pi.dev domain graciously donated by


exe.dev

Co-Mono

Looking for the pi coding agent? See packages/coding-agent for installation and usage.

Tools for building AI agents and managing LLM deployments.

Packages

Package	Description
@mariozechner/pi-ai	Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)
@mariozechner/pi-agent-core	Agent runtime with tool calling and state management
@mariozechner/pi-coding-agent	Interactive coding agent CLI
@mariozechner/pi-mom	Slack bot that delegates messages to the pi coding agent
@mariozechner/pi-tui	Terminal UI library with differential rendering
@mariozechner/pi-web-ui	Web components for AI chat interfaces
@mariozechner/pi-pods	CLI for managing vLLM deployments on GPU pods

Contributing

See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents).

Install

Public (binary)

Use this for users on production machines where you don't want to expose source:

curl -fsSL https://raw.githubusercontent.com/getcompanion-ai/co-mono/main/public-install.sh | bash

Then run:

co-mono

The installer downloads the latest release archive, writes a launcher to ~/.local/bin/co-mono, and creates a private agent settings directory at ~/.co-mono/agent/settings.json with remote packages.

Preinstalled package sources are:

[
  "npm:@e9n/pi-channels",
  "npm:pi-memory-md",
  "npm:pi-teams"
]

If npm is available, it also tries to install these packages during install.

If a release has not been published yet, the installer can fallback to a source checkout automatically. Set this explicitly with:

CO_MONO_FALLBACK_TO_SOURCE=1 curl -fsSL https://raw.githubusercontent.com/getcompanion-ai/co-mono/main/public-install.sh | bash

Keep it running

Start and keep co-mono alive with your process supervisor of choice (systemd, launchd, supervisor, Docker, etc).

For public installs, a minimal systemd user service is:

mkdir -p ~/.config/systemd/user
cat > ~/.config/systemd/user/co-mono.service <<'EOF'
[Unit]
Description=co-mono
After=network-online.target

[Service]
Type=simple
Environment=PI_CODING_AGENT_DIR=%h/.co-mono/agent
Environment=CO_MONO_AGENT_DIR=%h/.co-mono/agent
ExecStart=%h/.local/bin/co-mono
Restart=always
RestartSec=5

[Install]
WantedBy=default.target
EOF

systemctl --user daemon-reload
systemctl --user enable --now co-mono

Local (source)

git clone https://github.com/getcompanion-ai/co-mono.git
cd co-mono
./install.sh

Run:

./co-mono

Run with built-in runtime watchdog:

CO_MONO_RUNTIME_COMMAND="python -m http.server 8765" \
  ./co-mono --with-runtime-daemon

For a user systemd setup, create ~/.config/systemd/user/co-mono.service with:

[Unit]
Description=co-mono
After=network-online.target

[Service]
Type=simple
Environment=PI_CODING_AGENT_DIR=%h/.co-mono/agent
Environment=CO_MONO_AGENT_DIR=%h/.co-mono/agent
ExecStart=/absolute/path/to/repo/co-mono --with-runtime-daemon
Restart=always
RestartSec=5

[Install]
WantedBy=default.target

Then enable:

systemctl --user daemon-reload
systemctl --user enable --now co-mono

Optional:

npm run build   # build all packages
npm run check   # lint/format/typecheck

Development

npm install          # Install all dependencies
npm run build        # Build all packages
npm run check        # Lint, format, and type check
./test.sh            # Run tests (skips LLM-dependent tests without API keys)
./pi-test.sh         # Run pi from sources (must be run from repo root)

Note: npm run check requires npm run build to be run first. The web-ui package uses tsc which needs compiled .d.ts files from dependencies.

License

MIT