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-2.0v1.4.0enterprise 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
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.

150.6K SkillsPublish yours

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

Agents6470 Personas6709 Prompts18556 Templates31 Tools31517 Models

150630 results

446

risk-metrics-calculation

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.

by kutluGGitHub

Not rated yet

Free

acceptance-scenario-orchestrator

识别每日验收、PR 验收、commit 验收、未发布分支验收、缺陷复测、视觉回归和发布前验收等场景，并为 create-visual-test-to-kb 生成测试范围、指差法步骤、预期结果、证据链、截图回读和报告结构。Use when the user asks to optimize or run visual acceptance across different scenarios, as

by inernoroGitHub

criminal-case-trial-mock-training

--- name: criminal-case-trial-mock-training version: 1.0.0 name_en: criminal-case-trial-mock-training description: 对话式刑事庭审模拟训练，AI扮演审判员/公诉人等角色与律师进行庭审对抗推演。触发：模拟庭审/庭审练习/质证训练/辩论训练/庭审演练。不触发：生成辩护词——调用辩护词技能

by ahang1598GitHub

youtube-derivative-cuts

Plan a prioritized derivative content slate from one long YouTube source video using metadata, transcript, chapters, audits, portfolio evidence, and available metrics

by GeorgeQLeGitHub

dotnet-native-interop

Calls native libraries via P/Invoke. LibraryImport, marshalling, cross-platform resolution.

by rudironsoniGitHub

dotnet-native-interop

Calls native libraries via P/Invoke. LibraryImport, marshalling, cross-platform resolution.

by rudironsoniGitHub

kotlin-ktor-patterns

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.

by NguyenPhuocAnhDungGitHub

python-pypi-package-builder

End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI. Covers all four build backends (setuptools+setuptools_scm, hatchling, flit, poetr

by jcasnellie69GitHub

eds-block-css

This skill provides comprehensive guidelines for creating CSS for new Edge Delivery Services (EDS) blocks in Adobe Experience Manager Universal Editor projects. The focus is on simple, maintainable CS

by ComwrapUkReplyGitHub

stock-valuation

Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models

by severin-yeGitHub

heygen-avatar

Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (descript

by nickthelegendGitHub

building-automated-malware-submission-pipeline

Builds an automated malware submission and analysis pipeline that collects suspicious files from endpoints and email gateways, submits them to sandbox environments and multi-engine scanners, and gener

by adriannoesGitHub

cursor-subagent-creator

Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.c

by MercurykzGitHub

reiteracao-automatica-sisbajud-e-proporcionalidade

Use para Reiteração Automática Sisbajud e Proporcionalidade no Direito brasileiro, com análise do título, prova, estratégia do credor e defesa do executado, pedidos e resultado útil. Não use para conc

by bbpropulseGitHub

exploring-llm-evaluations

Investigate AI observability evaluations — `script` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their confi

by hanzoaiGitHub

kotlin-ktor-patterns

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.

by pvbangGitHub

gpt-multimodal

Analyze images and multi-frame sequences using OpenAI GPT series

by David-Li0406GitHub

governance-and-risk

Use when making architectural decisions without documentation, skipping risk analysis, accepting risks without mitigation, or treating governance as optional bureaucracy - enforces mandatory DAR/RSKM

by tomevault-ioGitHub

honcho

Configure and troubleshoot Honcho memory for Hermes.

by jgilb17GitHub

migrate-vstest-to-mtp

Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", or men

by josejaviercanonGitHub

relationships

Build meaningful connections on Botbook.space — the social graph for AI agents. Set relationship types (follow, friend, partner, mentor, rival, and more), manage your MySpace-style Top 8, browse agent

by baneeishaqueGitHub

bio-crispr-screens-hit-calling

Cross-method decision tree for calling hits in pooled CRISPR screens. Catalogs statistical models (MAGeCK RRA, MAGeCK MLE, BAGEL2, drugZ, JACKS, Chronos, CERES), experimental designs each is built for

by bg-szyGitHub

clerk-orgs

Clerk Organizations for B2B SaaS - create multi-tenant apps with org switching, role-based access, verified domains, and enterprise SSO. Use for team workspaces, RBAC, org-based routing, member manage

by filipecabral18GitHub

terraform-provider-tests

Analyze and improve Terraform provider test coverage using terraform-plugin-testing v1.13.3+ patterns. Use when (1) analyzing test coverage gaps, (2) adding missing tests (drift detection, import, ide

by David-Li0406GitHub

1
5963
5964
5965
5966
5967
6277