Supported agents
JiuwenSwarm¶
openJiuwen's agent.
| Key | jiuwenswarm |
|---|---|
| Driven over | ACP |
| From | PyPI |
| Installed | workswarm==0.2.7 |
| Licence | Apache-2.0 |
Versions¶
| Version | Upstream | Ports | Tools | |||||
|---|---|---|---|---|---|---|---|---|
| One task | Workspace files | MCP tools | Conversation | decoys | chain | retry | ||
jiuwenswarm | 0.2.7 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
Options¶
| Option | Values, default in bold | What it sets | Versions |
|---|---|---|---|
reasoning_effort |
default, off, minimal, low, medium, high, xhigh, max |
How much reasoning the model uses before answering, with default leaving the choice to the provider. |
every version |
Benchmarks it fits¶
| GSM8K | HumanEval | SWE-bench Verified | τ³-bench | Terminal-Bench 2.0 | |
|---|---|---|---|---|---|
| One task | Workspace files | Workspace files | MCP tools, Conversation | Workspace files | |
jiuwenswarm | ✓ | ✓ | ✓ | ✓ | ✓ |