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-2.0v1.3.0enterprise 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
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.

150.6K SkillsPublish yours

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

Agents6470 Personas6709 Prompts18556 Templates31 Tools31517 Models

150630 results

446

elixir-planning

Elixir architectural planning — the decisions made BEFORE writing code. Covers project layout, domain boundaries (contexts, aggregates), data ownership, multi-tenancy, process architecture and supervi

by BadBetaGitHub

Not rated yet

Free

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close appro

by MissTullyGitHub

postgresql

PostgreSQL database documentation - SQL queries, database design, administration, performance tuning, and advanced features. Use when working with PostgreSQL databases, writing SQL, or managing databa

by Aniket-a14GitHub

cso

Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10

by BiznomadGitHub

step

One iteration of the PR review→fix loop. Invoked by `/loop` (Claude Code's dynamic-mode loop driver). Returns by either:

by MarcinSufaGitHub

agent-observability-session-classify

Classify whether user intent was satisfied in a Datadog Agent Observability trace or session. Three modes: (1) session_id — classify a single CMD+I assistant session with RUM; (2) trace_id — classify

by gregrickabyGitHub

pr-review

Perform an evidence-based Pull Request code review using repository context, Bitbucket (via bitbucket-standalone-mcp), codebase-memory-mcp, and the review standards defined in the skill references.

by jabdon00GitHub

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

by smarmen86GitHub

taste-skill

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design system

by hwj123hwjGitHub

pr-grind

Post-PR feedback loop — reads CI failures and reviewer comments, fixes issues, pushes, and repeats until the PR is clean. Use after creating a PR or on any existing PR that needs attention.

by chris-yyauGitHub

design-consultation

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pag

by ManzuetiGitHub

next-fullstack-app

Opinionated blueprint for self-hosted, single-process, full-stack Next.js applications: an internal tool or control panel that owns its **own** auth, its **own** database, and a real-time dashboard UI

by kalevskiGitHub

rx9070-vllm-rocm-turboquant

Build latest vLLM from source on this user's WSL + ROCm + RX 9070 setup, then test local GPTQ Qwen/Qwopus models with baseline KV cache and TurboQuant KV cache presets.

by shawnq-msftGitHub

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge an

by kjuhwaGitHub

plan-devex-review

Developer Experience plan review. Evaluates plans through Addy Osmani's DX framework: zero friction, learn by doing, fight uncertainty. Rates 8 DX dimensions 0-10 with a DX Scorecard. Use when asked t

by louisfghbvcGitHub

skillify

Codify the most recent successful /scrape flow into a permanent browser-skill on disk. (gstack)

by WindWang2GitHub

cdrom-file-disc-images

CDROM disc image formats: CCD/IMG/SUB (CloneCD), CDI (DiscJuggler), CUE/BIN (Cdrwin), MDS/MDF (Alcohol), NRG (Nero), CDZ, ECM, PBP (Sony PSP), CHD (MAME). Use when converting, reading, or writing disc

by sadnescityGitHub

feature-implement

You are running the `feature-implement` skill. The user may have arrived here by typing `/feature-implement` (with an optional version in `$ARGUMENTS`), by chaining in from `/feature-plan`, or because

by cagriyGitHub

vlogall

Complete self-contained pipeline for producing time-travel history vlog episodes as scene-by-scene JSON for Higgsfield Seedance (8-12 scenes x 10s, 9:16, vertical selfie vlog), including the source-vi

by noellesugar99GitHub

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design system

by ElhamDevelopmentStudioGitHub

do-in-steps

Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results

by gabrielmoreiraGitHub

gh-merge

Merge Validated pull requests to main — the pipeline's single, tightly-guarded merger. Plans a collision-aware merge order across all open Validated PRs, re-confirms the review gate and CI at merge ti

by JAndrew13GitHub

gds-retrospective

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

by developAgentGitHub

mad-implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md

by tmalcolm-0607GitHub

1
6259
6260
6261
6262
6263
6277