lachtan/nanobot-runtime
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

dream: 2026-06-03 22:44, 2 change(s)

Browse Source 
[MEMORY] OpenRouter is pay-per-token alternative to Ollama subscription for model access
[MEMORY] Gemini Flash via Google AI Studio Free Tier: 15 RPM limit — unusable for agent work; only viable for simple prompts without tool calls
[MEMORY] Gemini Flash via Google AI Studio Tier 1 (paid): 360+ RPM
[MEMORY] Haiku (Claude) via OpenRouter: high rate limits, viable agent model alternative
[MEMORY] Gemini Flash Lite via OpenRouter: high rate limits, viable agent model alternative
This commit is contained in:
nanobot
2026-06-04 00:45:36 +02:00
parent 7cc0b48026
commit 14af90f497
2 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
memory/.dream_cursor
View File

@@ -1 +1 @@
296
298

5
memory/MEMORY.md
View File

@@ -44,6 +44,11 @@ This file stores important information that should persist across sessions.
- Primary nanobot agent model: GLM-5.1:cloud (best sustained productivity over long sessions/hundreds of rounds, strong real-world agent benchmarks)
- Alternative nanobot agent model for tool-heavy tasks: Qwen 3.5:cloud (397B variant)
- Conservative fallback nanobot agent model: DeepSeek V3.2:cloud
- OpenRouter is pay-per-token alternative to Ollama subscription for model access
- Gemini Flash via Google AI Studio Free Tier: 15 RPM limit — unusable for agent work; only viable for simple prompts without tool calls
- Gemini Flash via Google AI Studio Tier 1 (paid): 360+ RPM
- Haiku (Claude) via OpenRouter: high rate limits, viable agent model alternative
- Gemini Flash Lite via OpenRouter: high rate limits, viable agent model alternative
## Reminder System