Skip to content

Pricing
Compare
Blog

Sign in Get started

Site footer

Route every request to the right model, agent, skill, tool or human, and know why.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0v1.7.0enterprise edition

The daily newsletter

Models, LLMs and agents, one email a day. Confirm by email; leave with one click.

Email address

Product

Services
Models
Marketplace
Playground
Browser extension
Desktop app
Pricing

Developers

Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Self-hosting
Downloads

Company

Blog
Newsletter
Changelog
Support
Talk to sales
Status
Security
PyPI
npm

OpenSmartRouteCopyright 2026 the OpenSmartRoute contributors. Open source under Apache-2.0.

Terms Privacy Report a vulnerability

Support assistant

Connecting...

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Marketplace/Skills

Skills that teach a model one job well

Step-by-step SKILL.md packages an AI follows for a single kind of task.

A skill is a focused playbook - instructions, examples and constraints - that makes any model reliable at one job, from SQL reporting to changelog writing. The router fills a plan's skill slot with the best match for the request.

163.4K SkillsPublish yours

One job, done consistently
Model-agnostic instructions
Composable into plans

Agents6822 Personas6760 Prompts19466 Templates32 Tools33335 Models

163395 results

455

agent-template-rust

This repository is a Copier template for generating Rust projects. It is not itself the generated Rust project. Files under `template/` are copied or rendered into downstream projects, and files under

by leynosGitHub

Not rated yet

Free

f1-game-telemetry

Guidance for AI coding agents working in this repository. Humans should start with [CONTRIBUTING.md](CONTRIBUTING.md).

by rdgonzagaGitHub

terraform

Act as a Brutal Senior System Engineer. Laconic, peer-to-peer, and minimal. No hand-holding; focus on high-level architecture, security, automation, and performance.

by notseekeruGitHub

diagram_website

Act as a Brutal Senior System Engineer. Laconic, peer-to-peer, and minimal. No hand-holding; focus on high-level architecture, security, automation, and performance.

by notseekeruGitHub

wp-framework

Tool-agnostic brief for AI coding agents (Claude Code, Copilot coding agent, Codex). `rtcamp/wp-framework`: shared base contracts (interfaces, abstracts, traits) and small utilities consumed via Compo

by rtCampGitHub

Manifesto

This file applies to any AI agent (Claude, Copilot, Cursor, Codex, etc.) making changes in this repository — yours or a collaborator's. If you are an agent reading this: these rules override your defa

by LiberHackGitHub

IC-Botos_Track

Este repositório desenvolve uma metodologia para extrair, quantificar e visualizar a formação espacial de botos em vídeos aéreos zenitais. O sistema deve produzir representações geométricas, métricas,

by ReinanArgoloGitHub

UI_UX

DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and steps, using queues, using the DBOS Client

by dilmurodmuxsinjonovGitHub

zemn

Frontend notes

by zemn-meGitHub

gnoe2e

gnoe2e is a Go module that runs txtar scenarios against real multi-validator gnoland clusters built from this checkout, with the package-approver oracle (`contribs/gpao`) supervised from the script. I

humanizer

This file explains how to change Humanizer without breaking its package or prompt.

by akitaonrailsGitHub

metamaterials

Repository Instructions

demo-nativewind

This is an Expo/React Native mobile application. Prioritize mobile-first patterns, performance, and cross-platform compatibility.

by Online13GitHub

Reprise

改代码后跑 `npm run check`（[门禁](docs/engineering-gates.md)）。只改文档跑 `npm run verify:docs`。不要为一次改动默认跑全套。新增或修改门禁时，同一次变更必须附一个能让该门禁失败的自动化用例（[反向用例](docs/decisions/accepted/2026-08-15-gate-reverse-tests.md)）。覆盖率阈值

by caulifGitHub

OpenCode-Cybersecurity-Skills

This repository contains project-scoped OpenCode cybersecurity skills, validation tooling, and documentation for authorized defensive security assessment workflows.

by WebvelopersGitHub

mcp

Guidance for AI coding agents working in this repository.

by sphinx-contribGitHub

clard

Clard：Linux 代理管理工具（Rust）。架构 = root 常驻服务 `clard-helper`（持有 mihomo 核心、TUN 与全部数据）+ TUI 客户端 `clard`（ratatui）。

by kuraxiiGitHub

poc-launchers

ARM64 移植工具中的设备诊断启动器集合。

by jenny92-techGitHub

cursor-origin

Hub repo for Cursor stress-test sub-projects. GitHub: `az9713/cursor-origin`. Each product lives in its own folder with its own `index.html`. Do not put app code at the repo root.

by az9713GitHub

tt

The owner authorizes direct commits to mewhhaha/tt main and ongoing exploration of a fast refinement-first structural language. Preserve concurrent changes and never force-push. Publishing packages, d

by mewhhahaGitHub

shoulda-used-that

For work on domain behavior, use the repository skill `shoulda-development` and load only the relevant public contract, decision receipt, schema, source, and tests.

by pradeeptathineniGitHub

n42appv2

Common generation commands: - `flutter pub run intl_utils:generate` regenerates localization files. - `flutter pub run build_runner build --delete-conflicting-outputs` refreshes generated DI/model cod

by n42blockchainGitHub

stryke

The following Storm Software ecosystems are maintained in **separate repositories**. Do **not** modify their package code, vendored scaffolding, or `node_modules` contents in this repo — including via

by storm-softwareGitHub

full-stack-starter

This file defines the shared instructions for coding agents working in this repository.

by ericsharkGitHub

1
200
201
202
203
204
6809