Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.

Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.

Docker Sandbox template image for Pi coding agent

Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Pi extension: resolve `@filepath` (files & directories) in AGENTS.md, inject into system prompt

A monorepo for managing all my pi extentions. Handcrafted by me.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

A list of free LLM inference resources accessible via API.

Pi agent extension: semantic code tools via sem CLI

Personal internet radio: Agentic AI DJ

This repository contains my public JavaScript/TypeScript packages published via npm (using Bun and/or npm).

Comparison case study between Gliner V2 vs OpenAI Privacy filter model for PII Redaction

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!

100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

A vector index built on TurboQuant, written in Rust with Python bindings

Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an interlinked wiki that compounds over time. Follows Karpathy's LLM Wiki pattern.

Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path …

💎 LaPis — local coding memory for Pi. Persistent project context, code intelligence, and decisions backed by SQLite.

A llm disk cache for llama.cpp using a chat completions proxy to orchestrate the llama.cpp api.

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture