Tag: openrouter

Claw-Eval is an open-source evaluation harness for LLM agents featuring 300 human-verified tasks, 2,159 rubrics, and a strict Pass^3 consistency protocol. Maintained by PKU and HKU researchers.

V3SP3R transforms your Flipper Zero into an AI-powered command center controlled by natural language voice commands. This complete guide covers installation, architecture, real code examples, and advanced usage for security professionals and hardware hackers.

Claude Code Router lets you route AI coding requests to cheaper, faster models while keeping Anthropic's exceptional CLI interface. Cut costs by 90% with intelligent task-based routing to DeepSeek, Gemini, Ollama, and more.

Slash Claude Code costs 90% with Houtini LM—an MCP server that intelligently offloads grunt work to local or cheap cloud LLMs while keeping Claude as architect. One-line install, automatic model routing, and real savings tracking.

G0DM0D3 is a fully open-source, privacy-respecting multi-model chat interface for AI red teaming. Built as a single HTML file with 55+ models, parallel jailbreak racing, and systematic perturbation engines. Deploy anywhere in seconds.

Discover how Andrej Karpathy's LLM Council uses multi-model peer review to dramatically improve AI answer quality. Stop trusting single models—build your deliberative AI council today.

Discover nanocode, a revolutionary 250-line Python AI coding assistant with zero dependencies. This minimal Claude Code alternative delivers full agentic capabilities, tool use, and conversation history in a single file. Learn setup, real code examples, and why developers are embracing this minimalist powerhouse.