Crushvsfast-agent
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.”
fast-agent
evalstate · Terminal agent
#117OSSMCP
Panel
6.52 spec wins
- Reliability
- 5.8
- Usefulness
- 6.3
- Cost
- 8.0
- Longevity
- 5.8
“It is named fast-agent and published as fast-agent-mcp, which tells you which half of the name did the work.”
Spec by spec
| Spec | Crush | fast-agent |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | Yes |
| 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. | No |
| 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 | Anthropic, OpenAI, Hugging Face inference providers, llama.cpp |
| 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. | YesA generic provider covers any local endpoint, and the CLI can generate the correct configuration for llama.cpp. |
| 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 | 3,929 |
Which one would each critic pick
| Critic | Crush | fast-agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 7.0 | 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 | 6.3 | no preference |
| El Profesor | 6.5 | 6.5 | no preference |
| La Inversora | 5.8 | 5.0 | Crush — Charm put its coding agent under a source-available license and attached a $20 Hyper plan, which says they intend to sell it, and the terminal aesthetic is the distribution. |
| La Jefa | 5.8 | 5.8 | no preference |
| El Hacker | 7.5 | 8.5 | fast-agent — Apache-2.0, installed with one tool command, a generic provider for any local endpoint, and it will generate the configuration for a local inference runtime itself. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.