Open Issues Need Help
View All on GitHub Example apps: showcase quality gate + cache isolation about 1 month ago
documentation good first issue
MugdhaSontakke/ai-opticore MugdhaSontakke/ai-opticore An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Open project →
0
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
Add type-stub-free runtime validation error hints about 1 month ago
documentation good first issue
MugdhaSontakke/ai-opticore MugdhaSontakke/ai-opticore An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Open project →
0
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
Tokenizer: auto-discover model -> encoding mappings about 1 month ago
enhancement good first issue tests
MugdhaSontakke/ai-opticore MugdhaSontakke/ai-opticore An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Open project →
0
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python
Add disk-backed (file) cache backend about 1 month ago
enhancement good first issue roadmap:v0.2
MugdhaSontakke/ai-opticore MugdhaSontakke/ai-opticore An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Open project →
0
An open-source optimization layer for AI/LLM applications that reduces unnecessary token usage, latency, memory, and inference cost while preserving response quality.
Python