Skip to content

Pricing
Blog

Sign in Get started

Site footer

Spend less on every AI request. Safe before it leaves, explained after.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0v1.8.0enterprise 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
Security
Observability
Pricing

Solutions

Who it is for
Budget owners
Platform teams
Security teams
Developers
Industries
Enterprise
Bring your bill
ROI calculator
Compare

Developers

SDKs and API
Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Agent skills
Self-hosting
Downloads

Company

Blog
Newsletter
Changelog
Support
Contact sales
Status
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.

169.8K SkillsPublish yours

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

Agents6.8K Personas6.8K Prompts19.5K Templates33 Tools34.4K Models

169842 results

459

apple-ultra-skills

Ultra-tier AI agent skill combining 50+ top skills.sh patterns into one. Context-aware: auto-activates frontend, design, architecture, testing, security, performance, accessibility, agent, and devops

by Cookie-Cat21GitHub

Not rated yet

Free

rye-agent-ops

Operate Rye data safely for LLM agents. Use when implementing or executing agent read/write flows, connecting domain tables, selecting assertion keys, enforcing provenance, and applying agent-safe SQL

programming-philosophy

Programming philosophy - write code where you can see what the machine is doing. Favors simple, procedural, group-oriented code; imperative code over deferred data-driven engines; encapsulation bounda

by TimPaplerGitHub

engine-implementer

End-to-end phase.rs implementation pipeline: plan, review-plan, implement, review-impl, commit — each step run in a fresh spawned agent, with automatic phase decomposition for oversized workloads.

by phase-rsGitHub

mx-amazon-dsp

Read an Amazon DSP (Demand-Side Platform) advertiser straight from Amazon through MixShift's service. Two surfaces, addressed differently. REPORTING is async: submit a report, poll it, download it. Re

by miXshiftGitHub

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; do

by meldkinGitHub

sam-gov

Query and analyze US federal contracting, spending, regulation, vetting, and market data. 152 tools across 54 data sources, keyless-first (147 tools need no key; only 5 tools across Census CBP, FRED,

by cliwantGitHub

agent-gantry

Use this skill when the user is writing or debugging code that uses the `agent-gantry` Python library (semantic tool routing for LLM agents). Triggers on `import agent_gantry`, mentions of `AgentGantr

by CodeHalwellGitHub

pipeline-orchestrator

Universal SDLC pipeline orchestrator with stack provider auto-discovery. Reads manifest.yaml profiles from installed plugins, picks the highest-priority match, executes a workflow-defined pipeline (de

by NuclominusGitHub

remediation-discipline

Class-over-instance remediation discipline for Caro's Ledge platform engineering. When a problem surfaces, determines whether the failure is class or instance, then chooses remediation accordingly. Cl

by Dwarves77GitHub

ui-ux-pro-max

UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility,

by CikeLemonGitHub

pixellab-pip

Use for PixelLab/Pip setup, auth, MCP/API routing, asset generation, editing, animation, talking portraits, lip sync, skeleton/template/preset animations, multi-shot/looping cinematics, Game Builder,

chinese-indie-dev

处理 1c7/chinese-independent-developer 仓库的项目提交。检查 issue #160 新评论、新开的 Issue、新开的 PR，将有效项目添加到对应 README，关闭垃圾内容。当用户要求“收录项目”“处理提交”“处理 issue”“跑一下列表”或运行中国独立开发者列表维护流程时使用。

open-gstack-browser

Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed

by tolowa-studioGitHub

audit-docs

Audit documentation indexes, frontmatter, and links. Apply safe additive repairs; request confirmation for destructive changes.

by bionic-codingGitHub

ba-review-plan

Score a plan's sections with the built-in reviewers and, on approval, edit that plan file in place. Use when explicitly asked to review, critique, or strengthen a specific plan before implementing it.

by azevedoGitHub

ui-ux-pro-max

UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility,

by bnloadingGitHub

custom-plugin-flutter

State management is the **cornerstone of modern Flutter development**. It's the difference between a chaotic, unmaintainable codebase and an elegant, scalable architecture that grows with your busines

by pluginagentmarketplaceGitHub

qa

Systematically QA test a web application and fix bugs found. (gstack)

by jeel1566GitHub

account-reconciliation

Reconcile accounts, ledgers, bank statements, subledgers, variances, and supporting schedules.

by okou-aiskills.sh

agentphone

Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related

by okou-aiskills.sh

analysis-qa

Quality-check data analysis for joins, metrics, denominators, date ranges, leakage, and statistical pitfalls.

by okou-aiskills.sh

audit-readiness

Prepare audit workpapers, control tests, samples, evidence, deficiencies, and remediation tracking.

by okou-aiskills.sh

brand-guidelines

Define or enforce brand voice, messaging, terminology, tone, and style standards.

by okou-aiskills.sh

1
244
245
246
247
248
7077