disler

Master Claude Code Hooks

Comparison between open source PI agent and closed source Claude Code agent

Real-time monitoring for Claude Code agents through simple hook event tracking.

Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.

A pattern for an always on AI Assistant powered by Deepseek-V3, RealtimeSTT, and Typer for engineering

The way we interact with our data is changing.

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

Sharing early versions of Ada, a personal AI Assistant built on OpenAIs Realtime API

An experimental project demonstrating Infinite Agentic Loop in a two prompt system using Claude Code.

Combine Your Compute

Benchmarks you can feel

What if we could pack single purpose, powerful AI Agents into a single python file?

A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.

An agent skill for managing isolated execution environments

Lean how ONE system prompt turns Opus 5 from a 'load-bearing' smartass into a precise CRACKED senior engineering partner.

Durable Pi playground and agent network: persistent, multi-device durable agents with web and terminal clients

Scale your compute with Claude Code as a programmable agentic coding tool

Minimal MCP Server for Aider

Gemini 2.5 Computer Use + OpenAI Realtime API + Claude Code Multi-Agent Experiment

Simple CLI, Skills, and Prompts for operating your Mac devices with agents

Ten levels of Jev, from one smart if statement to a coding agent that reaches for Jev on its own

Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

Engineer your reusable, customizable, prompt library in Marimo reactive notebooks

What if the exact code snippet or idea you were looking for was one prompt away?

A MCP Server for a small scale engineering agents with multi-provider LLM support.

Fast STT, LLM, and TTS for personal AI assistants using OpenAI, Groq, AssemblyAI and ElevenLabs.

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

Communicate your work with diagrams in seconds with GenAI + Mermaid

A proactive pi-durable news agent that sweeps on a cron tick and ranks every story as Hype, Facts and Signal with jev. Runs on your Mac, an always-on Mac mini or a VM.

Inkwell: a small app, the Super Simple Software Factory that builds it, and the rebootable sandbox system that runs both on a throwaway VM.

Take your current agent running in your terminal and fork it N times to smoothly branch your engineering work.

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

Plans For Fable 5

It's time to push beyond MCP Servers... Right?

31 natural-language prompts that prove one primary agent can stand up, drive, and tear down a whole fleet of AI coding agents and terminals inside cmux.

Deterministic and Agentic patterns for installing and maintaining successful production applications

Live benchmarking platform — FastAPI + click CLI + Vue 3 frontend with real-time SSE bar charts

Your AI Peer Review Bro

Look, Anthropic's Claude-3.7-Sonnet is a powerful, hybrid CRASHOUT LLM. Let's understand this monumental release.

A Pi coding-agent extension that lets a long-running agent watch its own context and compact itself

LLM Prompt Testing Quick Start

Use this codebase to fine-tune OpenAI models with your own data.

LLM Use Case: LLM Powered, Reusable, Domain Agnostic Autocompletes

Simple, Opinionated benchmark for testing the viability of Efficient Language Models (ELMs) for personal use cases.

Local LLMs in One Line Of Code (thanks to llamafile)