Forgevsmini-SWE-agent
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Forge
Tailcall, Inc. · Terminal agent
#33OSSMCP
Panel
6.92 spec wins
- Reliability
- 6.5
- Usefulness
- 6.8
- Cost
- 8.0
- Longevity
- 6.2
“You summon it by typing a colon, which is the most vim thing ever to happen to a coding agent.”
mini-SWE-agent
SWE-agent (Princeton and Stanford) · Terminal agent
#35OSS
Panel
6.94 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.”
Spec by spec
| Spec | Forge | mini-SWE-agent |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local, sandbox |
| Platforms | macos, linux, windows | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | No | No |
| Sandboxed execution | No | Yes |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | No | Yes |
| Models | ||
| Backbone | Claude, GPT, Gemini, Grok, DeepSeek | any via litellm |
| Bring your own model | Yes | Yes |
| Local models | No | Yes |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | n/a | n/a |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | Apache-2.0 | MIT |
| GitHub stars | 7,638 | 8,145 |
Which one would each critic pick
| Critic | Forge | mini-SWE-agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 6.8 | Forge — Pick Forge if you want an agent inside the shell you already configured; pick Aider if you would rather keep the agent in its own process and your shell untouched. |
| El Crítico | 6.8 | 6.5 | Forge — Setup inserts it into the interactive path of your shell, so a coding agent with command execution now sits between you and every line you type. |
| El Profesor | 7.3 | 8.0 | 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 | 6.3 | 6.8 | 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 | 6.0 | 5.0 | Forge — Free to install with the model bill as the only cost, but it assumes one shell across sixty machines and cannot run unattended, so it stays a personal tool. |
| El Hacker | 8.0 | 8.5 | 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.