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-2.0v1.5.0enterprise 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
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.

156.4K SkillsPublish yours

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

Agents6650 Personas6717 Prompts18886 Templates31 Tools32184 Models

156395 results

449

wiki-enrich

Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完',

by Melon1234123GitHub

Not rated yet

Free

bingo-design

Design UI on the Bingo canvas with senior product-design judgment. Derive the project's visual language, name design nouns before JSX, resolve nouns to real components, build visibly in meaningful chu

by CarlosfengvGitHub

to-prd

화면·메뉴·권한·로그인·UI 요소를 먼저 정의하고 그 계약에서 FR과 데이터를 도출해, bkit(PDCA)의 /pdca plan이 바로 소비할 PRD를 생성·갱신한다. 기획 산출물·브리프·기존 PRD를 docs/PRD.md 정본과 feature별 docs/00-pm/{feature}.prd.md로 변환하고 착수 게이트로 검증한다. bkit용 PRD 작성·업

by donchang07GitHub

github-pr-workflow

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

by ArdeleanLucasGitHub

dev-guide-contributing

Nested lingtai-dev-guide reference for contribution workflow: issue/worktree/PR discipline, worktree inventory and exact-object approval gates, daemon decomposition, portfolio sweeps, repo-specific bu

by Lingtai-AIGitHub

sdd-document-phase

Runs one SDD document phase (requirements, design, or tasks) of one spec to agent-side approval. Drafts v1, runs adversarial review and revision rounds with pinned worker agents, rules on standoffs, a

by madmatt112GitHub

browser-rendering-pipeline

Use when working on or debugging how a page gets rendered: the HTML parser that must never fail and the DOM, the CSS cascade, selector matching and why it's backwards, style invalidation as the hard p

by the-vibey-projectGitHub

lean

Use for deliberate Lean 4 work: proof repair, theorem development, verified programs, model/specification design, external-code models, state-machine or trace invariants, termination proofs, Std/mathl

by tkerseyGitHub

HYRVE-AI

You are reading the HYRVE AI integration guide. If you are an AI agent, follow these instructions to register yourself on the HYRVE AI marketplace, find jobs, deliver work, and get paid.

by ertugrulakbenGitHub

ari-hemingway--structure-design-doc

Write or update design docs: proposals that present a problem, a proposed change, sequencing constraints, tradeoffs, and out-of-scope work. Three modes: propose (from scratch), distill (from session/S

by AriSweedlerGitHub

test-driven-development

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug repor

by Juan-LagomarsinoGitHub

gtfs-viz

Import GTFS transit feeds, query station/stop/pathway/route/trip/calendar/shape data, edit connections, nodes, routes, trips, and stop times, compare trip service patterns and schedules, export change

by gabrielAHNGitHub

faces-migrate

Migrate a Jakarta Faces project from one version to another (e.g. JSF 2.3 to Faces 4.1)

by omnifacesGitHub

mergify-stack

Use Mergify stacks for git push, commit, branch, and PR creation. ALWAYS use this skill when pushing code, creating commits, creating branches, or creating PRs. Triggers on push, commit, branch, PR, p

by MergifyioGitHub

hypit

Make, adapt, and revise videos with Hypit from references or briefs, including SVML/SVS/SVRun authoring, project components, and Runtime or credential setup.

by hypit-aiskills.sh

0xcarnemuerta-security-hub-portfolio

Browser-based security portfolio and technical blog covering AI security, data protection, ML threats, and secure engineering practices

by reason-machinesskills.sh

acidrain-security-script-hub

Web-oriented XSS analysis resources, JavaScript utilities, and PHP examples for authorized security testing and hands-on learning

by reason-machinesskills.sh

acidrain-security-testing-toolkit

Use AcidRain's XSS analysis resources, JavaScript utilities, and PHP injection testing samples for authorized web security research and learning

by reason-machinesskills.sh

acidrain-security-testing

Use AcidRain's XSS analysis resources, JavaScript utilities, and PHP injection testing samples for authorized security research and hands-on learning

by reason-machinesskills.sh

agent-security-scanner-mcp

Security scanner MCP server for AI coding agents with vulnerability detection, package hallucination checks, prompt injection firewall, AST analysis, and auto-fix capabilities

by reason-machinesskills.sh

agentic-security-scanner

AI-powered security scanner for agentic workflows with plain-English findings, dollar-cost estimates, and auto-fix capabilities

by reason-machinesskills.sh

ai-runtime-security-sandbox

Demonstrate and test RAG chatbot security vulnerabilities (prompt injection, tool abuse, data leakage) with live attack scenarios and defensive controls

by reason-machinesskills.sh

ai-security-knowledge-base

Comprehensive AI security knowledge base covering ML algorithms, threat modeling, offensive AI tactics, and defensive strategies including OWASP LLM Top 10 and adversarial ML

by reason-machinesskills.sh

ai-security-trainer-2026

Browser-based cybersecurity education platform with guided lessons, quizzes, gamified progression, and adaptive learning scenarios for information security practice.

by reason-machinesskills.sh

1
128
129
130
131
132
6517