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.

161.2K SkillsPublish yours

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

Agents6760 Personas6743 Prompts19362 Templates32 Tools33107 Models

161196 results

453

speckit-tasks

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

by hisptzGitHub

Not rated yet

Free

deployment-pipeline-design

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOp

by 0xzahedGitHub

awe-intake

1. **Read config.** Load optional `awe.config.json` plus `.cursor/state/awe-discovered.json` (baseBranch, roles, test command). If neither exists yet, discover from the repo (origin/HEAD, package.json

by muizatherGitHub

data-validation

Validate data quality for ML pipelines using Great Expectations, Pandera, Pydantic, and Deequ. Covers schema validation, data profiling, data quality checks (completeness, uniqueness, consistency, acc

by ehadziabdicGitHub

mdp-contribute

Contribute a finished MDP case, its playbook riding in the folder, upstream to github.com/tong-wang/auto-mdp-solver — optionally re-skinned to hide business context; a case too sensitive even re-skinn

by tong-wangGitHub

update-harnais

Met à jour le socle Harnais déjà installé sur ce projet vers la dernière version publiée sur GitHub — ajoute les nouveaux hooks/skills/agents, fusionne CLAUDE.md/.gitignore/settings.json, sans jamais

by MoyakekoGitHub

co-shim-context

Load at the start of every conversation in this repo, and whenever an error/bug is found in pseudo.txt (or other project pseudocode) before implementing a fix. Provides the full project context, invar

by mchac15GitHub

wiki

Create a comprehensive codebase wiki under .wiki/ with theory, implementation, data flow, and IEEE-cited references.

by ensismoebiusGitHub

seo-image-gen

Generate SEO-focused images such as OG cards, hero images, schema assets, product visuals, and infographics. Use when image generation is part of an SEO workflow or content publishing task.

by Krrish284GitHub

experiment-tracking-swanlab

Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.

bmad-party-mode

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspect

by InnodatGitHub

agent-caption

You are an AI **captioning agent**. This repo adds **accurate, perfectly-timed captions/subtitles to any video or audio, in any language** (English by default), for both **speech and music**, with fir

by ahkambohGitHub

commit

Commit staged or unstaged work in this repo, and keep CHANGELOG.md current as part of doing so. Handles the whole path: survey the diff, add the changelog entry if the change deserves one, draft a Con

by roycohen2013GitHub

bootstrap-github-skills-exercise

Bootstrap a GitHub Skills exercise repository from an approved outline. Use this when the user asks to create exercise files, step Markdown, issue templates, GitHub Actions workflows, validation scrip

by arilivigniGitHub

newm-chain-grpc

Use when calling, inspecting, or troubleshooting any newm-chain gRPC endpoint with grpcurl, including UTXO queries, monitoring streams, transaction building, and transaction submission.

by projectNEWMGitHub

influencer-marketing

Develop and execute influencer marketing campaigns across social platforms. Use for: identifying and vetting influencers, negotiating partnerships, managing campaigns, measuring ROI, building long-ter

by makaronzGitHub

humanize

Read-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the com

lumos-import-figma

Build a page or fill in Lumos for Astro variables from a Figma file, especially a messy one missing global variables. Use when the user shares a Figma link or design and asks to implement it, translat

by nikolasgannonGitHub

abase

Query Abase NoSQL data via ByteCloud gateway across multiple regions. Use whenever the user wants to query Abase data, list Abase tables, search Abase namespaces, check key values, or mentions Abase/N

by yuezhen-huangGitHub

qa-testing-automation

Design and implement automated testing strategies using modern frameworks like Playwright, Selenium, and Cypress. Use for: building test automation infrastructure, selecting appropriate testing framew

by makaronzGitHub

fsd-coding

Drive coding work through one FSD flow with a host-selected Codex, Cursor, or Claude harness on a local machine or Grok box where that harness is already signed in. Use whenever you would otherwise ed

by fixpoint-labsGitHub

redteam-mindset

Red team discipline, anti-patterns, engagement cadence, session tracking template, and self-throttling guidance for bug bounty hunters and pentesters. Covers scope hygiene, evidence preservation, burn

by Twinson333GitHub

supabase-conventions

Project-specific Supabase conventions for petticoat-monorepo. Use when writing or reviewing edge functions, SQL schemas, migrations, RLS policies, or Supabase client usage in @apps/supabase, @apps/web

by mikeislearningGitHub

workmux

Reference for the workmux CLI that manages git worktrees and tmux windows as isolated development environments. Use when the user mentions workmux, worktrees, or parallel agent workflows.

1
181
182
183
184
185
6717