@alchemystai/pi

Pi extension for AlchemystAI Context Layer — persistent, retrievable memory for coding sessions

Packages

Package details

extensionskill

Install @alchemystai/pi from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:@alchemystai/pi
Package
@alchemystai/pi
Version
0.1.0
Published
Jul 4, 2026
Downloads
193/mo · 8/wk
Author
anuran-roy
License
MIT
Types
extension, skill
Size
38.2 KB
Dependencies
0 dependencies · 0 peers
Pi manifest JSON
{
  "extensions": [
    "./src/index.ts"
  ],
  "skills": [
    "./skills"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

@alchemystai/pi

Pi extension for AlchemystAI Context Layer — persistent, retrievable memory for coding sessions.

Installation

Via git (recommended)

pi install git:github.com/AlchemystAI/pi-alchemyst

Via npm (if published)

pi install npm:@alchemystai/pi

Local installation for testing

# Clone the repository
git clone https://github.com/AlchemystAI/pi-alchemyst ~/.pi/agent/extensions/pi-alchemyst

Setup

  1. Get your API key from AlchemystAI Platform
  2. Configure the extension in Pi:
Use the alchemyst_configure tool to set your API key:
- apiKey: "your-jwt-token-here"
- defaultScope: "internal" or "external" (optional)
- groupName: ["project-name"] (optional, for categorizing context)

This saves your configuration to ~/.config/pi-alchemyst/config.json. It persists across sessions — you only need to do this once.

You can also pre-configure by creating the file manually:

{
  "apiKey": "your-jwt-bearer-token",
  "groupName": ["pi", "my-project"]
}

Available Tools

Tool Description
alchemyst_context_search Search stored context for decisions, docs, and reference material
alchemyst_context_add Save context to Alchemyst for future retrieval
alchemyst_context_ask Ask questions grounded in your stored context
alchemyst_memory_add Persist conversation turns to Alchemyst memory
alchemyst_memory_update Update saved memory entries
alchemyst_configure Configure the Alchemyst API key and settings

Context Arithmetic Best Practices

Alchemyst uses context arithmetic to filter and rank context. Use hierarchical groupName tags:

Layer 1: Domain (e.g., "engineering", "docs")
Layer 2: Project/Categories (e.g., "api-v2", "auth")
Layer 3: Specifics (e.g., "decisions", "patterns")

Example: groupName: ["engineering", "backend", "auth"]

Features

  • Persistent Memory: Save important decisions and recall them later
  • Context Search: Find relevant docs across all your projects
  • Hierarchical Tagging: Use groupName tags for precise context filtering
  • Session Memory: Persist conversation history across sessions
  • Security Guards: Automatically blocks secrets and sensitive data

Environment Variables

  • ALCHEMYST_API_KEY: Your Alchemyst API JWT token
  • ALCHEMYST_BASE_URL: Override API endpoint (optional)
  • ALCHEMYST_DEFAULT_SCOPE: "internal" or "external" (optional)
  • ALCHEMYST_GROUP_NAME: Comma-separated tags (optional)

Environment variables take priority over saved values — useful for per-session overrides.

License

MIT