Crushvswhip
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Crush
Charm · Terminal agent
#25OSSMCP
Panel
6.53 spec wins
- Reliability
- 6.0
- Usefulness
- 6.5
- Cost
- 7.3
- Longevity
- 6.2
“Has a --yolo flag, auto-discovers your local llama.cpp, and a license with MIT in the name that is not MIT yet.”
whip
Context Labs · Terminal agent
#109OSSMCP
Panel
6.52 spec wins
- Reliability
- 5.7
- Usefulness
- 6.5
- Cost
- 8.3
- Longevity
- 5.3
“Its roadmap cites which project each idea was taken from, which is more attribution than most research papers manage.”
Spec by spec
| Spec | Crush | whip |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | No |
| Browser control | NoThe built-in tools stop at web_fetch, web_search and download; there is no browser, CDP or Playwright tool. | YesThe documentation index lists browser and computer-use alongside MCP; the README itself does not describe the feature. |
| Sandboxed execution | NoShell and edit calls are guarded by permission prompts (or skipped with --yolo), with no container or OS-level isolation. | No |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes`crush run` executes a single non-interactive prompt, reads stdin and supports --quiet for scripts. | No |
| Models | ||
| Backbone | Claude, GPT, Gemini, any OpenAI-compatible or Anthropic-compatible provider | inference.net, OpenRouter, any OpenAI-compatible endpoint |
| Bring your own model | Yes | Yes |
| Local models | YesOllama, LM Studio, llama.cpp and MLX providers are auto-discovered, and any OpenAI- or Anthropic-compatible base_url can be added. | YesAny OpenAI-compatible endpoint works as a provider, which covers a locally served model. |
| 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 | FSL-1.1-MIT | Apache-2.0 |
| GitHub stars | 28,444 | 1,064 |
Which one would each critic pick
| Critic | Crush | whip | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 6.8 | Crush — Crush is the terminal agent to pick if you want LSP-grade context and a Charm-quality interface with your own keys, and the one to read the license on before you fork it. |
| El Crítico | 6.3 | 6.0 | Crush — A --yolo flag on an agent with no sandbox means a headless run is your shell with nobody watching; the LSP context is the reason to read past it. |
| El Profesor | 6.5 | 7.3 | whip — Per-path file locks and channel-based background subagents put parallelism exactly where two agents do not conflict and serialise them where they do. |
| La Inversora | 5.8 | 6.0 | whip — A harness that ships pointing at one inference provider is a distribution channel for that provider, and the question is what Context Labs gets for it. |
| La Jefa | 5.8 | 5.3 | Crush — Free with our own keys, Bedrock and Vertex built in, a --yolo flag that needs a policy, and a source-available license legal will want to read; approved with conditions. |
| El Hacker | 7.5 | 7.5 | no preference |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.