API costs are killing AI devs. Local models help, but multi-model setups are a pain.OpenCodeSE: my tuned OpenCode Desktop.- Multi-model routing (local/routine/pro), auto-selected- Dynamic AutoCompact after long tool-call rounds, not only at the context limit- Wizard Mode: token-lean workspace, agent files + optimized first promptTest: Local Qwen 3.8 125B + DeepSeek routing = 6c, 1.3M tokens. DeepSeek only = 30c, 14M tokens.https://github.com/24high/Opencode-SE#AI #LocalLLM #AIEngineering
Related
“By analyzing #NASA #lidar data, my #AI agents discovered a #Maya site in Mexico that, as far as anyone can tell, no one...
“By analyzing #NASA #lidar data, my #AI agents discovered a #Maya site in Mexico that, as far as anyone can tell, no one had reported before. It took less than 72 hours to go from ...
rtopy: an R to Python bridge -- noveltieshttps://thierrymoudiki.github.io/blog/2026/01/08/r/python/rtopy#Python #DataSci...
rtopy: an R to Python bridge -- noveltieshttps://thierrymoudiki.github.io/blog/2026/01/08/r/python/rtopy#Python #DataScience #MachineLearning #rstats #Techtonique
📰 Insector X - An unofficial AI fan port of Taito's 1989 horizontal shooter by caiusarcade {WIP}Caiusarcade has just rel...
📰 Insector X - An unofficial AI fan port of Taito's 1989 horizontal shooter by caiusarcade {WIP}Caiusarcade has just released an early build of an unofficial fan port of Taito's 19...