AI Plugin Indexgemini-38-live-extended-thinking-lite vs agent-mode
gemini-38-live-extended-thinking-lite and agent-mode are both ai and llm tools skills. agent-mode scores higher (88 vs 29 out of 100). agent-mode has more GitHub stars (3k), and agent-mode was updated more recently (yesterday). The table compares them side by side.
| gemini-38-live-extended-thinking-lite | agent-mode | |
|---|---|---|
| Score | 29 / 100 | 88 / 100 |
| What it does | Dual-mode Gemini 3.8 Live vs Extended Thinking — early ack, progress narration, background tools, budget-gated Live API (docs/GEMINI_38_LIVE_EXTENDED_THINKING.md). | Unified tool for managing agent LLM modes (add, remove, update, list, switch). |
| Publisher | Community: IgorGanapolsky | Community: PhyAgentOS |
| Grades | Maintenance A, Licence A, Quality C | Maintenance A, Licence A, Quality A |
| npm downloads a week | Not on npm | Not on npm |
| Runs | Skill | Skill |
| Works with | Claude Code, Claude apps | Claude Code, Claude apps |
| GitHub stars | 1 | 2,974 |
| Last commit | 19 Oct 2026 | 23 Oct 2026 |
| Licence | MIT | MIT |
| Listed since | 19 Oct 2026 | 23 Oct 2026 |
| Install gemini-38-live-extended-thinking-lite | Install agent-mode |
Questions
Is gemini-38-live-extended-thinking-lite or agent-mode more popular?
agent-mode has more GitHub stars: 2,974.
Can I use gemini-38-live-extended-thinking-lite and agent-mode together?
Yes. AI assistants can load several skills at once. Install both and the assistant picks the right one for each task.