Fleet Pi is a local-first web workspace for Pi-powered coding agents. It runs on your machine, uses your own AWS Bedrock credentials, and keeps agent memory, plans, skills, and artifacts as reviewable files insideDocumentation Index
Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt
Use this file to discover all available pages before exploring further.
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 standard AWS Bedrock credentials. No hosted SaaS account required.
Composable with Pi resources
Project-local skills, prompts, and extensions load automatically from
.pi/ and agent-workspace/pi/.Features
| Category | Capability |
|---|---|
| Chat | Persistent Pi sessions, streaming responses, session resume after refresh |
| Tools | Repo-scoped read, write, edit, and bash in Agent mode |
| Planning | Read-only Plan mode with structured execution plans, follow-up questions, and resumable plan actions |
| Memory | agent-workspace/ keeps memory, plans, evals, and artifacts in Git |
| Resources | Browser for project-local Pi skills, prompts, and extensions |
| Architecture | TanStack Start app + Nitro backend + React 19 UI |
Agent mode and Plan mode
- Agent mode enables repo-scoped coding tools (
read,write,edit,bash) plus approved external Pi tools. - Plan mode is read-only. The agent inspects the repo, asks focused follow-up questions, and produces numbered execution plans. Structured plan cards keep execute, stay, and refine actions visible after refresh or session resume.
Two setup paths
Standalone
Run Fleet Pi locally as a web app with Pi-backed chat. Needs Bedrock access and AWS credentials.
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.
Agent workspace
Understand the durable workspace model that keeps memory and plans reviewable.
Adaptive workspace contract
The canonical workspace contract and projection boundary.
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.