An extensible, terminal-based AI coding agent for software-development workflows, with provider support and extensions.

Recent stories
Practitioners argue that coding-agent results depend heavily on the evaluation harness, including tools, execution control, compaction, and token handling. They propose stable common harnesses rather than vendor-specific setups.
Community tests report Qwen 3.8 27B handling coding, OCR, and long-context workloads locally. One vLLM setup reached 3,200 tokens per minute at 262K context on two RTX 3090s without NVLink.
Local users report that Qwen 3.8 27B agent behavior changes substantially with the harness, quantization, context settings, and hardware. One 3-bit MacBook Air run at 57K context took 63 hours.
AI SDK canary added HarnessAgent, a unified abstraction that runs Claude Code, Codex, and Pi in sandboxed sessions with AI SDK-compatible streams. One integration can now target multiple agent harnesses without separate model-specific plumbing.
Three independent Pi builders shipped a goal runner, contract-style subagent acceptance gates, and a new Lovely Dev Tools extension in the same window. That gives Pi users more deterministic long-running loops and cleaner local tool interfaces without starting from an empty harness.
Pi v0.75.5 now shows only the read line in collapsed tool cards while keeping the full inspected range behind Ctrl+O. That matters because long read outputs were obscuring edits and steering signals in collaborative coding sessions.
Pi raised its minimum Node version from 20 to 22.19.0, then shipped a follow-up after Undici-related changes in Node 26 caused Copilot and Codex login failures. This matters because agent CLIs built on Node and Undici can hard-fail on auth or install paths after runtime upgrades.
Builders shipped pi-treebase, a Miko voice mode for pi-listens, devrage support, and a Japanese OpenCode Go guide after the first Pi extension burst. The releases arrive as Pi’s provider abstraction gets stress-tested by OpenClaw-scale multi-provider use.
Independent Pi builders shipped a voice layer, a kanban and observability dashboard, a Codex-conversion tool with `apply_patch`, and smaller UI extensions in the same window. The burst matters because it turns Pi from a single coding agent into a real local-first extension ecosystem with voice, review, and workflow primitives.