Earendil and the Pi community shipped Pi 1.0 alongside Pi Durable, an experimental package for building long-running, durable agents that run anywhere a JavaScript runtime exists. Pi Durable ships mem…
Pi, the coding harness from Earendil, has added Model Context Protocol (MCP) support to its core after previously declaring on pi.dev that it did not support MCP, following a year of changes to MCP it…
Pi, the free open-source agent harness from Earendil, has drawn more than 5,000 user-shared extensions, according to a first-person account from a non-engineer employee at the company. The author desc…
An agent harness is a piece of software that provides an environment for an AI model to operate within, according to a definitional explainer that distinguishes it from the AI model itself. The explai…
Pi, a coding agent from pi.dev, implements compaction to manage LLM context window limits by summarizing older conversation content while preserving recent messages. Compaction triggers automatically …
Pi, a minimal coding harness from earendil-works, outperformed Claude Code and Codex at lower cost in Databricks' benchmark of coding agents on its multi-million line codebase, and Shopify built its p…
Inference APIs are increasingly returning provider-bound state that makes AI sessions non-portable, according to a critical analysis by Earendil. Features like encrypted content and server-side storag…
Prompt caching, which reuses computed attention states from previous LLM requests, is critical for making coding agents economically viable but remains fragile to changes in tool definitions, model sw…