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-2.0SDK 1.3.0enterprise edition

Product

Models
Marketplace
Playground
Pricing

Developers

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

Company

Blog
Changelog
Support
Security
PyPI
npm
Source

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.

147.7K SkillsPublish yours

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

Agents6380 Personas5428 Prompts17744 Templates31 Tools31217 Models

147678 results

446

competitor-launch-radar

Weekly scan of Product Hunt + Hacker News for NEW AI-agent-framework launches outside the 9-framework cohort already tracked by ai-framework-watch

by anajuliabitGitHub

Not rated yet

Free

dev-loop

Use when the user wants to audit, diagnose, optimize, or protect a software project's development feedback loop, including slow local builds, slow tests, oversized validation scope, small changes trig

by ceasarXuuGitHub

bio-variant-annotation

Annotates VCF variants with functional consequences, population frequencies, and pathogenicity scores using bcftools annotate/csq, Ensembl VEP, SnpEff, and ANNOVAR. Use when deciding which annotation

by lilinjiGitHub

android-to-harmonyos-migration-workflow

多 agent 协作的 Android 到 HarmonyOS 代码迁移工作流（迭代式）。当用户需要将 Android 项目迁移到 HarmonyOS 时触发，提供：1) Analyzer Agent 扫描代码结构 2) Planner Agent 制定迁移计划 3) Translator Agent 执行代码转换 4) **Validator Agent（验证代理）** 使用 **ohos-ap

by openharmonyinsightGitHub

ai-hive-simulate-he-jiayan

当用户搜索用AI模拟何加盐、AI模拟何加盐、何加盐AI模拟、何加盐数字人、何加盐AI分身、何加盐内容风格、何加盐选题、何加盐文案、何加盐短视频、何加盐知识库、何加盐思想顾问、何加盐战略顾问，或希望借助 AI 研究何加盐公开内容中的商业认知、创业、企业经营、财经分析、组织管理或增长方法时使用。本 Skill 面向创业者、企业管理者、职场人、投资与商业内容受众，先建立公开来源样本库，再提炼选题母题、受

by wubin1836GitHub

stacks-buddy

Use when working with the Stacks CLI (buddy/bud/stacks/stx) — understanding all 50+ commands with their flags and options, adding custom commands, the make:* scaffolding commands, development server c

by statushqorgGitHub

maintain-cross-platform

Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.

by agisotaGitHub

detecting-serverless-function-injection

Detects and prevents code injection attacks targeting serverless functions (AWS Lambda, Azure Functions, Google Cloud Functions) through event source poisoning, malicious layer injection, runtime comm

by EstudelyGitHub

pptx

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts

by dy9759GitHub

gse-go

Detect project state, propose next activity. Triggered by /gse:go. Includes --adopt mode for existing projects.

by nicolasguelfiGitHub

ccm-expert

CSA CCM expert for cloud security. Deep knowledge of Cloud Security Alliance Cloud Controls Matrix including 197 controls, 17 domains, CAIQ questionnaire, cloud service models (IaaS/PaaS/SaaS), shared

by aibot88GitHub

capability-creator

Autonomous loop for **uplifting** a target capability on Qwen3.5-4B through any combination of SFT, OPD, GRPO, and agentic-GRPO stages chained into a multi-method pipeline. Use when asked to "train ca

by ericfloGitHub

todowrite-orchestration

Track progress in multi-phase workflows with TodoWrite. Use when orchestrating 5+ phase commands, managing iteration loops, tracking parallel tasks, or providing real-time progress visibility. Trigger

by Activer007GitHub

gstack

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads,

by shengdabaiGitHub

ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROA

by thedixitjainGitHub

fastapi

Build Python APIs with FastAPI, Pydantic v2, and SQLAlchemy 2.0 async. Covers project structure, JWT auth, validation, and database integration with uv package manager. Prevents 7 documented errors. U

by Shresth-shGitHub

brutal-deepresearch

Structured deep research pipeline with confirmation gates and resume support. Generates outline, launches parallel research agents, produces validated JSON results and markdown report.

by sssemilGitHub

javascript-testing-patterns

Implement comprehensive testing strategies using Jest, Vitest, and Testing Library for unit tests, integration tests, and end-to-end testing with mocking, fixtures, and test-driven development. Use wh

by majiayu000GitHub

td-builder-howto

Load when working in or with the TD Builder Alpha project — building, editing, or debugging TouchDesigner networks via the td-builder MCP. Triggers on TouchDesigner, TD, .toe, .tox, TouchDesigner oper

by TrueFiascoGitHub

hf-cli

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managi

by RatnaAtikaGitHub

courier-content-writer

当需要撰写快递相关专业文案、行业指南、科普文章时使用。触发场景：快递/物流品牌内容。当用户提到"快递内容"、"快递"、"物流品牌内容"、"courier"、"content"时应触发此技能。

by caishengoldGitHub

dataset-engineering

Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for traini

by ScientiaCapitalGitHub

skill-librarian

Use when the user wants to make an agent skill self-contained and portable, or file a skill into a central skill library so it works on any machine and across agent runtimes (Claude Code, Codex, Herme

by davehagueGitHub

ai-seo

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine opti

by TiagoDaninGitHub

1
5914
5915
5916
5917
5918
6154