Top Finds

🧠 Enhance AI learning with the Claude Reflect System, an innovative self-learning tool that adapts from your corrections for improved performance.

Real-time Human Action Recognition using CNN + LSTM in PyTorch. Recognizes actions from videos or webcam, displaying top predictions with confidence scores via a Streamlit web app.

🛠️ Build and explore multi-agent workflows in LangChain with a user-friendly UI for deep research and monitoring AI agents.

MPNN-UnderReach explores the under-reaching phenomenon in message-passing neural PDE solvers. We propose physics-guided lower bounds on the number of message passing iterations. These bounds link graph information propagation to the CFL condition and PDE type. Official code for Tesan L. & Iparraguirre M.M. (2025)

Sentiment analysis with TextBlob and TF-IDF + Logistic Regression, Flask web UI — Python

🌟 beautifully styled demo web-app for revenue analytics (showcase)

🚀 Enhance your AI-assisted security workflows with plugins from the Trail of Bits Skills Marketplace for smarter analysis and testing.

Deep4ge: 14,227 mutation-induced DNN training logs for fault detection and diagnosis research (ICST 2026 Data Showcase)

w handcricket stats app

🧠 Implement UltraMem for enhanced memory performance with a streamlined design, leveraging advanced techniques from Bytedance AI labs.

Vietnamese NLP system for sentiment analysis and order-intent extraction from unstructured social content.

🛠 Extract skills from job descriptions and match candidates with relevant resumes using this NLP-powered recommendation engine.

🧠 Integrate hippocampus-inspired spatial memory into transformers with Hippoformer for enhanced learning and representation capabilities.

🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.

💰 Optimize your Claude API usage to save 50-90% on costs with batching techniques and efficient request management.

🚀 Connect Burp Suite MCP Server to multiple AI backends with practical guides and templates for safe, real traffic analysis.

High-performance ML model serving API built with Go and Python, featuring Redis caching, model drift monitoring, A/B testing, and MLflow integration

🤖 Build intelligent, offline LLM agents with LangGraph and llama-cpp-python using this starter template for local, private tool-calling applications.

Pipeline de classificacao com Random Forest, EDA e visualizacoes — projeto educacional (scikit-learn, pandas, matplotlib)

Deep ensemble EPL match prediction engine — 13 base learners, Dixon-Coles statistical model, 376+ engineered features, 8 data sources, NLP sentiment analysis. 60.2% accuracy, outperforms market odds.

🩺 Analyze post-stroke aphasia risks by investigating medication patterns and mental health impacts to improve patient outcomes and reduce hospital readmissions.

Structured knowledge packs that turn AI agents into domain experts — for products, people, and processes.

Computer vision system that detects capsules in a camera frame and classifies them as damaged, scuffed, or intact using OpenCV for detection and PyTorch for deep learning inference.

⚖️ Address inconsistencies in LLM-as-a-judge evaluations with TrustJudge's advanced scoring framework for reliable and nuanced assessments.

🚀 Automatically Cythonize to speed up projects!