Skip to content

9Router vs wshobson/agents

Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.

9Router

Open source · MIT

A local router that lets AI coding tools use multiple model providers, with fallback when limits hit.

wshobson/agents

Open source · MIT

A collection of plugins, agents, skills, and commands that run across several AI coding tools.

The short answer

Choose 9Router if you need…

  • Developers who use AI coding tools and want to reduce spending
  • People with several AI subscriptions who want to use up their quota
  • Users who want one local endpoint for multiple AI providers
  • Tinkerers willing to configure providers and model names by hand

Choose wshobson/agents if you need…

  • Developers who already use one of the listed AI coding tools and want ready-made specialist agents
  • Python or JavaScript/TypeScript developers looking for testing, packaging, or project setup guidance
  • Teams wanting a shared set of review and security-scanning workflows across different tools
  • People who want to install only individual skills without the full plugin set

Side-by-side

9Routerwshobson/agents
TypeDev toolDev tool
PriceFree and open sourceFree and open source
LicenceMITMIT
GitHub stars31.8k42.1k
Setup difficultyIntermediateBeginner
How you get itInstall with a package managerInstall with a package manager
Main languageJavaScriptPython
Last code update9 days ago4 days ago

What each one is

9Router

9Router runs on your computer as a local server at localhost:20128. You point tools such as Claude Code, Codex, Cursor or Cline at it instead of a provider, and it forwards requests to one of 40+ AI providers. It can switch to a cheaper or free model when a primary subscription runs out, and its README says it compresses tool output to save tokens.

wshobson/agents

This project is a shared library of prompts-as-plugins for AI coding assistants. It contains 94 plugins with specialist agents, skills (reference guidance an agent loads when relevant), and commands (named workflows) covering areas like Python, JavaScript, code review, testing, infrastructure, and security. One Markdown source is adapted to Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi.

Best for

9Router

  • Developers who use AI coding tools and want to reduce spending
  • People with several AI subscriptions who want to use up their quota
  • Users who want one local endpoint for multiple AI providers
  • Tinkerers willing to configure providers and model names by hand

wshobson/agents

  • Developers who already use one of the listed AI coding tools and want ready-made specialist agents
  • Python or JavaScript/TypeScript developers looking for testing, packaging, or project setup guidance
  • Teams wanting a shared set of review and security-scanning workflows across different tools
  • People who want to install only individual skills without the full plugin set

Strengths

9Router

  • Single local endpoint works with many AI coding tools
  • Automatic fallback between tiers of providers
  • MIT licensed and open source with a large public following

wshobson/agents

  • Covers seven coding tools from one shared source of components
  • Large catalog: 94 plugins, 202 agents, 185 skills, and 105 commands according to the README
  • Offers a skills-only install route that does not require the full plugin set

Not ideal for

9Router

  • Users who need guaranteed uptime or enterprise support, since the README describes no such commitments
  • People who do not want to manage API keys or provider accounts
  • Anyone expecting every listed model to be truly unlimited, since free tiers and credits have limits the README itself mentions

wshobson/agents

  • People who do not use any supported AI coding tool, since the components only run inside those harnesses
  • Anyone expecting the scores from the plugin-eval tool to prove a task will succeed, because the README says the LLM judge and Monte Carlo layers are experimental and not validated against human labels
  • Users wanting a fully stable, versioned release, since the README lists no latest release

Trade-offs

9Router

  • Free tiers and credits are limited and can change, so 'unlimited' is marketing wording
  • Source-based setup and production build require extra steps and system tuning
  • Relies on third-party providers whose terms and availability are outside the project's control

wshobson/agents

  • The README notes that available components depend on the installation route and each harness's limits, so features differ by tool
  • Some features (LLM judge, Monte Carlo evaluation) are experimental and may bill your Anthropic API account if ANTHROPIC_API_KEY is set
  • Pi agents need a separate subagent extension, and the Codex native and generated routes behave differently

Getting started

9Router

Install globally with npm

npm install -g 9router

Start the router and dashboard

9router
Step-by-step guide: how to use 9Router

wshobson/agents

Claude Code: register marketplace (run inside Claude Code)

/plugin marketplace add wshobson/agents

Claude Code: install Python plugin (run inside Claude Code)

/plugin install python-development@claude-code-workflows
Step-by-step guide: how to use wshobson/agents

Frequently asked questions

What is the difference between 9Router and wshobson/agents?

9Router: A local router that lets AI coding tools use multiple model providers, with fallback when limits hit. wshobson/agents: A collection of plugins, agents, skills, and commands that run across several AI coding tools. 9Router suits developers who use ai coding tools and want to reduce spending, while wshobson/agents suits developers who already use one of the listed ai coding tools and want ready-made specialist agents.

Are 9Router and wshobson/agents free?

9Router: Free and open source. wshobson/agents: Free and open source.

Which is easier to set up, 9Router or wshobson/agents?

wshobson/agents is easier to get started with (rated beginner); 9Router is rated intermediate and usually needs more setup.

Is 9Router or wshobson/agents more popular?

wshobson/agents has more GitHub stars (42.1k) than 9Router (31.8k). Popularity isn't the same as fit — check which one matches your use case above.

What are other alternatives to 9Router and wshobson/agents?

Other options people compare them with include Ollama, planning-with-files, ECC, Claude Code Game Studios, codebase-memory-mcp.

Keep comparing

Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.