Safer agent skills

Telegraphic text compression for LLM outputs.

C · Review first · Execution High

Replication materials for The Permission Effect: How Non-Anthropomorphic Framing Modulates LLM Self-Description

C · Review first · Execution High

omnimodel is a LLM proxy for any api shape

C · Review first · Execution High

🚀 Deploy production-ready AI infrastructure on Amazon EKS with strong observability, security, and authentication for seamless LLM management.

C · Review first · Execution High

🤖 Build an AI-driven autonomous trading system for Korean stocks using multiple LLMs, combining AI insights, statistical validation, and human decisions.

C · Review first · Execution High

A production-ready, modular RAG chat API built with FastAPI and LangChain. Strictly separates embeddings, vector retrieval, conversational memory, and LLM routing for easy testing, scaling, and provider swapping.

C · Review first · Execution High

WorkForce Development modules of LLM Vertex main website

C · Review first · Execution High

GitHub repository Nikhil-UCEOU/LLM-Security-Evaluation-Platform; metadata recovered from GitHub Search API.

C · Review first · Execution High

GitHub repository taro-univ/Research_LLM; metadata recovered from GitHub Search API.

C · Review first · Execution High

GitHub repository gmeoms/LLM-Guardrail; metadata recovered from GitHub Search API.

C · Review first · Execution High

DRBFM Assist - LLM-powered search system for defect analysis

C · Review first · Execution High

🛡️ Verify AI outputs with llmverify for Node.js, ensuring safety and accuracy without sacrificing privacy.

C · Review first · Execution High

A rust-based microservice and CLI for LLM tokenization.

C · Review first · Execution High

🚀 Benchmark LLM routing with OpenRouterBench, featuring 25+ datasets and models for robust inference and evaluation in diverse domains.

C · Review first · Execution High

Auditor for Claude Code skills and slash commands. Validates structured output against schemas using layered evaluation — deterministic assertions, LLM-graded extraction, and quality regression testing. Catches when your skill produces the wrong shape, not just the wrong answer.

C · Review first · Execution High

📘 Master LangChain and LLMs with hands-on notebooks, covering data ingestion, text processing, and AI application fundamentals for real-world tasks.

C · Review first · Execution High

⚡ Evaluate LLM prompts at scale with fast, parallel execution, real-time cost tracking, and insightful analytics across multiple models.

C · Review first · Execution High

Universal LLM Model Price & Metadata Matrix

C · Review first · Execution High

🚀 Build and deploy a lightweight RAG demo using FastAPI, Chroma, and Ollama LLM for efficient AI-assisted information retrieval.

C · Review first · Execution High

🔍 Optimize LLM requests by routing them to the best models, while leveraging semantic caching and real-time cost analytics for efficient resource use.

C · Review first · Execution High

GitHub repository agri-pat/onnx-llm-server; metadata recovered from GitHub Search API.

C · Review first · Execution High

GitHub repository juanso123/local-llm-pdf-ocr; metadata recovered from GitHub Search API.

C · Review first · Execution High

🚀 Build your own LLM easily with OpenLabLM, a lightweight, hackable codebase tailored for hobbyists using a single consumer GPU.

C · Review first · Execution High