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.

158.8K SkillsPublish yours

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

Agents6706 Personas6739 Prompts19237 Templates31 Tools32720 Models

158792 results

450

prompt-craft

Multi-session prompt craft coach with an onboarding wizard, personalized plan, hands-on exercises on your real prompts, and saved progress. Use only when asked to start or continue this course.

by soreavisGitHub

Not rated yet

Free

visual-recap

Use when the user wants a visual summary of work that was done — "visual recap", "recap this PR/branch/commit visually", "show me what changed in the browser" — for a PR, branch, commit range, or unco

by patrickdappollonioGitHub

openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

by JoeShiGitHub

kaizen

Turn a finished session's transcript into (1) real token usage, (2) the priciest tools/subagents, (3) an honest accuracy read, (4) concrete improvements — then record one lesson so patterns surface ac

agent-context-system

A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at session start, update the

by AndreaGriffiths11GitHub

detection-bootstrap

Bootstrap an object-detection dataset and a small trained detector from images that have NO labels — zero-shot label with Falcon-Perception, validate, convert, then fine-tune a compact Apache-licensed

by davanstrienGitHub

sign-artifact

Add an Artifact Signing (SscaArtifactSigning) step to an existing Harness pipeline to Cosign-sign container or local-stage artifacts with keyless, key-based, or Vault signing. Supports Third-Party reg

by harnessGitHub

testsprite-verify

TestSprite verification loop — after finishing a feature or fix in a TestSprite-tested repo, use the `testsprite` CLI to run the relevant TestSprite tests against the change and inspect any failure ar

by eslameldemerdasGitHub

workflow-knowledge

CLI tool for querying the workflow knowledge base — a retrieval-augmented store of all completed workflow artifacts, searchable by semantics or keyword. This file is the API documentation layer. Load

by leeoveryGitHub

speckit-clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

by Avlis1412GitHub

services-extension-consumption

Consume the salesforcedx-vscode-services extension API. Use when an extension depends on salesforcedx-vscode-services and you are registering commands, calling its services (Workspace, Connection, Pro

by forcedotcomGitHub

kernel-commit-message

Write or review the commit message for a Linux kernel patch headed upstream — subject line, root-cause narrative, quoted code excerpt, concrete consequence, user-visible impact and provenance, imperat

by Radon10043GitHub

slide-writer

把想法、大纲、文档或草稿变成结构清晰、设计精良的企业级 HTML 演示文稿。

by FeeiCNGitHub

lark-smart-meeting-assistant

智能会议助手：自动获取会议纪要、提取待办事项、创建任务、发送会议总结邮件，支持任务状态跟踪和会议提醒。基于飞书 CLI 1.0.7，支持从日历事件提取纪要文档令牌、send_as 邮件发送等新功能。适用于会议后处理自动化、任务管理、团队协作场景。

by mmmnhjghGitHub

prisma-composer-core-concepts

Use when deploying or managing an app that uses Prisma Composer (`@prisma/composer`): wiring its services and Modules, running it locally, testing composed services, or standing up / tearing down an e

by Furqan-7GitHub

work-queue

Use when asked "what should I work on", "what's on my plate", "what's assigned to me", or for a to-do list gathered from every channel. Sweeps Linear, GitHub, mail, chat, meetings and local work-in-pr

by ibraheem4GitHub

pr-impact-review

PR・ブランチ差分を「ユーザー価値とプロダクト品質」の観点で、PdMとしてレビューするスキル。「PRをレビューして」「この変更でユーザーに何が起きる？」「ユーザーへの価値はどう変わる？」「イシューの意図に沿ってる？」「これマージして大丈夫？」「PdM目線で見て」「合否を判断して」といったリクエストで使う。codex review や code-review が行レベルのコード品質を見るのに対し、本

by tktcorporationGitHub

import-model

Use when importing a new model architecture into MAX from a Hugging Face model ID. Triggers on: "import a model into MAX", "add model to MAX", "bring up <HF model> in MAX". Workflow: inspect Hugging F

by shakfuGitHub

nav-loop

Run tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode".

by qf-studioGitHub

empirical-project-playbook

Use when starting, building, or auditing an empirical/data-driven project with AI agents - anything that measures something (edge, conversion, performance, a business hypothesis) and decides with data

by manusabbath-archGitHub

speckit-clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

by alumnx-ai-labsGitHub

shmem-ops-performance-optim

基于 SHMEM 的算子性能优化迭代，固定 5 轮机制优化，每轮输出 Δ% 对比。触发：用户需要定位 SHMEM 算子瓶颈、调优通信机制或执行自动性能优化时使用。关键词：基于SHMEM性能优化、调优、optimization、机制优化、性能调优。

by WangWindowGitHub

duet-work-full

Беседа и рабочая папка.

by alatyshauGitHub

godot-2d-physics

Expert patterns for Godot 2D physics including collision layers/masks, Area2D triggers, raycasting, and PhysicsDirectSpaceState2D queries. Use when implementing collision detection, trigger zones, lin

by bgrenatGitHub

1
176
177
178
179
180
6617