pi-diet-semble
v0.1.2
Published
On-demand Semble semantic code search tools for Pi.
Maintainers
Readme
pi-diet-semble
One of my diet context engineering and workflow extensions. Add pi-diet-LSP, pi-diet-Ripgrep, pi-repo-move and others from npm.
On-demand Semble semantic code search tools for Pi.
pi-diet-semble gives Pi agents compact, model-visible tools for exploratory code discovery with Semble. It is designed for behavior and intent searches — finding where authentication, persistence, rendering, or other concepts are implemented — without MCP, automatic scans, or large prompt snippets.
Use it alongside structural tools: Semble for behavior discovery, AST tools for syntax-shaped searches, LSP tools for known symbols and types, and grep for exact literals.
Tools
semble_search— natural-language, symbol, or identifier code searchsemble_related— find code related to a known file and line
Both tools support includeTextFiles: true to pass Semble's --include-text-files flag for Markdown, YAML, JSON, and other non-code text files.
Requirements
Install the Semble CLI so semble is on your PATH:
pip install semble
# or
uv tool install sembleInstall
From npm:
pi install npm:pi-diet-sembleFrom GitHub:
pi install git:github.com/ProbabilityEngineer/pi-diet-sembleFor project-local install, add -l:
pi install -l npm:pi-diet-sembleFor local testing:
pi -e ./index.tsUsage
Ask Pi questions like:
- "Find where authentication is handled."
- "Search for the save model implementation."
- "Find code related to
src/auth.tsline 42."
The extension nudges agents to use Semble for exploratory behavior discovery, AST/LSP for structural code or known symbols, and grep for exact literal text.
Prompt overhead
pi-diet-semble registers two compact tools and routing guidance only. It does not inject search results or repository state into prompts.
Development
npm install
npm run typecheckLicense
MIT
