claude-code-routervsContrabass
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
claude-code-router
musistudio · Agent harness
OSSMCP
Panel
7.04 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.”
Contrabass
junhoyeo · Agent harness
OSSMCP
Panel
7.15 spec wins
- Reliability
- 6.8
- Usefulness
- 7.3
- Cost
- 8.2
- Longevity
- 6.0
“Every issue gets a worktree under workspaces/ named after the ticket, so your filesystem is now a faithful copy of your backlog.”
Spec by spec
| Spec | claude-code-router | Contrabass |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux, windows, web | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | No | Yes |
| Capabilities | ||
| Runs terminal commands | NoCCR is a routing proxy; the agent CLI behind it does the executing. | Yes |
| Multi-file edits | No | YesFiles are changed by the agent runner Contrabass launches in each issue's worktree. |
| Git operations | No | Yes |
| Browser control | No | No |
| Sandboxed execution | YesA documented docker compose deployment runs the router itself in a container; it does not sandbox the agents that call it. | No |
| Multi-agent orchestration | 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. | Yes |
| Headless / CI mode | No | YesA --no-tui flag runs the orchestrator headless with events logged to stdout. |
| Models | ||
| Backbone | OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek, SiliconFlow, Moonshot Kimi, Mistral, Z.AI, Bailian | Codex app-server, OpenCode, oh-my-opencode, OMX, OMC |
| Bring your own model | Yes | Yes |
| Local models | 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. | No |
| 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 | Apache-2.0 |
| GitHub stars | 37,511 | 223 |
Which one would each critic pick
| Critic | claude-code-router | Contrabass | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 7.5 | Contrabass — Pick it when your backlog already lives in a tracker and you want it drained; pick a session manager when you would rather choose each task yourself. |
| El Crítico | 6.3 | 6.8 | Contrabass — Stall detection and orphan recovery supervise five external agent runners, so liveness is inferred from processes this project does not control. |
| El Profesor | 7.0 | 7.5 | Contrabass — Teams mode separates plan, exec and verify into phases with branch advance verification and deterministic retry backoff, which is a pipeline rather than a loop. |
| La Inversora | 6.5 | 6.5 | no preference |
| La Jefa | 6.5 | 6.3 | 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 | 8.8 | 8.0 | 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.