llucs/Patchly
Autonomous software engineering agent that lives inside repositories
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| mode | Operation mode (review, scan, resolve, command) | no | review |
| provider | LLM provider (api or ollama) | no | api |
| model | Model name for API provider | no | deepseek-v4-flash-free |
| ollama_model | Ollama model tag for local inference | no | qwen3-coder:30b |
| ollama_context_length | Context window in tokens for Ollama | no | 32000 |
| ollama_flash_attention | Enable flash attention for Ollama | no | true |
| ollama_kv_cache_type | KV cache quantization for Ollama | no | q8_0 |
| ollama_num_thread | CPU threads for Ollama inference | no | 4 |
| auto_create_issues | Automatically create issues for findings | no | true |
| auto_create_fix_prs | Automatically create fix PRs | no | false |
| config_file | Path to custom config file | no | "" |
Outputs
no outputs