabilities it should handle:

docker run --rm \
  -e NENJO_API_KEY="$NENJO_API_KEY" \
  -e OPENAI_API_KEY="$OPENAI_API_KEY" \
  -e NENJO_CAPABILITIES=chat,task,repo \
  -v nenjo-data:/home/nenjo/.nenjo \
  -v "$PWD:/home/nenjo/.nenjo/workspace" \
  ghcr.io/nenjo-ai/nenjo-worker:latest

Image variants

Image	Use
`ghcr.io/nenjo-ai/nenjo-worker:<version>` / `latest`	Production baseline — `git`, `git-lfs`, shell utilities, `rg`, `curl`, `wget`, `jq`, Python, TLS certificates
`ghcr.io/nenjo-ai/nenjo-worker:<version>-dev` / `dev`	Larger toolbox — compilers, Rust, Node/npm, GitHub CLI, Docker CLI, editors, and debugging utilities

Use a versioned tag for pinned deployments:

docker pull ghcr.io/nenjo-ai/nenjo-worker:v0.12.0

Update containers by pulling a new image and replacing the container — not with nenjo update. The images set NENJO_NO_UPDATE_CHECK=1 so logs don't suggest self-updating an immutable image.

Next steps

With the harness installed, continue to Onboarding to connect it to your workspace, then Bootstrap your first project and agent.

Installation