Multi-agent architecture brainstorming -- agents debate code design for simplicity, modularity, and reusability
Project description
ArchSwarm
Multi-agent architecture brainstorming. Agents with different perspectives (simplicity, modularity, reusability, scalability) debate design decisions.
Install
pip install arch-swarm-ai
Usage
# Analyze project architecture
arch-swarm analyze . --scope src/
# Start a design debate
arch-swarm debate . --topic "How to reduce coupling in server.py?"
# View debate results
arch-swarm report <session-id>
Agent Roles
| Role | Focus |
|---|---|
| Simplicity Critic | Less is more. Flags over-engineering. |
| Modularity Expert | Clean boundaries, single responsibility. |
| Reuse Finder | Finds duplication, suggests abstractions. |
| Scalability Critic | Will this scale? Performance bottlenecks? |
| Trade-off Mediator | Synthesizes perspectives, proposes compromises. |
License
MIT
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
arch_swarm_ai-0.2.4.tar.gz
(89.1 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file arch_swarm_ai-0.2.4.tar.gz.
File metadata
- Download URL: arch_swarm_ai-0.2.4.tar.gz
- Upload date:
- Size: 89.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2c54f28d979d2e9d5c8dc091df7e48fb6351503bf55823135e2e4326bda7c581
|
|
| MD5 |
d02a5862466f145d0ab152b8b21efc6a
|
|
| BLAKE2b-256 |
4fd2180e0d59cde459c1eea53a5b1b9c45f3b298d723d7ce29c6c5f13ff11be1
|
File details
Details for the file arch_swarm_ai-0.2.4-py3-none-any.whl.
File metadata
- Download URL: arch_swarm_ai-0.2.4-py3-none-any.whl
- Upload date:
- Size: 97.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b9efb736e73364c6e61fe9dd96c0884e5954fa94aea188785294df3035b40268
|
|
| MD5 |
56952dc7af647e61e22bfcceb512cbb9
|
|
| BLAKE2b-256 |
127492ee0bd0abce76005e6b5b2cf894fa23b429db22beb01d28dfafc8d748ce
|
