6 packages
agentbench
Lighthouse for AI coding harnesses. Benchmark your Claude Code setup and get a score out of 100.
agentdial
Dial your AI agent into every platform. One identity. Every channel.
agentmoney
Track what your AI agents actually spend. Real-time cost monitoring for Claude, OpenAI, and other LLM APIs.
claude-harness
Battle-tested Claude Code scaffold. Same model, 2x output.
@namanparikh/agentgrid
Spawn a grid of AI coding agents in one command
wikimem
Self-improving wiki IDE. Ingest anything (13 formats), query with any LLM, three automations: ingest, scrape, improve.