mini-SWE-agentvsOpenCode
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
#8OSS
Panel
6.91 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.”
OpenCode
Anomaly (formerly SST) · Terminal agent
#5OSSMCP
Panel
7.03 spec wins
- Reliability
- 6.7
- Usefulness
- 7.3
- Cost
- 7.3
- Longevity
- 6.8
“Two hundred thousand GitHub stars, seventy-five providers, and a vendor that renamed itself before the tool did.”
Spec by spec
| Spec | mini-SWE-agent | OpenCode |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local, sandbox | local |
| Platforms | macos, linux | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | No | NoBuilt-in tools include webfetch and websearch only; nothing drives or reads a browser. |
| Sandboxed execution | Yes | NoTool calls are gated by the permission config, which is an approval policy rather than container or OS-level isolation. |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | any via litellm | Claude, GPT, Gemini, DeepSeek, Kimi, Ollama |
| Bring your own model | Yes | Yes |
| Local models | Yes | Yes |
| Cost | ||
| Pricing model | byok | mixed |
| Starts at | n/a | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 8,410 | 212,773 |
Which one would each critic pick
| Critic | mini-SWE-agent | OpenCode | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 8.0 | OpenCode — OpenCode is what to hand anyone who wants the Claude Code shape with their own keys and a model picker; pick Claude Code if you want one vendor and one bill. |
| El Crítico | 6.5 | 7.0 | OpenCode — Commands run with your permissions and no sandbox, and the Zen gateway offers free models without saying who pays for them. |
| El Profesor | 8.0 | 6.8 | 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 | 6.0 | mini-SWE-agent — No company, a Princeton and Stanford lab with 6,938 stars; the funding is grants and the exit is a paper, which is more stable than half the cap tables on this board. |
| La Jefa | 5.0 | 5.8 | OpenCode — Free and MIT is the easy line; sixty engineers each holding a provider key with no SSO, no audit log and no vendor is the hard one. |
| El Hacker | 8.5 | 8.8 | OpenCode — MIT, Ollama for offline, MCP servers in opencode.json with a published $schema, custom agents, and it has already been forked, which is the point. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.