An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models as MCP tools — gpt-4o-mini goes from 26/75 to 75/75 with them.
Cross-referenced across 55 tracked directories
#52335
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
9/23/2026
Created
1
GitHub Stars
9/23/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
byteclawmail
MCP server for Wundervault zero-knowledge secret management
Sovereign encrypted persistent memory for AI agents. 8 MCP tools. GDPR erasure. Apache-2.0.
Pantani
Build real visual systems in TouchDesigner from plain language with Claude, Cursor or Codex.
hermoso-dev
MCP server + CLI for Hermoso — research winning ads and generate finished image/video ads with AI