rpi — a Rust-native coding-agent runtime
rpi is a library-first coding-agent runtime written in Rust, plus a terminal
agent built on top of it. Eleven composable crates span provider adapters, a
durable crash-resumable agent loop, a reusable runtime, a terminal UI, and a
stable plugin ABI — so the same code works as an embedded SDK or as a ready-to-run
rpi command.
rpi began as a Rust reimplementation of the Pi TypeScript SDK
by Mario Zechner. It now includes its own Rust-native plugin ABI and execution
infrastructure. See Acknowledgements and NOTICE
for upstream attribution.
Website · Docs · Extension catalog · rpi-package
See it in action
Interactive TUI, recorded with an isolated configuration. See the user guide for the full command surface.
Open the terminal agent and explore /help, with no real API key or model request. Recording script: demo/tui.tape.
The agent loop and a real write tool round-trip, recorded with no API key and no network — the same path the tests take. Source of truth is demo/sdk.tape; regenerate with task demo.
Three ways to use it
| You want | Depend on | Start at |
|---|
| A working terminal coding agent | nothing | cargo install rpi-cli |
| Your own agent inside your process | rpi-agent (+ rpi-ai, rpi-tools) | examples/minimal |
| A tool/provider that extends every session | rpi-plugin-sdk | examples/plugin-stub |
The three share one implementation. Build your tools once, debug them inside an
embedded agent, and ship the same code as a cdylib plugin that the global rpi
loads. See docs/agent/project-structure.md for the recommended
project layout.
Install
Prebuilt binary (no Rust toolchain needed):
curl -fsSL https://raw.githubusercontent.com/bigfish1913/pi-rust/main/scripts/install.sh | sh
Verifies the published SHA-256 checksum and installs to /usr/local/bin or
~/.local/bin. Preview first with --dry-run.
On Windows (x64), run in PowerShell 5.1 or later:
& ([scriptblock]::Create((Invoke-WebRequest -UseBasicParsing https://raw.githubusercontent.com/bigfish1913/pi-rust/main/scripts/install.ps1).Content))
Verifies the published SHA-256 checksum and installs to
$env:LOCALAPPDATA\Programs\rpi. Follow the printed instructions to add it to
PATH, then run rpi --version. Append -DryRun to preview, or use
-Version <version> and -Dir 'C:\Tools\rpi' to select a version and directory.
From crates.io (requires Rust 1.88+):
cargo install rpi-cli
rpi --version
Package managers:
brew tap bigfish1913/tap && brew install rpi # macOS (Apple silicon), Linux
scoop bucket add bigfish1913 https://github.com/bigfish1913/scoop-bucket
scoop install rpi # Windows
The Homebrew formula currently supports Apple silicon on macOS. Intel Macs can
use the prebuilt installer for releases with an x86_64-apple-darwin asset, or
cargo install rpi-cli. A winget manifest is open for
review.
From source:
git clone https://github.com/bigfish1913/pi-rust.git
cd pi-rust && cargo run -p minimal # offline agent, no API key required
Real output of the two offline examples — no credentials, no network, identical
bytes every run. Regenerate with task demo-transcript:
$ cargo run -q -p minimal
minimal example: 2 messages after run
- user
- assistant
assistant reply: Hello from the faux provider!
AgentEnd observed.
$ cargo run -q -p tools-example
tools example: 4 messages after run
wrote out.txt (28 bytes): "hello from the tools example"
AgentEnd observed; tool ran against OsExecutionEnv.
Quick start
The CLI
export ANTHROPIC_API_KEY=... # or OPENAI_API_KEY, or ~/.rpi/agent/models.json
rpi # interactive TUI
rpi -p "summarize the README" # one-shot
rpi --mode json -p "list the crates" # machine-readable event stream
Sessions persist as JSONL and survive a crash mid-run; rpi resumes from the
last committed frame rather than replaying the turn. Custom Anthropic or
OpenAI-compatible gateways are declared in ~/.rpi/agent/models.json and
selected with --model <provider>/<model>.
Runtime diagnostics
To investigate slow model preparation, context construction, tool execution, or
persistent assistant-frame writes, temporarily enable stderr diagnostics:
RPI_AGENT_DIAGNOSTICS=1 RPI_FRAME_DIAGNOSTICS=1 \
rpi -p "reproduce the issue" 2>rpi-diagnostics.log
여기까지가 README 앞부분입니다. 나머지는 원문에서 읽을 수 있습니다. README 전문 보기 ↗
