Show HN: Single-header C++ libraries for LLM APIs – zero deps beyond libcurl1 points·by Shmungus·4 mesi fa·0 comments- llm-stream — streaming from OpenAI + Anthropic, callback-based - llm-cache — file-backed semantic cache, LRU eviction - llm-cost — offline token counting + cost estimation - llm-retry — exponential backoff + circuit breaker + provider failover - llm-format — structured output enforcer with hand-rolled JSON parserDrop in one .hpp, link libcurl, done. No nlohmann, no boost, no Python.https://github.com/Mattbusel/llm-stream https://github.com/Mattbusel/llm-cache https://github.com/Mattbusel/llm-cost https://github.com/Mattbusel/llm-retry https://github.com/Mattbusel/llm-format0 commentsPost comment—
Drop in one .hpp, link libcurl, done. No nlohmann, no boost, no Python.
https://github.com/Mattbusel/llm-stream https://github.com/Mattbusel/llm-cache https://github.com/Mattbusel/llm-cost https://github.com/Mattbusel/llm-retry https://github.com/Mattbusel/llm-format