Pretty much inherent to how we build software on top of LLMs – mixing developer instructions with untrusted user input is an anti-pattern that's baked into how we build this stuff
CODE
-
Stock Research DeepAgent: LangChain Multi-Agent Market Analysis System
By
–
Stock Research DeepAgent A stock analysis system using LangChain's DeepAgent framework to coordinate specialized agents for comprehensive market research and real-time data analysis. Check out the implementation and build your own! https://
github.com/sagar-n/deepag
ents
… -
ScrapeCraft: AI-Powered Web Scraping with LangGraph
By
–
ScrapeCraft: AI Web Scraping Editor Uses AI and LangGraph to power intelligent web scraping with automated code generation and real-time data streaming. Simplifies complex scraping workflows through bulk URL support. Check it out! https://
github.com/ScrapeGraphAI/
scrapecraft
… -
CodeLLM Launches New CLI Tool with Free ChatLLM Included
By
–
CodeLLM Now Has A CLI! Try the brand new CLI by downloading CodeLLM Click on the "CLI" button to try the new CLI. It's as good as Claude Code Comes with ChatLLM For Free
-
Apache Spark 4.0 transformWithState API for Operational Monitoring
By
–
Learn to build operational monitoring pipelines using Apache Spark™ 4.0's new transformWithState API This blog walks through how to use the new transformWithState API to:
-Track, alert on, and analyze sensor data with ValueState, ListState, and MapState
-Set up time-based state -
AI IPO Analyst: Automated Indian IPO Document Analysis Tool
By
–
AI IPO Analyst Automates Indian IPO document analysis by transforming complex financial documents into structured reports with real-time market data, financial ratios, and automated processing. Check out this powerful financial analysis tool https://
github.com/AKMessi/AI-IPO
-Analyst
… -
Hugging Face releases AI sheets for dataset building without code
By
–
Hugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code.
— Shubham Saboo (@Saboo_Shubham_) 16 août 2025
Works with Qwen, Kimi, Llama 3 and other opensource LLMs.
100% Free, local and Opensource.pic.twitter.com/onvrgg5hqRHugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code. Works with Qwen, Kimi, Llama 3 and other opensource LLMs. 100% Free, local and Opensource.
-
Axolotl: YAML-based LLM fine-tuning and LoRA optimization framework
By
–
4. Axolotl • Yaml-based setup for fine-tuning, LoRA/QLoRA, DPO, GRPO, and multimodal workflows
• Includes kernel optimizations for memory-efficient training GitHub repo: -
DeepSpeed: Distributed Fine-Tuning Framework for Large Language Models
By
–
3. DeepSpeed • Built for large-scale distributed fine-tuning with ZeRO and FSDP
• Optimized for multi-GPU and multi-node training with advanced memory management
• Trusted in production environments for scalable LLM training GitHub repo: -
LLaMA Factory: Fine-tune 100+ Models with Simple CLI
By
–
2. LLaMA Factory • Fine-tune over 100 models (LLaMA, Mistral, Gemma, etc.) using a simple CLI or WebUI
• Supports LoRA, QLoRA, full or frozen fine-tuning across 2–8‑bit precision GitHub repo: