RAG

Local semantic memory in front of TypeSafe Jev: answers repeated decisions on CPU in ~30 ms, asks Jev only when unsure, and remembers the answer.

Assess your résumé and LinkedIn profile from a recruiter’s perspective with a Codex and Claude Code skill grounded in ATS documentation and hiring guides.

The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools.

Deterministic, offline citation router for UK legislation: maps a query to the exact Act or SI provision, or explains why it can't. Zero dependencies, built for legal RAG.

Estou compartilhando com o objetivo de ajudar as pessoas a terem uma noção de como é um desafio técnico para estágio no itaú!

Pedagogical semantic chunking and RAG dataset preparation from OpenStax textbooks

Local-first Markdown vaults, customizable knowledge graphs, and built-in research tools.

Statistically rigorous, causal evaluation for LLM apps on top of DeepEval: confidence intervals, causal interventions (RAG grounding, perturbations, agent attribution), and judge validity (bias audits, calibration, PPI).

Regression-testing for RAG retrieval pipelines using stable source-document anchors

Give your AI agents the context in your notes. Local Markdown and Obsidian retrieval, source-linked memory, MCP, and optional GitHub sources.

THE LLM TRUTH TELLER

Answer-aware memory for Markdown notes: hybrid search + pluggable passage reranker, as a Claude Code plugin

A local AI assistant that can see, hear, speak, browse the web, control your computer, and remember — built entirely in native C++, it is GPU agnostic with in-process implementation and privacy-safe embeddings vectors & LoRA adapters synchronization,with faster whisper/playwright libraries reimplemented into cpp.