9Router vs planning-with-files
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.
Open source · MIT
A local router that lets AI coding tools use multiple model providers, with fallback when limits hit.
Open source · MIT
A file-based planning skill that keeps AI coding agents on track across resets and crashes.
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 planning-with-files if you need…
- Developers running long multi-step tasks in Claude Code or Codex CLI
- People who lose agent progress when the context window fills or is cleared
- Teams wanting a plan that lives in the project as plain markdown files
- Users of agents that support the Agent Skills standard
Side-by-side
| 9Router | planning-with-files | |
|---|---|---|
| Type | Dev tool | Dev tool |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 31.8k | 27.8k |
| Setup difficulty | Intermediate | Beginner |
| How you get it | Install with a package manager | Install with a package manager |
| Main language | JavaScript | Shell |
| Last code update | 9 days ago | 6 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.
planning-with-files
This is a skill for AI coding agents that stores a task plan, research notes, and progress log as markdown files in your project. Lifecycle hooks re-inject that planning context so the agent can pick up where it left off after /clear, context compaction, or a crash. The README says it works across 60+ agents via the Agent Skills standard, with native plugins for several hosts including Claude Code and Codex CLI.
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
planning-with-files
- Developers running long multi-step tasks in Claude Code or Codex CLI
- People who lose agent progress when the context window fills or is cleared
- Teams wanting a plan that lives in the project as plain markdown files
- Users of agents that support the Agent Skills standard
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
planning-with-files
- Plain markdown files on disk that you can read, edit, and version-control or gitignore
- Works through the Agent Skills standard across many agents, with native plugins for several hosts
- MIT licensed with a published benchmark and install options via npm, the Claude Code marketplace, or npx
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
planning-with-files
- Short one-off questions where a plan file adds overhead
- People who want a hosted service rather than local files in their repo
- Users of hosts not listed in the README, since native support depends on the host and results may vary
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
planning-with-files
- Benchmark figures are from the project's own measurements and are reported with stated limits; independent verification is not shown in the README
- Commands and tools vary by host, so the experience differs between integrations
- Session catchup modes can read local agent session records, which the README says requires an explicit opt-in
Getting started
9Router
Install globally with npm
npm install -g 9routerStart the router and dashboard
9routerplanning-with-files
Install the skill globally via npx skills
npx skills add OthmanAdi/planning-with-files --skill planning-with-files -gFrequently asked questions
What is the difference between 9Router and planning-with-files?
9Router: A local router that lets AI coding tools use multiple model providers, with fallback when limits hit. planning-with-files: A file-based planning skill that keeps AI coding agents on track across resets and crashes. 9Router suits developers who use ai coding tools and want to reduce spending, while planning-with-files suits developers running long multi-step tasks in claude code or codex cli.
Are 9Router and planning-with-files free?
9Router: Free and open source. planning-with-files: Free and open source.
Which is easier to set up, 9Router or planning-with-files?
planning-with-files is easier to get started with (rated beginner); 9Router is rated intermediate and usually needs more setup.
Is 9Router or planning-with-files more popular?
9Router has more GitHub stars (31.8k) than planning-with-files (27.8k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to 9Router and planning-with-files?
Other options people compare them with include Ollama, wshobson/agents, 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.