Reach 125K+ monthly visitors
Advertise on TrendshiftRAG
Entoure ton LLM de reseaux de capacites verifiables (calcul, savoir, web), et redit chaque resultat dans sa voix. Model-agnostic, sans dependances.
AI-powered incident response platform combining NVIDIA AI, Hindsight persistent memory, and CascadeFlow runtime intelligence to analyze production incidents, retrieve historical knowledge, and accelerate root-cause analysis.
HR assistant on WhatsApp: RAG over policy docs + live HRMS data (leave balances, salary slips as PDF) with OTP verification. Powered by Groq, LangChain, FAISS, FastAPI, Twilio.
Four AI engineering skills evaluated with deterministic gates. The crow surveys you build.
Autonomous Web3 research agent for Telegram — live Mantle ecosystem data, ReAct loop, 14 skills
Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embeddings, a Rust port of PixelRAG, with a metaharness benchmark CLI: npx rupixel
Local-first Telegram support agent for Codex and Claude. Index Telegram, docs, and repo evidence locally; draft replies; post only after operator confirmation.
Long-term memory engine for LLMs. 80.2% on LongMemEval-S (full 500, official gpt-4o judge). Reproducible in one command.
Self-host the modern LLM stack.
🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applications
High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.
H-RAG: Hierarchical Vector Compression & Topic-Guided Retrieval for RAG
Codebase containing the RAS and AEGIS algorithm code for the ACL 2026 FIndings paper "LLM Program Optimization via Retrieval Augmented Search"
Chatbot RAG para consulta de documentación técnica y catálogo de vehículos. Python, LangChain, OpenAI, FastAPI, ChromaDB, Docker.
Jake is a time traveler from 2326. This gives him memory using RAG + ChromaDB + Ollama.