Best LLM Open Source Repos

The collection centers on practical and research-oriented LLM resources, with a strong emphasis on open-source tools, interoperability, and interpretability. The main themes include multi-LLM orchestration and APIs (calling diverse providers like OpenAI, Azure, Bedrock, Cohere, HuggingFace, and others), LLM interpretability, hands-on learning and deployment, and foundational education for building AI applications. Resource types span curated lists, tutorials, code repositories, and experiential materials that teach designing, training, deploying, and evaluating LLM-based systems. The focus areas cover cross-provider integration, real-time financial advisory demos, interpretability frameworks, and approachable introductions to LLM concepts (LLM101n) and storytelling applications. Overall, the collection aims to empower developers and researchers to experiment with, compare, and implement open-source LLM solutions, while prioritizing accessibility, experimentation, and practical implementation. 3 sources collected on Markwise, last updated June 6, 2025.

  1. GitHub - iusztinpaul/hands-on-llms: ๐Ÿฆ– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป about ๐—Ÿ๐—Ÿ๐— ๐˜€, ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€, and ๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐——๐—•๐˜€ for free by designing, training, and deploying a real-time financial advisor LLM system ~ ๐˜ด๐˜ฐ๐˜ถ๐˜ณ๐˜ค๐˜ฆ ๐˜ค๐˜ฐ๐˜ฅ๐˜ฆ + ๐˜ท๐˜ช๐˜ฅ๐˜ฆ๐˜ฐ & ๐˜ณ๐˜ฆ๐˜ข๐˜ฅ๐˜ช๐˜ฏ๐˜จ ๐˜ฎ๐˜ข๐˜ต๐˜ฆ๐˜ณ๐˜ช๐˜ข๐˜ญ๐˜ด

    github.com ยท Article ยท Added Dec 28, 2023

    ๐Ÿฆ– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป about ๐—Ÿ๐—Ÿ๐— ๐˜€, ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€, and ๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐——๐—•๐˜€ for free by designing, training, and deploying a real-time financial advisor LLM system ~ ๐˜ด๐˜ฐ๐˜ถ๐˜ณ๐˜ค๐˜ฆ ๐˜ค๐˜ฐ๐˜ฅ๐˜ฆ + ๐˜ท๐˜ช๐˜ฅ๐˜ฆ๐˜ฐ & ๐˜ณ๐˜ฆ๐˜ข๐˜ฅ๐˜ช๐˜ฏ๐˜จ ๐˜ฎ๐˜ข๐˜ต๐˜ฆ๐˜ณ๐˜ช๐˜ข๐˜ญ๐˜ด - GitHub - iusztinpaul/hands-on-llms: ๐Ÿฆ– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป about ๐—Ÿ๐—Ÿ๐— ๐˜€, ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€, and ๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐——๐—•๐˜€ for free by designing, training, and deploying a real-timeโ€ฆ

  2. GitHub - BerriAI/litellm: Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

    github.com ยท Article ยท Added Dec 13, 2023

    Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs) - GitHub - BerriAI/litellm: Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

View the full collection on Markwise