pi.dev domain graciously donated by
![]()
exe.dev
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.
I regularly publish my own pi-mono work sessions here:
All Packages
| Package | Description |
|---|---|
| @caupulican/pi-ai | Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.) |
| @caupulican/pi-agent-core | Agent runtime with tool calling and state management |
| @caupulican/pi-adaptative | Interactive coding agent CLI and adaptive harness |
| @caupulican/pi-tui | Terminal UI library with differential rendering |
For Slack/chat automation and workflows see earendil-works/pi-chat.
Contributing
See CONTRIBUTING.md for contribution guidelines and AGENTS.md for project-specific rules (for both humans and agents).
Development
npm install --ignore-scripts # Install all dependencies without running lifecycle scripts
npm run build # Build all packages
npm run check # Lint, format, and type check
./test.sh # Run tests (skips LLM-dependent tests without API keys)
./pi-test.sh # Run pi from sources (can be run from any directory)
Supply-chain hardening
We treat npm dependency changes as reviewed code changes.
- Direct external dependencies are pinned to exact versions. Internal workspace packages remain version-ranged.
.npmrcsetssave-exact=trueandmin-release-age=2to avoid same-day dependency releases during npm resolution.package-lock.jsonis the dependency ground truth. Pre-commit blocks accidental lockfile commits unlessPI_ALLOW_LOCKFILE_CHANGE=1is set.npm run checkverifies pinned direct deps, native TypeScript import compatibility, and the generated coding-agent shrinkwrap.- The published CLI package includes
packages/coding-agent/npm-shrinkwrap.json, generated from the root lockfile, to pin transitive deps for npm users. - Release smoke tests use
npm run release:localto build, pack, and create isolated npm and Bun installs outside the repo before tagging a release. - Local release installs, documented npm installs, and
pi update --selfuse--ignore-scriptswhere supported. - CI installs with
npm ci --ignore-scripts, and a scheduled GitHub workflow runsnpm audit --omit=devplusnpm audit signatures --omit=dev. - Shrinkwrap generation has an explicit allowlist for dependency lifecycle scripts; new lifecycle-script deps fail checks until reviewed.
License
MIT