Pi coding agent hits 1.0 and adds MCP support its creator once dismissed

The Pi coding agent reached its 1.0 milestone on Thursday, October 1, adding support for the Model Context Protocol (MCP), which Pi creator Mario Zechner once dismissed as unnecessary.

Pi was acquired in April 2026 by Earendil, the company formed by Armin Ronacher and Colin Daymond Hanna. Earendil says the reversal came because circumstances changed: MCP improved, and the changes Pi's developers implemented in it made integrating other capabilities easier.

An about-face on MCP

"For example, the changes we have made to MCP also enable the use of Jev more easily within Pi," the company said, referring to the widely noted decision model that has already drawn imitators. By Earendil's account, Pi ultimately needs much the same thing MCP does: a sandbox to play with, in the form of an interpreter.

Earendil describes Pi as "a hardened, minimal, extensible agent harness that you can make your own." If Pi were a Python web framework, it would be Flask rather than Django.

What's new in 1.0

Nonetheless, Pi has gained some features. These include Codemode, a harness-side sandbox that helps agents issue tool calls, with support for MCP, decision models and image models, as well as extension support for virtual models, deferred tool loading, cache warming for Anthropic models, mid-conversation system messages, a new TUI theme and full-screen mode by default.

Pi Durable for long-running agents

Earendil also built Pi Durable, described as "a new substrate for building long-running agentic applications." It is a distinct component from Pi, the company explained, in order to preserve Pi's minimalist design. The Pi agent connects the underlying model to tools to manage a conversation; Pi Durable is the layer that orchestrates multiple conversations and handles the storage backend, via SQLite and JSONL.

"Pi Durable is that harness. It does not replace the Pi coding agent. It is a framework for building any agentic application, coding agents included. It shares not only code with the Pi coding agent, like pi-ai, but also its principles: minimalism and malleability," Earendil said.