omp Coding Agent
omp (also known as oh-my-pi) is an open-source, terminal-first AI coding agent available at omp.sh. It provides a rich terminal interface for exploring repositories, writing code, running tools, and managing long-running sessions.
omp supports custom OpenAI-compatible providers through a YAML configuration. Connected to our Swiss-hosted Everyware AI API, your prompts and source code stay within our Swiss GPU infrastructure.
Key Features
- Terminal-first TUI: Interactive coding directly in your project directory.
- Custom providers: OpenAI-compatible endpoints are configured in
~/.omp/agent/models.yml. - Model roles: Assign persistent roles such as default, small, or slow to specific models.
- Thinking levels: Control reasoning effort with
--thinkingor the:levelmodel suffix. - Full data sovereignty: All requests are routed through our Swiss Everyware AI API.
Installation
curl -fsSL https://omp.sh/install | sh
brew install can1357/tap/omp
bun install -g @oh-my-pi/pi-coding-agent
Verify the installation:
omp --version
Configuration
1. Save API Key
Export your virtual API key as an environment variable:
export EW_AI_API_KEY="sk-bf-..."
omp reads the variable name from models.yml; if the variable is unset, the literal text is used as the token. Make sure the variable is exported before starting omp.
2. Register the Gateway
Create or edit ~/.omp/agent/models.yml:
providers:
ew:
baseUrl: https://ai.ewcs.ch/v1
api: openai-completions
apiKey: EW_AI_API_KEY
models:
- id: flagship
name: Everyware Flagship
reasoning: true
input: [text, image]
contextWindow: 1048576
maxTokens: 131072
- id: balanced
name: Everyware Balanced
reasoning: true
input: [text, image]
contextWindow: 1000000
maxTokens: 131072
- id: fast
name: Everyware Fast
reasoning: true
input: [text, image]
contextWindow: 262144
maxTokens: 131072
The provider ID ew combined with the model IDs produces the selectors ew/flagship, ew/balanced, and ew/fast.
3. Optional: Set a Default Model
Create or edit ~/.omp/agent/config.yml:
modelRoles:
default: ew/flagship
smol: ew/fast
4. Verify and Start
cd /path/to/project
omp models ew
omp --model ew/flagship
Typical Commands and Workflows
- Start interactively:
omp - Select a model at startup:
omp --model ew/balanced - Set the thinking level:
omp --model ew/flagship:high - Set the default thinking level:
omp config set defaultThinkingLevel medium - In the TUI:
/model– open the model picker/model ew/fast– switch directly to a model
- One-shot prompt:
omp -p "Summarize this repository."