Pi Coding Agent, an open-source terminal coding harness created by Mario Zechner and now maintained by Earendil Works, takes a minimal approach to AI coding tools by shipping with only four default to…
Oh-My-Pi, a fork of the Pi coding agent by Mario Zechner, introduces hash-anchored edits to prevent coding agents from overwriting entire files during small edits. The terminal-native agent, built wit…
A developer's comparison of open-source coding agents Pi and OpenCode after 100+ hours of real use found a dead tie in features but distinct trade-offs. Pi, built by Mario Zechner, excels in efficienc…
Matt Pocock's new AI Coding Crash Course teaches developers how to maintain control over AI coding agents by understanding large language models, harnesses like Claude Code and Codex, and applying Rea…
Coding agents' verbose text output is hurting usability, and HumanLayer has released an open-source skill called show-me that prompts agents to explain code visually using component trees, call stacks…
HumanLayer released 'show-me', a coding agent skill that prompts AI agents to explain their work with compact visuals like component trees and call stacks instead of prose, available via 'npx skills a…
Gabriella Gonzalez's essay 'A sufficiently detailed spec is code' argues that producing a specification precise enough for an AI agent requires the same intellectual work as programming, so specificat…
Mario Zechner, creator of libGDX, built the open-source coding agent Pi after becoming frustrated with Claude Code. Pi, which has 85k+ GitHub stars and powers OpenClaw, outperformed Claude Code on a t…
Developer Nitin M M has built Litos, a minimal AI coding agent written entirely in pure C#/.NET, with no Python or TypeScript. The project, inspired by Tau and pi, separates the core agent loop, tools…
A developer reports that the AI harness Pi from pi.dev ignored MCP server instructions and deviated from project skills during a Clojure-to-Common-Lisp port, while the Goose harness from Goose-docs.ai…
Mario Zechner built a new coding agent called Pi after becoming frustrated with Claude Code's behavior drifting due to undocumented system prompt changes, tool modifications, and injected context. Pi …
A developer describes how AI coding tools have shifted from forbidden to expected in interviews within two years, and argues that engineers must ride the wave of rapid AI progress rather than ignore i…
Pi, a coding agent built by Mario Zechner and acquired by Earendil Inc., deliberately omits features like MCP support, sub-agents, and plan mode that competitors emphasize, instead offering only four …
Pi Agent, a minimal coding harness created by Mario Zechner, has become the glue between heavier tools like Claude Code, Codex, and Gemini CLI for a developer who runs four coding agents daily. Its su…
Databricks CTO Matei Zaharia's team built an internal benchmark on their own polyglot codebase to evaluate coding agents, finding that multiple models are now competitive at the top tier, including op…
Anthropic's Agent Skills, announced October 16th, use progressive-loading markdown files to replace many MCP servers at 1/100th the context cost. Skills load metadata (~50 tokens each) always, instruc…
Mario Zechner, creator of Pi, criticized the complexity of configuring Pi.dev, leading to the launch of LazyPi, a one-command setup that installs 60+ skills, 67 themes, MCP support, sub-agents, and mo…
Pi (Rust), a high-performance AI coding agent CLI written in Rust, has been released as a port of the original Pi Agent. It offers instant startup, stable streaming, and a smaller memory footprint com…
GitHub hosts over 4.3 million AI repositories, but only a few projects consistently appear in developer workflows. Eleven key repos, including OpenClaw and pi-mono, signal a shift toward local-first, …
Developer Mario Zechner expresses exhaustion with the AI landscape, calling it pointless. The author argues that AI-generated software feels dead because it lacks a step-wise creation process with fee…