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
MCP server
Self-hosting

Company

Blog
Changelog
Support
PyPI

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

strip-llms

Stripe Documentation documentation and resources. Use this skill when working with Stripe Documentation or when the user mentions stripe documentation.

by hk-vkGitHub

Not rated yet

Free

sdd:implement

Implement a task with automated LLM-as-Judge verification for critical steps

by Pepsi1978GitHub

shipment-reconcile

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status, and closes shipments with the single-artifac

by softwaresaltGitHub

liquidation-cascade-monitor

Monitors DeFi protocol liquidation thresholds and positions CEX perp shorts on OKX to profit from cascade price impact. Does NOT compete for onchain liquidation bonuses (Flashbots domain). Instead: de

by yelunamaGitHub

harmonyos-arkui

HarmonyOS ArkUI 声明式 UI 开发 skill：ArkTS 声明式页面、状态管理 V1/V2、列表导航动画手势、多端自适应的方法论与文档路由。 TRIGGERS: "ArkUI声明式UI", "ArkUI组件", "@State @Prop @Link状态管理", "@Provide @Consume跨层级", "List列表/Grid网格", "Navigation导航", "T

by ximingGitHub

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge an

hunt-idor

Hunting skill for Insecure Direct Object Reference / Broken Object Level Authorization (BOLA — OWASP API1:2023). Built from 1,117 public IDOR bug bounty reports across HackerOne, Bugcrowd, Intigriti,

by begineer-pyGitHub

shipment-reconcile

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status, and closes shipments with the single-artifac

by softwaresaltGitHub

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design system

by minhcamonGitHub

bmad-retrospective

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

by one-step-beh1ndGitHub

environmentalist-analyst

Analyzes events through environmental lens using ecological principles, systems thinking, sustainability frameworks, and conservation biology to assess ecosystem health, biodiversity impacts, and long

by rysweetGitHub

android-example-voting

Build a voting/poll dApp on Midnight Network using the Kuira Android SDK — Compact smart contract with create/cast/close circuits, passkey-derived identity, embedded wallet, Compose UI, reactive ledge

by ArpitSiNgh08GitHub

ax-agent

This skill helps an LLM generate correct AxAgent code using @ax-llm/ax. Use when the user asks about agent(), child agents, namespaced functions, discovery mode, shared fields, llmQuery(...), RLM code

by colinfwalshGitHub

rar-kody-w-windows-vm-install-lab

Runs an allowlisted Hyper-V Windows 11 lab for repeatable RAPP installer release testing with an embedded, hash-verified toolkit.

by kody-wGitHub

android-example-voting

Build a voting/poll dApp on Midnight Network using the Kuira Android SDK — Compact smart contract with create/cast/close circuits, passkey-derived identity, embedded wallet, Compose UI, reactive ledge

by vynrideGitHub

skillify

Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)

by aicodeproGitHub

research-paper-writing

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

by arun-raze19GitHub

document-generate

Generate missing documentation from scratch for a feature, module, or entire project. Uses the Diataxis framework (tutorial / how-to / reference / explanation) to produce complete, structured document

by sanjanbGitHub

manimgl-3b1b

ManimGL, o motor original do 3Blue1Brown (pacote `manimlib`, CLI `manimgl`, venv `.venv-gl`) — quando ele é a resposta e quando é a resposta errada, o fluxo INTERATIVO que só existe aqui (`self.embed(

by frederico-kluserGitHub

embedded-engineer

Use when selecting MCU/MPU architectures, configuring RTOS, designing peripheral interfaces, optimizing power profiles, implementing bootloaders, or setting up HIL testing. Handles ARM Cortex-M/R/A, R

by zeroes-onesGitHub

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack)

by aicodeproGitHub

experiment-discipline

Use for experiment discipline recipes in scripted Coworld policy optimization.

by Metta-AIGitHub

gds-retrospective

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

by DiviZitionGitHub

plan-devex-review

Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION

by linktrendGitHub

1
6151
6152
6153
6154