Crab CodevsGemini CLI
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Crab Code
lingcoder · Terminal agent
#236OSS
Panel
5.31 spec wins
- Reliability
- 4.8
- Usefulness
- 5.2
- Cost
- 7.0
- Longevity
- 4.2
“Twenty-five crates of hand-written Rust, so the prompt asking whether it may delete something is now memory-safe.”
Gemini CLI
Google · Terminal agent
#66OSSMCP
Panel
5.26 spec wins
- Reliability
- 6.0
- Usefulness
- 5.7
- Cost
- 4.5
- Longevity
- 4.7
“A 1M token context window and, since June 18, zero tokens for the free users who filled it.”
Spec by spec
| Spec | Crab Code | Gemini CLI |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local, sandbox |
| Platforms | macos, linux | macos, linux, windows |
| Context window | not documented | 1M tokens |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | No | YesA first-party `browser_agent` subagent, disabled by default, drives Chrome 144+ through chrome-devtools-mcp with settings for sensitive-action confirmation and file-upload blocking. |
| Sandboxed execution | No | Yes |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | Anthropic, OpenAI, DeepSeek, Bedrock, Vertex AI | Gemini 3, Gemini 2.5 Pro, Gemini 2.5 Flash |
| Bring your own model | Yes | YesVertex AI authentication (with GOOGLE_CLOUD_PROJECT/GOOGLE_CLOUD_LOCATION or a service account) selects your own cloud deployment, and GOOGLE_GEMINI_BASE_URL / GOOGLE_VERTEX_BASE_URL redirect model requests to a proxy or gateway you run. Models themselves are still Gemini-family. |
| Local models | No | YesGOOGLE_GEMINI_BASE_URL and GOOGLE_VERTEX_BASE_URL explicitly permit plain HTTP to localhost, 127.0.0.1 or [::1], so a self-hosted Gemini-compatible endpoint works; the experimental Gemma Model Router also runs a local LiteRT-LM server on http://localhost:9379. No Ollama or LM Studio integration is documented. |
| Cost | ||
| Pricing model | byok | mixed |
| Starts at | $0/mo | n/a |
| Free tier | Yes | No |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | Apache-2.0 |
| GitHub stars | 76 | 107,222 |
Which one would each critic pick
| Critic | Crab Code | Gemini CLI | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 5.8 | 5.0 | Crab Code — Pick it if you want the agent you already know as a single Rust binary with no vendor attached; pick the original if you want the release notes to be someone else's job. |
| El Crítico | 5.0 | 4.8 | Crab Code — Permissions live in a TOML file and nothing else stands between the agent and the machine, while the same agent is allowed to commit and branch. |
| El Profesor | 5.8 | 6.0 | Gemini CLI — A sandboxed, open scaffold with a 1M context window and a vendor that has moved its consumer path to a successor; the architecture is sound, the product is in transition. |
| La Inversora | 4.0 | 4.8 | Gemini CLI — The free tier was the growth engine, and the growth engine was switched off on June 18, 2026; what remains is a paid-only path and a successor product. |
| La Jefa | 4.8 | 4.8 | no preference |
| El Hacker | 6.5 | 6.0 | Crab Code — MIT, my key, five providers to route between, and a build from a clone, which is the install path I trust most because it is the one I can read. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.