# BrokeCrew [![CI](https://github.com/oiupoyt/brokecrew/actions/workflows/ci.yml/badge.svg)](https://github.com/oiupoyt/brokecrew/actions) [![License](https://img.shields.io/badge/license-MIT%20OR%20Apache--2.0-blue.svg)](LICENSE-MIT) [![Crates.io](https://img.shields.io/crates/v/brokecrew.svg)](https://crates.io/crates/brokecrew) **A lightweight, resilient, async-first Rust CLI that coordinates a specialized team of AI personas backed by OpenRouter models.** BrokeCrew makes free-tier models first-class citizens while eliminating their instability through live model catalog discovery, ranked multi-candidate fallback cascades, account-wide rate-limit budgeting, and multi-agent handoff pipelines. --- ## Why BrokeCrew (vs LiteLLM or RouteLLM)? | Feature | BrokeCrew | LiteLLM Proxy / RouteLLM | | :--- | :--- | :--- | | **Footprint & Startup** | Single standalone native binary (~15MB), sub-10ms startup. | Heavy Python runtime, tens of pip dependencies, slower startup. | | **Hardware Fit** | Designed to run smoothly on low-RAM ARM tablets, Raspberry Pis, and local dev boxes. | Heavy memory consumption unsuited for constrained devices. | | **Persona Fallback Walk** | Declarative ranked candidates per persona (`qwen:free` → `deepseek:free` → paid fallback). | Static routing with complex configuration layers. | | **Live Catalog Awareness** | Syncs `/v1/models` in background; skips dropped/offline models before wasting requests. | Often returns raw 404/400 errors when models vanish. | | **Account-Wide Budgeting** | Tracks rolling 20 req/min and daily quotas (50 or 1,000 req/day) across all calls including router. | Typically only tracks proxy tokens, not OpenRouter account limits. | | **Multi-Agent Handoffs** | Built-in typed pipelines (`coder` → `reviewer`) with real-time SSE streaming per persona. | Requires external orchestration frameworks (LangGraph, CrewAI). | --- ### Technical Invariants - **Fail-Fast Cascade Walk**: Free endpoints on OpenRouter frequently return transient `429`, `503`, or drop out of `/v1/models` without warning. Candidate resolution treats failures as cascade triggers rather than fatal aborts, stepping to the next viable candidate model within `<250ms`. - **Sliding-Window Budgeting**: Token usage and request counts are stored in atomic sliding windows (`VecDeque>`). Router and classifier calls deduct from the shared account budget to prevent downstream API lockouts. - **Async Non-Blocking SSE**: Streaming tokens are decoupled from the Ratatui TUI render loop via crossbeam/tokio MPSC channels, ensuring UI frame rates remain at 60 FPS even during erratic remote network jitter. --- ## OpenCode / Pi-Style Interactive TUI Simply run `brokecrew` to enter the rich, full-screen interactive TUI: ```bash brokecrew ``` - **Live Team View**: Color-coded persona indicators (`● coder`, `● reviewer`, `● architect`), token streaming with markdown & syntax formatting. - **Quota & Budget Monitor**: Real-time headers displaying rolling minute and 24h limits (`1m: 2/20`, `24h: 14/50`). - **Interactive Modals**: - `[Tab]` — Open Persona Selector (switch between intelligent Stage A/B `Auto-Route` and dedicated personas). - `[Ctrl+P]` — Open Pipeline Selector (execute multi-agent pipelines like `build-and-review`). - `[PgUp/PgDn]` — Scroll conversation history. - `[Ctrl+L]` — Clear screen. - `[Esc]` — Dismiss modal or exit. - **Non-TUI / Scripting**: Use `brokecrew --cli` or `brokecrew chat "..."` for headless pipelines or script integration. --- ## Quickstart ### 1. Installation **One-line curl install (Linux & macOS):** ```bash curl -fsSL https://raw.githubusercontent.com/oiupoyt/brokecrew/main/install.sh | bash ``` **Via Cargo (Crates.io):** ```bash cargo install brokecrew ``` **Build from source:** ```bash git clone https://github.com/oiupoyt/brokecrew.git cd brokecrew cargo install --path . ``` ### 2. Configure OpenRouter API Key BrokeCrew securely stores your API key in your OS credential store (`keyring`), never in plaintext: ```bash brokecrew config set-key ``` *(You can also export `OPENROUTER_API_KEY="sk-or-v1-..."` or pass `--api-key` for headless servers).* ### 3. Start Chatting Zero-config instant routing: ```bash brokecrew chat "build me a proxy checker site" ``` *Stage A regex/keyword routing automatically detects "build/site" and dispatches to the `coder` persona in 0ms!* Run an interactive team session: ```bash brokecrew chat ``` Run a multi-agent handoff pipeline: ```bash brokecrew chat --pipeline build-and-review "Implement a token bucket rate limiter in Python" ``` Check model catalog and quota health: ```bash brokecrew status ``` List available personas: ```bash brokecrew personas list ``` --- ## Declarative Personas (`personas.toml`) Personas are defined in `~/.config/brokecrew/personas.toml` (or `./config/personas.example.toml`): ```toml [[persona]] name = "coder" system_prompt = "You are a precise, terse coding assistant. Output working code, minimal commentary." trigger_words = ["build", "code", "script", "function", "website", "api"] [[persona.candidates]] id = "qwen/qwen-2.5-coder-32b-instruct:free" tier = "free" is_stealth = false [[persona.candidates]] id = "deepseek/deepseek-coder:free" tier = "free" is_stealth = false [[persona.candidates]] id = "google/gemini-2.0-flash-001" tier = "paid" is_stealth = false ``` --- ## License Dual-licensed under either: - Apache License, Version 2.0 ([LICENSE-APACHE](LICENSE-APACHE)) - MIT license ([LICENSE-MIT](LICENSE-MIT)) at your option.