Routed

The Universal Local Router for Agent Skills

Overview | Architecture | Installation | Quick Start | Comparison | Environments | CLI | FAQ | Star History | License

[!TIP] Download standalone installers directly from GitHub Releases: RoutedSetup.exe (Windows), RoutedSetup.pkg (macOS), and RoutedSetup.deb (Linux).

---

Overview

Routed is a universal, local, zero-token router for Agent Skills across AI coding environments. It automatically scans, indexes, and routes coding prompts to the most relevant skill using a local hybrid search engine combining Okapi BM25, exact matching, and local dense semantic embeddings.

• Zero Token Cost: Eliminates costly LLM routing calls (saving 1,000+ prompt tokens per interaction).
• Sub-20ms Latency: Local CPU-evaluated hybrid search responds instantly without network roundtrips.
• Privacy First: Prompt routing is executed 100% locally; no user queries leave your machine.
• Multi-Skill Dispatch: Decomposes compound prompts and activates multiple skills simultaneously.

---

Architecture

Routed evaluates queries using a multi-tier hybrid scoring pipeline running entirely on local CPU:

flowchart LR
    UserPrompt["User Prompt (/route)"] --> Engine["Routed Core Engine"]

    subgraph Engine["Hybrid Scoring Pipeline (Local CPU)"]
        Exact["Exact / Alias Match (10%)"]
        BM25["Okapi BM25 Lexical (25%)"]
        Semantic["Dense Vector Embeddings (60%)"]
        Meta["Metadata & Recency (5%)"]
    end

    Exact --> Scorer["Composite Hybrid Scorer"]
    BM25 --> Scorer
    Semantic --> Scorer
    Meta --> Scorer

    Scorer --> Selection["Top Skill(s) Resolved (< 20ms)"]
    Selection --> Agent["AI Host Agent (Antigravity / Claude / Cursor / OpenCode / Codex)"]

Loading

$$\text{Composite Score} = 0.60 \cdot \text{Semantic} + 0.25 \cdot \text{BM25} + 0.10 \cdot \text{Exact} + 0.05 \cdot \text{Metadata}$$

---

Comparison

Dimension	Routed (Local)	Traditional Cloud LLM Routing	Manual Skill Selection
Token Cost	$0.00 (Zero tokens)	500 to 2,000 paid tokens	$0.00
Latency	Under 20ms (Local CPU)	1,200ms to 3,500ms network API	Manual human browsing
Privacy	100% Local (Air-gapped)	Sends user prompts to cloud	Local
Ranking Engine	Deterministic Hybrid	Non-deterministic prompt drift	Memory or string grep
Multi-Agent Sync	Automatic adapter synchronization	Fragmented per-tool prompting	Manual copy and paste

---

Installation

Platform	Installer Package	Format	Quick Install
macOS	RoutedSetup.pkg / RoutedSetup.dmg	Apple Installer / Disk Image	Run .pkg or mount .dmg
Linux	RoutedSetup.deb / routed-linux-x64.tar.gz	Debian Package / Tarball	sudo dpkg -i RoutedSetup.deb
Windows	RoutedSetup.exe / Install-Routed.ps1	NSIS Executable Installer	Run RoutedSetup.exe

Build from Source

git clone https://github.com/bshea-1/Routed.git
cd Routed
npm install
npm run build
npm run setup

---

Quick Start

1. Interactive Setup Wizard

Run the setup wizard to detect installed AI coding tools and configure /route adapters:

routed setup

2. Discover & Index Skills

Scan local directories and build the hybrid index:

routed scan
routed skills

3. Route Prompts

Inside your AI agent chat (Antigravity, OpenCode, Claude Code, Cursor, Codex):

/route write a unit test for my authentication service using TDD

Or from your terminal:

routed route "audit accessibility and fix memory leaks" --explain

4. Diagnostics

Verify system health, SQLite indices, and embedding models:

routed doctor

---

Supported Environments

Environment	Adapter Path	Auto-Detection	Integration Method
Antigravity	~/.gemini/config/skills/route/SKILL.md	Supported	Native skill dispatch & background router
OpenCode	~/.opencode/skills/route/SKILL.md	Supported	Local skill loader & interactive prompts
Claude Code	~/.claude/skills/route/SKILL.md	Supported	Slash command integration & terminal runner
Cursor	.cursor/rules/routed.mdc	Supported	Rule-based automatic prompt interception
Codex	.agents/skills/route/SKILL.md	Supported	Universal Agentic Skill schema

---

CLI Reference

Command	Description	Example
routed setup	Run interactive setup wizard	routed setup
routed route "<prompt>"	Find matching skill(s) for a prompt	routed route "write unit test with TDD"
routed scan	Scan supported environments and update index	routed scan
routed skills	List all discovered and indexed skills	routed skills
routed adapters	Manage /route adapters across AI tools	routed adapters --install
routed doctor	Run diagnostics and self-repair	routed doctor --fix
routed reindex	Incrementally re-index and re-embed skills	routed reindex
routed watch	Continuously monitor skill dirs for changes	routed watch
routed feedback	Manage routing preferences and corrections	routed feedback --list
routed status	Display status and detected environments	routed status
routed benchmark	Run routing accuracy and latency benchmarks	routed benchmark
routed uninstall	Safely remove Routed and clean adapters	routed uninstall --dry-run

Click to view full CLI options

Usage:
  routed <command> [arguments] [options]

Commands:
  setup               Run the interactive setup wizard
  route "<prompt>"    Find the best matching Agent Skill(s) for a prompt
  scan                Scan supported AI environments and update index
  skills              List all discovered and indexed skills
  adapters            Manage /route adapters across AI coding tools
  doctor              Run system, database, and model diagnostics (--fix to repair)
  reindex             Incrementally re-index and re-embed installed skills
  watch               Continuously monitor skill directories for file changes
  feedback            Manage local routing preferences and corrections
  uninstall           Safely uninstall Routed and remove adapters (--dry-run available)
  status              Display current system status and detected environments
  benchmark           Run routing benchmark suite and measure accuracy and latency
  version             Print version information
  help                Display help screen

---

FAQ

How does Routed operate with zero external API keys?

Routed runs quantized ONNX dense embedding models (Snowflake Arctic Embed S / all-MiniLM-L6-v2) directly on local CPU alongside Okapi BM25. Vector similarity and text indices are cached in a local SQLite database, requiring no internet connection or cloud tokens.

How are multiple skills selected simultaneously?

When a prompt contains compound intents or conjunctions (such as "and", "with", "as well as"), Routed decomposes the prompt into sub-clauses, scores candidates across all clauses, and returns all matching skills in selectedSkills for joint agent activation.

Does Routed introduce noticeable latency?

No. Benchmark execution times average under 20 milliseconds on local CPU, making routing practically instantaneous compared to remote cloud roundtrips (1,200ms to 3,500ms).

Where are skill embeddings and cache files stored?

Routed stores its index and database files in standard platform directories:

• macOS: ~/Library/Application Support/Routed
• Linux: ~/.local/share/routed
• Windows: %LOCALAPPDATA%\Routed

---

Star History

---

License

MIT License. Copyright (c) 2026 bshea-1.

See LICENSE for full details.