Multi-Provider Support
Target OpenAI, xAI, Google Gemini, Anthropic, or an OpenAI-compatible gateway from the same CLI.
pbi-agentDocumentation
Multi-provider LLM CLI agent for Power BI report editing
Target OpenAI, xAI, Google Gemini, Anthropic, or an OpenAI-compatible gateway from the same CLI.
Run multiple model-requested tool calls concurrently with a configurable worker limit.
Discover project-local sub-agent definitions from `.agents/*.md` and route delegated work through `sub_agent`.
Bootstrap a Power BI Project from the bundled template with the init command or the init_report tool.
Use the default browser UI for interactive work, or switch to single-prompt and audit commands for headless execution.
Discover project-local MCP servers from `.agents/mcp.json` and expose their tools to the model.
TIP
Running pbi-agent without a command defaults to pbi-agent web, so a bare invocation launches the browser UI.
curl -LsSf https://astral.sh/uv/install.sh | shpowershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"uv tool install pbi-agentWARNING
If this is your first uv tool install, reload your shell before running pbi-agent or the command may not be on your PATH yet.
pbi-agent --api-key "$OPENAI_API_KEY"| Section | What you will find |
|---|---|
| Guide | Installation, provider setup, and architecture overview |
| CLI Reference | Commands, flags, defaults, and audit behavior |
| Tools | The built-in function tools available to the agent |
| Environment Variables | PBI_AGENT_* settings and provider-specific key fallbacks |
| Customization | INSTRUCTIONS.md, AGENTS.md, project skills, sub-agents, and MCP discovery |
pbi-agent is designed for local, file-based Power BI Project workflows. It edits PBIP assets directly and talks to LLM providers through synchronous HTTP REST requests implemented with Python's standard library.