Albatrossvskimchi
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Albatross
Morgan Linton · Terminal agent
#172OSSMCP
Panel
6.22 spec wins
- Reliability
- 5.8
- Usefulness
- 5.8
- Cost
- 8.2
- Longevity
- 4.8
“Optimised for Apple Silicon, so your local model and your laptop can run out of memory in perfect harmony.”
kimchi
kimchi · Terminal agent
#75OSSMCP
Panel
6.24 spec wins
- Reliability
- 6.2
- Usefulness
- 6.8
- Cost
- 5.8
- Longevity
- 5.8
“It divides work between an orchestrator, a builder and an explorer, which is more organisational structure than some of its users have.”
Spec by spec
| Spec | Albatross | kimchi |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux | macos, linux, windows |
| 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 | No | Yes |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | YesMulti-model mode assigns separate models to orchestrator, builder and explorer roles and delegates tasks between them. |
| Headless / CI mode | No | YesThe repository ships a Terminal-Bench adapter that aggregates usage across session files, which implies unattended runs. |
| Models | ||
| Backbone | Ollama, LM Studio, MLX, llama.cpp, OpenRouter, OpenAI, Anthropic, Grok | kimchi-dev models, Anthropic |
| Bring your own model | Yes | Yes |
| Local models | Yes | No |
| Cost | ||
| Pricing model | byok | usage |
| 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 | 234 | 2,231 |
Which one would each critic pick
| Critic | Albatross | kimchi | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.5 | 6.5 | no preference |
| El Crítico | 5.8 | 6.0 | kimchi — In multi-model mode an orchestrator delegates to role-specific models, so a bad result has three possible authors and nothing documented attributes it. |
| El Profesor | 6.0 | 6.5 | kimchi — A Terminal-Bench adapter ships in the repository, which makes the capability claim checkable by a third party, and no score accompanies it. |
| La Inversora | 5.5 | 6.0 | kimchi — 2,220 stars, a permissive CLI and an API key in the middle: the code is the marketing and the inference is the company. |
| La Jefa | 5.5 | 5.0 | Albatross — It installs through cargo, which means a Rust toolchain on sixty machines before anyone writes a line, and nothing here runs unattended afterwards. |
| El Hacker | 7.8 | 7.0 | Albatross — MIT, and Ollama, LM Studio, MLX and llama.cpp are all named providers, so the same session runs on my own weights or on a hosted key without changing anything else. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.