#large-language-models

skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

Open research framework and practical toolkit for studying interaction-shaped behavior, trajectory reconstruction, and long-horizon human–AI collaboration.

A living catalog of LLM security research, updated daily from arXiv

GenAI Career Roadmap 2026 🚀 | AI Job Paths & Skills Guide

Minimalist LLM chatbot 🐤

LLM-agnostic agent harness for trading futures on Claude Code, Codex, or Qwen Code, with a risk-gated order path and pluggable broker MCP servers (TopstepX default).

A bilingual, multi-tier, community-PR-driven knowledge base for LLM principles and papers.

?? AI ??(Wanyu AI Companion)- Android AI emotional companion app: PAD continuous emotion, layered memory, Live2D desktop pet, Agent capability market (plugin/Skill/MCP/permission)

Keep It Real — a schema-level deferral channel that makes LLM brevity safe. Code, data, and pre-registered protocols: a 400-conversation replication sweep, a placebo control, and a blinded human study (n=46).

Turns public officials' asset declarations into corruption risk scores and evidence-backed findings using local or cloud LLMs. Built for Ukraine's open NAZK register, adaptable to other countries.

How much of an LLM agent’s apparent behavior comes from the decoder rather than the model alone? SamplerScope holds the model’s logits fixed, changes only the decoding method, and measures how this alters outcomes in small decision environments.

From Scientific Papers to Knowledge Graphs: Exploring Agentic AI Literature.

A minimal Rust terminal client for OpenAI-compatible streaming chat APIs