<p align="center" <a href="https://pi.dev" <img alt="pi logo" src="https://pi.dev/logo-auto.svg" width="128" </a </p <p align="center" <a href="https://discord.com/invite/3cU7Bz4UPx"<img alt="Discord" src="https://img.shields.io/badge/discord-community-5865F2?style=flat-square&logo=discord&logoColor=white" /</a </p <p align="center" <a href="https://pi.dev"pi.dev</a domain graciously donated by <br /<br / <a href="https://exe.dev"<img src="packages/coding-agent/docs/images/exy.png" alt="Exy mascot" width="48" /<br /exe.dev</a </p
New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See CONTRIBUTING.md.
---
Pi Adaptative
Pi Adaptative is a fork of Pi focused on adaptive agent runtime: reloading changes, making bounded self-modifications, and staying compatible with normal Pi workflows.
Fork credit: Built on Pi by Mario Zechner / badlogic.
Purpose
This repo keeps the scope simple:
- reload supported runtime changes while working;
- make source-backed self-modifications with validation;
- scope loaded resources through profiles when needed;
- keep per-repo configuration out of the repo by using user-level state;
- keep the package installable and usable as a normal coding-agent CLI.
Compatibility mode
pi-adaptative keeps Pi-compatible CLI, SDK, settings, skills, prompt templates, themes, extensions, and package loading where practical. Adaptive features are additive. Legacy settings such as disabledResources still work as aliases for profile blocks.
- @caupulican/pi-adaptative: Interactive CLI and self-evolution harness
- @caupulican/pi-agent-core: Agent runtime package published for this fork
- @caupulican/pi-ai: Multi-provider LLM API package published for this fork
- @caupulican/pi-tui: Terminal UI package published for this fork
Share your OSS coding agent sessions
If you use pi or other coding agents for open source work, please share your sessions.
Public OSS session data helps improve coding agents with real-world tasks, tool use, failures, and fixes instead of toy benchmarks.
For the full explanation, see this post on X.
To publish sessions, use badlogic/pi-share-hf. Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and pi-share-hf.
You can also watch this video, where I show how I publish my pi-mono sessions.