Since the servers are always “exhausted,” could it be possible to integrate local Ollama models for both offline and a more stable agent experience, or to just use your own OpenAI, Gemini, Anthropic, etc., API key?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Servers busy error | 0 | 229 | April 9, 2026 | |
| [Feature Request] Native Hybrid Execution: Package Gemma 4 & Local Indexers to Offload Cloud Model Quotas | 0 | 104 | July 24, 2026 | |
| Can we add option of main agent and sub agents? So each LLM model could be different | 0 | 77 | May 24, 2026 | |
| Can we add gemma4 models to AG 2.0? | 1 | 324 | June 29, 2026 | |
| Gemma on oMLX locally for Antigravity2 | 0 | 167 | June 12, 2026 |