@nerisma/pi-agents

What this package can reach

Detected automatically from the source at version 1.3.2. This describes access, not safety — you decide whether it's appropriate for what the package claims to do.

• 🤖
  Behavior — Changes how the agent thinks Modifies the system prompt, injects messages, or rewrites conversation context.
• ⚡
  Commands — Runs shell commands Spawns processes on your machine.
• 📁
  Files — Reads files outside your project Touches paths beyond the working directory, such as your home folder.
• 📡
  LLM traffic — Sees raw model API traffic Reads or replaces provider requests, headers or responses — including your prompts.
• 🔀
  Tool control — Can switch pi's tools on and off Calls setActiveTools, so it can disable built-ins — including safety-relevant ones.
• 🔧
  New tools — Adds model-callable tools Gives the agent new abilities. Additive and visible, unlike an override.
• ▤
  UI — Draws its own interface Renders widgets, footers, dialogs or full-screen views.