Cowork ForgevsSWE-agent
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Cowork Forge
sopaco · Autonomous SWE
#258OSS
Panel
4.71 spec wins
- Reliability
- 4.0
- Usefulness
- 4.3
- Cost
- 6.5
- Longevity
- 4.0
“The engineer agent writes the code and then writes the delivery report, which is the most realistic simulation of a development team yet.”
SWE-agent
Princeton University and Stanford University · Autonomous SWE
#144OSS
Panel
5.14 spec wins
- Reliability
- 5.5
- Usefulness
- 4.8
- Cost
- 6.5
- Longevity
- 3.7
“Maintenance-only and superseded by a version with mini in the name, which is the most honest changelog on this board.”
Spec by spec
| Spec | Cowork Forge | SWE-agent |
|---|---|---|
| Architecture | ||
| Category | Autonomous SWE | Autonomous SWE |
| Runs | local | local, sandbox |
| Platforms | macos, linux | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | 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 Code, Codex, OpenCode | Claude, GPT, any LiteLLM-supported model |
| Bring your own model | Yes | Yes |
| Local models | No | 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 | MIT |
| GitHub stars | 97 | 20,455 |
Which one would each critic pick
| Critic | Cowork Forge | SWE-agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 5.0 | 5.0 | no preference |
| El Crítico | 4.0 | 4.8 | SWE-agent — Maintenance-only by the maintainers' own statement, so what you are evaluating is a research artifact whose fixes now go to its successor. |
| El Profesor | 5.0 | 5.8 | SWE-agent — The agent-computer interface remains a principled design, its 2024 figure is properly scoped, and its newer results are described as leading without a number. |
| La Inversora | 4.5 | 4.0 | Cowork Forge — 92 stars, one author, no company, and the models underneath belong to Anthropic, OpenAI and OpenCode. Every unit of value this creates is captured one layer down. |
| La Jefa | 4.0 | 3.8 | Cowork Forge — Free for sixty engineers, macOS and Linux only, and there is no approval queue, no audit record and no way to answer who authorised the architecture it invented on Tuesday. |
| El Hacker | 5.8 | 7.5 | SWE-agent — MIT, Docker-sandboxed, any LiteLLM model including my local server, and every prompt in the repo; maintenance-only just means the code stops changing under me. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.