Agent runtime infrastructure Coding Agents Model Routing Benchmarks Computer Use Harness Engineering Developer tools Agent Communication Claude Code Cost Optimization

Pi

A coding agent for the terminal.

Visit site

An open-source, terminal-based coding-agent harness for working on software projects with models, tools, persistent sessions, and extensions.

Recent stories

4 linked stories

newsPRIMARY2026-08-10

Composio and Ante benchmark coding agent harnesses with 47%–67% success range

Composio and Ante tests reported that the same models behaved very differently by harness. DeepSeek V4 Flash ranged from 47% to 67% task success and $0.019 to $0.104 per task across harnesses.

releaseSECONDARY2026-08-08

Relay opens people-and-agents messenger for cross-session agent messaging

Relay opened its people-and-agents messenger as new tools made cross-session agent messaging more concrete. Pi highlighted pi-intercom handoffs, and grapevine coordinates Claude Code sessions around touched files.

newsSECONDARY2026-07-08

Databricks benchmarks coding agents on internal codebase tasks

Databricks published an internal coding-agent benchmark using tasks from its codebase. OpenAI, Anthropic, and GLM-5.2 models landed on its Pareto frontier, and the company argues teams should optimize cost per task rather than per token.

newsPRIMARY2026-04-26

Pi ecosystem ships computer use, `/parallel-review`, and Chrome extension templates

Independent builders shipped Pi-GUI computer use, pi-subagents parallel review, and starter templates for extensions, Docker workers, and voice add-ons. The releases add reusable computer-use, subagent, and local-runtime building blocks around the base Pi harness.