Search

My Python LLM project

Weave production-grade LLM prompts with cache boundaries, tool injection, and token budgeting. Reverse-engineered from Claude Code's 7-layer prompt architecture.

Minimal recursive subagent orchestration for pi. No bundled agents, no opinions.

Human-in-the-loop review for Pi edit/write tool calls

Easily interact with the IndexedDB API with a simplified, promise-based approach.

TypeScript SDK for the KBForge API — semantic search and RAG chat over your knowledge bases

<p align="center"> <h1 align="center">Semnova</h1> <p align="center"> Zero API keys. Zero cloud costs. Local AI-powered semantic search for Node.js. </p> <p align="center"> <a href="https://www.npmjs.com/package/semnova"><img src="https://

Stop waiting for Opus on every grep — routes 80% of tasks to faster models with zero quality loss. One command, zero dependencies.

🚀 Salesforce Deployment Viewer - Visualize deployment results with a modern UI (SOAP API + XML support)

CLI and WordPress plugin for routing AI inference to models running on your own machine.

A lightning-fast, express validator using zod (body, query, params)

OneBrain integration for Vercel AI SDK — persistent memory for AI apps

AI chat toolkit for React Native — SSE streaming, chat hooks, and UI components for any LLM backend

Scaffold a new Even Realities G2 glasses app from a template gallery

Load API keys with secret-tool

OpenClaw plugin for intercepting tool calls with user confirmation

ESP32 LAN voice coding bridge with inject, Codex, and Claude modes; inject is the recommended default.

Your terminal has feelings now

A futuristic, real-time voice assistant React library powered by Gemini Live API.

Core library for Grimoire AI — file I/O, search, and database operations