fast-agentvsminion
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
fast-agent
evalstate · Terminal agent
#117OSSMCP
Panel
6.54 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.”
minion
Sentdex · Terminal agent
#50OSS
Panel
6.50 spec wins
- Reliability
- 5.8
- Usefulness
- 6.5
- Cost
- 8.7
- Longevity
- 4.8
“It renders the model's separate reasoning stream as a thinking block, so you can watch it talk itself into the bug.”
Spec by spec
| Spec | fast-agent | minion |
|---|---|---|
| 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 | No |
| MCP server | Yes | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Anthropic, OpenAI, Hugging Face inference providers, llama.cpp | any OpenAI-compatible endpoint, llama.cpp, vLLM, SGLang, OpenAI, Z.ai |
| Bring your own model | Yes | Yes |
| Local models | YesA generic provider covers any local endpoint, and the CLI can generate the correct configuration for llama.cpp. | YesMINION_BASE_URL points at any OpenAI-compatible server; local llama.cpp, vLLM and SGLang are the primary target. |
| 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 | Apache-2.0 | MIT |
| GitHub stars | 3,929 | 337 |
Which one would each critic pick
| Critic | fast-agent | minion | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 6.8 | fast-agent — Pick it if tool servers are central to how you work; pick Goose when you want the same protocol focus with a friendlier path for people who do not read specifications. |
| El Crítico | 6.3 | 5.8 | fast-agent — The claim of first complete end-to-end tested protocol support arrives without a test matrix, and the features it names include the authentication path that fails quietly. |
| El Profesor | 6.5 | 7.3 | minion — The 625-token figure is measured precisely: a bare greeting, a system prompt, five tool schemas and the chat-template framing, which is a definition most claims of this kind lack. |
| La Inversora | 5.0 | 5.8 | minion — 327 stars, one author, and a design with nothing in it to sell: no service, no hosted tier, no upgrade, and by construction no way for this to become a company. |
| La Jefa | 5.8 | 5.3 | fast-agent — Free at any headcount, and the useful detail is that a configuration pack points it at a subscription some of our engineers already hold, so the spend is not new. |
| El Hacker | 8.5 | 8.0 | 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.