mini-SWE-agentvsStakpak
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
mini-SWE-agent
SWE-agent (Princeton and Stanford) · Terminal agent
#35OSS
Panel
6.92 spec wins
- Reliability
- 6.3
- Usefulness
- 5.5
- Cost
- 8.8
- Longevity
- 7.0
“One hundred lines of Python, which is fewer than most competitors spend on their pricing page.”
Stakpak
Stakpak · Terminal agent
#133OSSMCP
Panel
7.03 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 | mini-SWE-agent | 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 | Yes | 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 | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | any via litellm | any OpenAI-compatible endpoint, Ollama, LM Studio |
| Bring your own model | Yes | Yes |
| Local models | Yes | Yes |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | n/a | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | Apache-2.0 |
| GitHub stars | 8,145 | 1,806 |
Which one would each critic pick
| Critic | mini-SWE-agent | Stakpak | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 7.3 | Stakpak — Pick it if you want infrastructure work that continues while you sleep and wakes you only when it must; pick a normal terminal agent if you want to watch every step. |
| El Crítico | 6.5 | 6.5 | no preference |
| El Profesor | 8.0 | 7.3 | mini-SWE-agent — The reference harness for the SWE-bench bash-only leaderboard: one bash action per turn via subprocess.run, a linear history, no tool-calling API, and Gemini 3 Pro reported above 74% on Verified. |
| La Inversora | 6.8 | 6.8 | no preference |
| La Jefa | 5.0 | 6.5 | Stakpak — It runs headless, so it becomes a pipeline step I can gate on, and there is still no directory integration or retention policy to put in front of my security team. |
| El Hacker | 8.5 | 8.0 | mini-SWE-agent — MIT, any model through litellm, OpenRouter or Portkey including my local server, a YAML config, and source short enough to read before breakfast; the missing MCP client is the only gap. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.