AI coding - ProkopHapala/FireCore GitHub Wiki
AI model Comparisons / Leaderboards
Free API providers
- MetaCentrum
- https://metavo.metacentrum.cz/export/sites/meta/cs/seminars/Seminar2025/UzivatelskySeminar-AI-2025-Hejtmanek.pdf
- https://metavo.metacentrum.cz/cs/news/vypadek_2026_0003.html
- https://docs.cerit-sc.cz/en/docs/ai-as-a-service/introduction
- https://docs.cerit-sc.cz/en/docs/ai-as-a-service/llm-integration
Good Local Models
Cost Effective Models
AI Coding Rules / Workglow
- Andrej Karphathy CLAUDE.md
- How Claude Code works in large codebases: Best practices and where to start
To Do
- Make hierarchical
AGENTS.mdin sub-folder - Use OpenCode with local LLM (LMstudi) to build documentation
- User Hermes with local LLM to build documentation
Coding Tools / Agents
Context Building
Chat platforms
RAG for Coding
- Mistral RAG docs
- generative-ai/code_rag.ipynb : Code RAG - Reuse your already created codebase to generate more code
- Improving Retrieval Performance in RAG Pipelines with Hybrid Search
- Implementing RAG in Refact.ai AI Coding Assistant
- Hybrid search: RAG for real-life production-grade applications
- CodeRAG-Bench: Can Retrieval Augment Code Generation?
- Exploring the Combination of Full-Text Index with Cohere’s Reranker for RAG over a Knowledge Graph.
- Code Generation using Retrieval Augmented Generation + LangChain
- Building Hybrid Search Platforms: Combining Vector and Full-Text Search in RAG Pipelines
- https://python.langchain.com/docs/tutorials/local_rag/
- Advanced RAG techniques part 2: Querying and testing
- youtube : RAG for Code Generation, an AI Hacker Cup example
- youtube : Local GraphRAG with LLaMa 3.1 - LangChain, Ollama & Neo4j
PDF to Text
pip install "docling[vlm]" # pulls the Nougat weights
run
docling --pipeline vlm --enrich-formula --to md --image-export-mode referenced Vivace_paralel_triangular_matrix_GPU_nvr-2011-001.pdf