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-2.0v1.6.0enterprise edition

The daily newsletter

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

Email address

Product

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.

156.4K SkillsPublish yours

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

Agents6650 Personas6717 Prompts18886 Templates31 Tools32184 Models

156395 results

449

wireless-security-wifi-pentest

Wireless security penetration testing with aircrack-ng, WEP/WPA/WPA2/WPA3 attacks, and 802.11 exploitation

by reason-machinesskills.sh

Not rated yet

Free

wireless-security-wifi-pentesting

Expertise in Wi-Fi penetration testing using aircrack-ng, monitor mode, WEP/WPA/WPA2/WPA3 cracking, and wireless security assessment.

by reason-machinesskills.sh

wxmini-security-audit

Automated WeChat mini-program security auditing framework using Claude Code Agent Teams with 7 specialized agents for comprehensive static analysis

by reason-machinesskills.sh

zen-ai-pentest-framework

AI-powered autonomous penetration testing framework with multi-agent system, real security tool execution, and compliance reporting

by reason-machinesskills.sh

oracle-advisor

Request a second-model consultation with explicit API, browser, or render transport and per-run provenance. Use when transport choice or model/effort evidence is part of the request; the existing orac

by steipeteskills.sh

ddd-codegen

OpenAPI-first DDD codegen — core-only after YAML edits; full scaffold for new domains

by rahalioGitHub

no-codegen-commit

Never commit or push the local .codegen directory

by rahalioGitHub

git

Git, GitHub and gh instructions

by eastlondonerGitHub

api

API controller and route conventions

by ECCdigitalGitHub

doc

description: ドキュメントの記述方法 globs: *.rs,*.md alwaysApply: false ---

by frozenlibGitHub

git

Branch names should go by the following structure (anything in "{}" brackets is a placeholder). "{short-slug}" should be replaced with a short name that best describes the changes - do ask for confirm

by linchpinGitHub

frontend-architecture

Clean, extensible React/TypeScript architecture for Vazinedalat frontend

by vazinedaalatGitHub

tdd

TEST-DRIVEN DEVELOPMENT GUIDELINES. MANDATORY READING BEFORE WRITING CODE.

by LuthienResearchGitHub

100-agent-mode

Autonomous agent execution mode

by internet-dotGitHub

uv

These rules define strict guidelines for managing Python dependencies in this project using the `uv` dependency manager.

by batpoolGitHub

ddd-codegen

OpenAPI-first DDD codegen — core-only after YAML edits; full scaffold for new domains

by rahalioGitHub

docs

Update root README.md

by commercetoolsGitHub

apple-au-accessibility

WCAG 2.2 AA, keyboard-first, and testable a11y gates for Apple AU-style UI

by axcel-bladeGitHub

codeguard-0-cloud-orchestration-kubernetes

rule_id: codeguard-0-cloud-orchestration-kubernetes

by kgrizz-gitGitHub

testing-visual

The full snapshot suite is slow and its failures are hard to attribute. Always scope to the component you changed:

by Ocean-Industries-Concept-LabGitHub

rules

1. ### **Module layout**

by titaniummachine1GitHub

ponytail

Ponytail, lazy senior dev mode. Always pick the simplest solution that works.

by gannonhGitHub

persona-meridian

Apply when the user is reviewing an epic or plan, asking for a VP/Meridian review, or running the review checklist. Use Meridian (VP Success) persona.

by wtthorntonGitHub

rules

1. ### **Module layout**

by titaniummachine1GitHub

1
136
137
138
139
140
6517