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
| Layer | Technology |
|---|---|
| Framework | TanStack Start (Vite + Nitro) on Node ≥ 22 |
| UI | React 19, TanStack Router, Tailwind CSS v4, shadcn/ui, agent-elements |
| Agent runtime | @earendil-works/pi-coding-agent + @earendil-works/pi-ai |
| Model provider | Google Gemini (gemini-3.5-flash) by default; Amazon Bedrock, OpenAI, Anthropic, Mistral, Groq, and Ollama also supported through Pi’s provider registry |
| Reliability | opossum circuit breaker around every model call |
| Logging | pino + pino-pretty with PII redaction and request correlation IDs |
| Validation | zod schemas + @asteasolutions/zod-to-openapi (generated openapi.json) |
| Auth | Better Auth with optional Google OAuth and SQLite |
| Monorepo | pnpm 10.33.3 workspaces + Turborepo |
Features
| Category | Capability |
|---|---|
| Chat | Persistent Pi sessions, NDJSON streaming, session resume after refresh, queued steering / follow-up prompts |
| Tools | Repo-scoped read, write, edit, bash, grep, find, ls, web_fetch, workspace_write, resource_install |
| Planning | Read-only Plan mode with structured execution plans, follow-up questionnaires, and resumable plan cards |
| Harness mode | Workspace-architecture mode that swaps general repo mutation tools for workspace_write + resource_install |
| Memory | agent-workspace/ keeps memory, plans, evals, and artifacts in Git under a versioned contract |
| Resources | Browser for project-local Pi skills, prompts, extensions, themes, and packages |
| Provenance | Per-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 theQredence/fleet-pi repository — when the docs disagree with the code, trust the code.