Arborvsclaude-code-router
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Arbor
penso · Agent harness
OSSMCP
Panel
7.24 spec wins
- Reliability
- 7.0
- Usefulness
- 7.0
- Cost
- 8.7
- Longevity
- 6.0
“It manages your repositories, your worktrees, your terminals and your processes, so the only unmanaged thing left in the room is you.”
claude-code-router
musistudio · Agent harness
OSSMCP
Panel
7.02 spec wins
- Reliability
- 6.3
- Usefulness
- 7.7
- Cost
- 8.3
- Longevity
- 5.8
“Its main job is pointing Claude Code at a model that is not Claude, and it is named after both of them.”
Spec by spec
| Spec | Arbor | claude-code-router |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux, windows, web | macos, linux, windows, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | Yes | No |
| Capabilities | ||
| Runs terminal commands | Yes | NoCCR is a routing proxy; the agent CLI behind it does the executing. |
| Multi-file edits | Yes | No |
| Git operations | Yes | No |
| Browser control | No | No |
| Sandboxed execution | No | YesA documented docker compose deployment runs the router itself in a container; it does not sandbox the agents that call it. |
| Multi-agent orchestration | Yes | YesCCR fronts many agent CLIs at once (Claude Code, Codex, Grok CLI, Kimi CLI, Kilo Code, OpenCode, ZCode) but does not itself orchestrate agents against a task. |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Claude Code, Codex, OpenCode | OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek, SiliconFlow, Moonshot Kimi, Mistral, Z.AI, Bailian |
| Bring your own model | Yes | Yes |
| Local models | YesOllama appears among the providers Arbor can be pointed at. | YesAny OpenAI-compatible endpoint can be added as a custom provider with its own base URL, which covers a locally hosted server; no named Ollama or LM Studio preset is documented. |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 831 | 37,511 |
Which one would each critic pick
| Critic | Arbor | claude-code-router | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.3 | Arbor — Pick it if you work locally and responsiveness matters to you; pick AgentsMesh if the work has to live somewhere your team can reach. |
| El Crítico | 6.8 | 6.3 | Arbor — The desktop app, the web interface and the command line all read one daemon, and nothing documents what an in-flight session does when it dies. |
| El Profesor | 7.5 | 7.0 | Arbor — The unit of work is an issue and the working tree is created for it, so the boundary of the task and the boundary of the checkout are the same boundary. |
| La Inversora | 6.8 | 6.5 | Arbor — 809 stars, a personal namespace and a documentation site on GitHub Pages: nothing to fund, nothing to fail, and nobody to answer the phone. |
| La Jefa | 6.3 | 6.5 | claude-code-router — Free for sixty, and the credential pool with key rotation is the first thing on this board that looks like something a platform team would actually want. |
| El Hacker | 8.3 | 8.8 | claude-code-router — MIT, and any OpenAI-compatible endpoint becomes a provider by writing its base URL into the config, which includes the server on my own machine. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.