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

start-office-hours-prd

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design think

by dhomini-rabeloGitHub

Not rated yet

Free

gstack-plan-design-review

Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live si

by ifalvarezGitHub

design-shotgun

Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. Standalone design exploration you can run anytime. Use when: "explore designs",

by VOID-PlatformGitHub

deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

by wang030327-botGitHub

elite-qa-architect

Master of TDD, E2E (Playwright/Cypress), Integration testing, and Bug hunting.

by krishujeniyaGitHub

prompt-builder

Gunakan skill ini ketika pengguna ingin membuat, menyempurnakan, atau memperbaiki prompt untuk AI agent / autopilot yang akan mengerjakan task di repo manapun. Trigger phrases: "buatkan prompt", "buat

by rickicodeGitHub

model-tier-policy

Split work across model tiers — an Opus 5 orchestrator session coordinates a team of pinned-model agents; Fable 5 does the thinking and planning; Opus 5 (or Sonnet 5) does everything procedural. Use w

by BinaryInfinityDevGitHub

write

Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.

by Rycen7822GitHub

dfx_reviewer

Bundle Framework DFX 代码审查技能，专注于 HiLog API、HiSysEvent 和 HiTrace 组件的审查，包含日志基础规范、常见模式日志打印检查

by eclipse-oniro-mirrorsGitHub

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by henriquemeireles7GitHub

geoffrey-hinton

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

by clodoaldoperito-droidGitHub

incident-postmortem

Write incident postmortems that transform incidents into institutional learning. Document incident timeline with decision points, capture hypotheses explored, record remediation options and rationale,

by constellizeGitHub

catalyst-calendar

One unified catalyst & event lens with three modes. (A) **Day-of brief** — "what's big today/tomorrow" tight 500–1,500 word note covering macro releases (NFP, CPI, PCE, FOMC, ISM, jobless claims, reta

by dadachundanGitHub

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 miko06GitHub

optimize-cortex-agent

This goes through a workflow to guide AI assistants through optimizing Snowflake Cortex Agents for production readiness through systematic evaluation, improvement, and generalization. The process uses

by randoneeringGitHub

geoffrey-hinton

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

by welitonevocGitHub

marketing-awareness-level-messaging

Use when deciding what a page, email, or listing should actually say — ranking which desire a message should channel on urgency, staying power and scope, testing whether the buyer can feel or see the

by seanfillmoreGitHub

new-feature-design

Design and document new features with GitHub issue, low-level design (LLD), expert review, and testing plan. Creates structured documentation in .scratchpad/ with issue spec, technical design with dia

by NineLivesDemoGitHub

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each f

by geoffreywooGitHub

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

by majiayu000GitHub

bmad-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 delorenjGitHub

research-paper-writing

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated e

by DeepleaperGitHub

yann-lecun

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.

by thai06052003GitHub

gstack-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

by vib795GitHub

1
6148
6149
6150
6151
6152
6154