Upstream baseline: Pi Coding Agent 0.85.0, commit 47236c84450656043dd8fb21c8513d1421505ae3, verified 2026-09-04.

Pi Coding Agent is the minimal agent harness published at pi.dev. AIWG's pi provider targets that harness directly; pi.dev is not a separate provider ID.

Pi is an experimental AIWG deployment provider. AIWG installs declarative context, skills, prompt templates, and a reviewed trust-gated policy extension; it does not install Pi packages or credentials. Start with Install, Connect, and Verify for the general AIWG setup journey.

Pi 0.85.0 requires Node.js 22.19 or newer and is published as @earendil-works/pi-coding-agent.

npm install -g @earendil-works/pi-coding-agent
npm install -g aiwg
cd /path/to/project

aiwg use all --provider pi --dry-run
aiwg use all --provider pi

The deployment command refreshes AIWG's shared project context and prints a verification result. Follow any reload notice in that output before starting a Pi session.

Here, AIWG's --provider pi selects the coding-agent integration. It is not Pi's own --provider option, which selects an LLM backend such as OpenRouter. Pi documents its model flags in the coding-agent README.

Project-local settings, extensions, skills, and prompts are trust-gated; context files such as AGENTS.md load independently of that decision. In interactive Pi, run /trust and restart after approving the project. Non-interactive modes do not show the trust dialog, so every automated invocation must choose explicitly between --approve and --no-approve; see Pi's project trust documentation.

pi
# In Pi: /trust, approve, then restart

aiwg doctor --provider pi
aiwg steward capabilities --provider pi

Try one small task immediately after trust and verification:

Review this project's README and getting-started docs for unclear positioning,
missing setup steps, or unsupported claims. Return the three highest-priority
fixes with file references and a recommended next edit.

Success means Pi names the intended project, loads AGENTS.md and the trusted AIWG project resources, and produces a concrete review you can inspect.

For a bounded, non-interactive check that loads trusted project resources:

PI_CODING_AGENT_SESSION_DIR="$(mktemp -d)" \
  pi --approve --mode json -p "List the AIWG skills available in this project"

This may call the selected model and consume tokens. Use --no-approve when testing without project-local resources.

Pi discovers project skills in .pi/skills/ and .agents/skills/, as documented in Skills. Prompt templates live in .pi/prompts/; AIWG flattens generated prompt names because Pi's prompt-template discovery is non-recursive.

aiwg refresh --provider pi --dry-run
aiwg refresh --provider pi
aiwg list
aiwg remove <installed-framework-or-addon> --dry-run
aiwg remove <installed-framework-or-addon>

aiwg remove operates on an installed framework or addon, not on a provider alone. Repeat it for each installed item you intend to remove. AIWG only removes receipted files and preserves operator-owned .pi/settings.json, prompts, skills, extensions, packages, sessions, and Pi's trust decisions.

For user scope, session handling, OpenRouter examples, limitations, and troubleshooting, see the Pi operational reference.

External Ralph can launch Pi with --provider pi; pass a Pi-native provider/model identifier using --model, and optionally --thinking and --tools. Session ingestion supports authorized Pi v3 JSONL roots; see Pi session acquisition.