A terminal-based coding agent
Model the agentic harness like a game engine and most of its hard problems — durable state, tools, configuration, the TUI, inference — collapse into ones other people already solved.
An agent harness is a piece of software that provides an environment for an AI model to operate within.
Why compaction is needed for large language models and how Pi implements it
How Pi's minimal harness improves coding-agent cost and performance, with examples from Databricks and Shopify's pi-autoresearch extension.
I recently came across a tweet about Pi's programmatic APIs. I knew Pi as a coding agent, but its portable internals caught my attention.
We recently finished moving the camelAI agent off of virtual machines.
I turned code mode into a programmable Pi extension. Then it used itself to build most of the runtime.
How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.
