1.google / langextractA Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.llmnlppythongemini-aiinformation-extrationlarge-language-models+5 morePythonAPACHE-2.039K total2.8K forks+205 starsfrom 39,057 · score 5.33
2.pydantic / pydantic-aiHow Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.agent-frameworkpydanticpythongenaillmharness+1 morePythonMIT21K total3.1K forks+108 starsfrom 20,908 · score 4.69
3.Generated-Computers / LocalsRun many AI agents at once on your Mac, up to 3x faster.agentsapple-siliconartificial-intelligenceinference-accelerationinference-enginemacos+2 morePythonAPACHE-2.0451 total36 forks+95 starsfrom 356 · score 4.56
4.vercel-labs / json-renderThe Generative UI frameworkTypeScriptAPACHE-2.019K total1K forks+88 starsfrom 18,811 · score 4.49
5.nokia-applied-research / AnyJevTurn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)calibrationdecision-modeljevjev-modelllmsystem-one+2 morePythonAPACHE-2.01.6K total179 forks+80 starsfrom 1,498 · score 4.39
6.567-labs / instructorstructured outputs for llms openaipythonpydantic-v2openai-functionsvalidationopenai-function-calliPythonMIT14K total1.4K forks+27 starsfrom 14,067 · score 3.33
7.dottxt-ai / outlinesStructured Outputsgenerative-aillmsprompt-engineeringsymbolic-aicfgjson+2 morePythonAPACHE-2.016K total910 forks+16 starsfrom 15,985 · score 2.83
8.guidance-ai / guidanceA guidance language for controlling large language models.Jupyter NotebookMIT22K total1.2K forks+4 starsfrom 21,813 · score 1.61