HermvsStakpak
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Herm
aduermael · Terminal agent
#102OSS
Panel
7.20 spec wins
- Reliability
- 7.2
- Usefulness
- 6.8
- Cost
- 8.5
- Longevity
- 6.2
“It offers an in-process Unix-like sandbox, for the days when Docker feels like too much of a commitment.”
Stakpak
Stakpak · Terminal agent
#133OSSMCP
Panel
7.04 spec wins
- Reliability
- 6.7
- Usefulness
- 7.3
- Cost
- 7.8
- Longevity
- 6.3
“It debugs Kubernetes on its own initiative, which is either the future or the most thankless job ever handed to a machine.”
Spec by spec
| Spec | Herm | Stakpak |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local, sandbox | local, sandbox |
| Platforms | macos, linux | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | Yes | YesSubagents run sandboxed analysis with restricted tool access, and the README recommends 2GB+ RAM for autopilot and sandbox runs. |
| Multi-agent orchestration | YesA session can mix models by role, such as one model as the main agent, a cheaper one for exploration and another for vision. | Yes |
| Headless / CI mode | No | Yes |
| Models | ||
| Backbone | Anthropic, OpenAI, Gemini, Grok, OpenRouter, Ollama, Azure OpenAI, Vertex AI, AWS Bedrock | any OpenAI-compatible endpoint, Ollama, LM Studio |
| Bring your own model | Yes | Yes |
| Local models | Yes | Yes |
| 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 | MIT | Apache-2.0 |
| GitHub stars | 234 | 1,806 |
Which one would each critic pick
| Critic | Herm | Stakpak | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.3 | Herm — Pick it if approval prompts have trained you to click yes without reading; pick a host-based agent if installing Docker is a fight you would rather skip. |
| El Crítico | 6.8 | 6.5 | Herm — It extends its own environment by writing Dockerfiles dynamically, which means the agent authors the definition of the box it is confined to. |
| El Profesor | 7.8 | 7.3 | Herm — Model assignment is per role rather than per session: a main agent, an exploration model and a vision model can each be a different provider inside one run. |
| La Inversora | 6.0 | 6.8 | Stakpak — A company shipping since December 2024 with 1,768 stars, giving the agent away while the operational surface it produces is where a business would sit. |
| La Jefa | 6.8 | 6.5 | Herm — It defaults to running the agent in Docker, which means a container runtime on sixty machines, and a Homebrew tap is the closest thing here to a distribution channel. |
| El Hacker | 8.3 | 8.0 | Herm — MIT, and everything is open including the system prompts, the skills and the tools, with nine providers listed and Ollama among them. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.