Open-Source AI Tools That Feel ILLEGAL To Use

Author: The Stack - Bewertung: 4580x - Views:133617

Ten open-source AI tools that feel like cheating once you know them. Every one is free, most are self-hostable, and most builders have never heard of them.



We cover what each tool does and when to reach for it: LiteLLM for routing every model through one API, Crawl4AI for turning messy websites into clean LLM input, Instructor for forcing structured output, and seven more worth a slot in your stack. Repos and setup notes are in the video.



If you want to build more with AI and spend less doing it, start with these.



#OpenSource #AITools #AI



Chapters:

0:00 Intro

0:22 Number 10, Chonkie

1:53 Number 9, Marker

3:15 Number 8, Langfuse

4:37 Number 7, Qdrant

5:45 Number 6, Ollama

7:16 Number 5, DSPy

8:53 Number 4, Crawl4AI

10:15 Number 3, Outlines

11:47 Number 2, LiteLLM

13:40 Number 1, Instructor



Tools & resources mentioned:

- Instructor (567-labs): https://python.useinstructor.com/

- LiteLLM: https://github.com/BerriAI/litellm

- Outlines (dottxt-ai): https://github.com/dottxt-ai/outlines

- Crawl4AI: https://github.com/unclecode/crawl4ai

- DSPy: https://github.com/stanfordnlp/dspy

- Qdrant: https://github.com/qdrant/qdrant

- Ollama: https://github.com/ollama/ollama

- Langfuse: https://github.com/langfuse/langfuse

- Marker: https://github.com/VikParuchuri/marker

- Chonkie: https://github.com/chonkie-ai/chonkie



About The Stack

The Stack is a channel for people building with AI. Every video is a short, illustrated breakdown of the tools, models, and patterns that actually ship: Claude Code and AI coding tools, AI agents and orchestration, open-source AI tools and repos worth knowing, RAG and vector search, local and open-weight LLMs, and the model and cost calls that matter. Opinionated, evidence-led, no fluff.



New breakdowns regularly. Subscribe so you catch them: https://www.youtube.com/@The-Stack-ai?sub_confirmation=1



#opensource #llmtools #aiengineering #rag #machinelearning