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
Python SDK
TypeScript SDK
MCP server
Self-hosting

Company

Blog
Changelog
Support
Security
PyPI
npm
Source

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

flow

Personal task and agent-session manager. CLI binary is `flow` (assumed on PATH) and stores metadata in ~/.flow/flow.db (SQLite). Use this skill when the user asks about their work, tasks, or projects

by Facets-cloudGitHub

Not rated yet

Free

tooluniverse-clinical-trial-matching

AI-driven patient-to-trial matching for precision medicine and oncology. Given a patient profile (disease, molecular alterations, stage, prior treatments), discovers and ranks clinical trials from Cli

by BioTender-maxGitHub

shellx-host

ShellX host-session manifest. Use only when the current prompt or runtime metadata positively identifies this session as running inside ShellX, when ShellX host tools are advertised, or when the user

by martinsbrezauckisGitHub

photography-style-development

Identifies a user's visual preferences from described examples, extracts the defining characteristics including color treatment, contrast, subject selection, and composition, and produces a personal p

by FerroxLabsGitHub

android

Android platform development for Pulp — NDK cross-compilation, Oboe audio, Dawn/Skia GPU rendering, JNI bridge, touch interaction, emulator workflows, and end-to-end smoke validation. Covers build, de

by Generous-CorpGitHub

aegis-injection

Audit playbook module for detecting and remediating the full injection family (SQL, NoSQL, OS command, template, code/expression, LDAP, XPath, header/CRLF/log) via static taint tracing and authorized

by AS-FOSSGitHub

scrape

Pull data from a web page. (gstack)

by charlieviettqGitHub

teams-api

Microsoft Teams automation using Graph API, Bot Framework, Adaptive Cards, and webhooks for enterprise messaging and collaboration

by majiayu000GitHub

product

Consolidated Galyarder Framework Product intelligence bundle.

by galyarderlabsGitHub

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

by pinkpixel-devGitHub

david-hume-expert

Embody David Hume - AI persona expert with integrated methodology skills

by sethmblackGitHub

target

Use when: build this feature, get it done end-to-end, or execute a plan from idea to PR.

by bllshttngGitHub

qa

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

by gabrielmoreiraGitHub

push-notify

Implement push notifications end-to-end — from FCM/APNs setup through token management, notification handling in all app states, rich notifications with actions, and deep linking. Covers React Native,

by heaptracetechnologyGitHub

memory-kit

Librarian-solo hygiene-sweep toolkit and cadence: deterministic hygiene/audit tools (cleanup, path-update, dedupe, memory-review, claude-md/agent/skill audits, memory-coherence) plus a stasis/coverage

by ethosengineGitHub

customaize-agent:context-engineering

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

by AntifragileTechGitHub

ios-clean

Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

by raghavbadhwarGitHub

codex

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anythin

by az9713GitHub

deliver

Use to run the DELIVERY phase of the doctrine twin — offer the journalist the forms their beat's format allows, wait for the choice, and materialise only that one. Never builds a form nobody asked for

by buriedsignalsGitHub

setup-deploy

Configure deployment settings for /land-and-deploy.

by codewpurposeGitHub

study-content

Use this skill whenever a user uploads lecture slides, a PDF, notes, or any educational content and wants study materials generated from it. Triggers include: 'make study notes', 'turn this into a pre

by sabarixrGitHub

context-restore

Restore working context saved earlier by /context-save. (gstack)

by codewpurposeGitHub

tool-pydantic

Load when working with pydantic, BaseModel validation, TypeAdapter, ConfigDict, field validators, JSON schema, or V1 migration. Covers full Python API surface, setup, error handling, and lessons.

by auronpepGitHub

video-js

Create agency-quality short animated videos (up to ~2 minutes max — longer runs are much harder to export, so size to the content) programmatically using React, Framer Motion, GSAP, and Three.js. Use

by Ragula-Ajay-kumarGitHub

1
6087
6088
6089
6090
6091
6154