Skip to main content
Fleet Pi is a local-first web workspace for Pi-powered coding agents. It runs on your machine, uses your own model-provider credentials (Google Gemini by default, with optional Amazon Bedrock, OpenAI, Anthropic, and others), and keeps agent memory, plans, skills, and artifacts as reviewable files inside agent-workspace/ so every change shows up in normal Git diffs.

Why Fleet Pi

Most coding-agent tools keep plans, memory, and session state locked away in the cloud or in ephemeral logs. Fleet Pi takes the opposite approach:

Reviewable agent state

Memory, plans, skills, and artifacts live in agent-workspace/ and show up in normal Git diffs.

Safe exploration before execution

Plan mode lets the agent inspect your repo, produce numbered execution plans, and keep plan cards resumable across refresh and resume — without touching files.

Local-first with your credentials

Runs entirely on your machine using your own model-provider credentials — Google Gemini by default, with Amazon Bedrock, OpenAI, Anthropic, and others available. No hosted SaaS account required.

Composable with Pi resources

Project-local skills, prompts, and extensions load automatically from .pi/ and agent-workspace/pi/.

Stack at a glance

LayerTechnology
FrameworkTanStack Start (Vite + Nitro) on Node ≥ 22
UIReact 19, TanStack Router, Tailwind CSS v4, shadcn/ui, agent-elements
Agent runtime@earendil-works/pi-coding-agent + @earendil-works/pi-ai
Model providerGoogle Gemini (gemini-3.5-flash) by default; Amazon Bedrock, OpenAI, Anthropic, Mistral, Groq, and Ollama also supported through Pi’s provider registry
Reliabilityopossum circuit breaker around every model call
Loggingpino + pino-pretty with PII redaction and request correlation IDs
Validationzod schemas + @asteasolutions/zod-to-openapi (generated openapi.json)
AuthBetter Auth with optional Google OAuth and SQLite
Monorepopnpm 10.33.3 workspaces + Turborepo

Features

CategoryCapability
ChatPersistent Pi sessions, NDJSON streaming, session resume after refresh, queued steering / follow-up prompts
ToolsRepo-scoped read, write, edit, bash, grep, find, ls, web_fetch, workspace_write, resource_install
PlanningRead-only Plan mode with structured execution plans, follow-up questionnaires, and resumable plan cards
Harness modeWorkspace-architecture mode that swaps general repo mutation tools for workspace_write + resource_install
Memoryagent-workspace/ keeps memory, plans, evals, and artifacts in Git under a versioned contract
ResourcesBrowser for project-local Pi skills, prompts, extensions, themes, and packages
ProvenancePer-run provenance records around session lifecycle, tool execution, and canonical file mutations

Three chat modes

Fleet Pi exposes the same chat surface in three distinct modes that change which tools the agent is allowed to call:

Agent mode

Full repo-scoped editing. read, write, edit, bash, plus workspace and resource tools.

Plan mode

Read-only inspection. Inspect-only tools, questionnaire follow-ups, structured plan cards.

Harness mode

Workspace architecture work. workspace_write and resource_install replace general mutation tools.

Two setup paths

Standalone

Run Fleet Pi locally as a web app with Pi-backed chat. Needs a Google Gemini API key by default, or credentials for any other supported provider.

Pi / Codex

Use the shared Codex local environment and worktree bootstrap flow for advanced multi-agent setups.

Where to go next

Quickstart

Install Fleet Pi and launch the workspace in under five minutes.

Configuration

Every environment variable Fleet Pi reads, and what it does.

Agent workspace

The durable workspace model that keeps memory and plans reviewable.

Architecture

Runtime boundaries between the browser client, web app, and agent workspace.

Source

Fleet Pi is open source under Apache 2.0. The canonical source of truth is the Qredence/fleet-pi repository — when the docs disagree with the code, trust the code.