AI Dev Impact Lab JA
← Topics ranking · 2026-08
GITHUB TOPIC

#agent-benchmark

GitHub repositories that have self-applied the topic "agent-benchmark" — a creator-tagged metadata that surfaces how AI projects describe themselves.

4
tagged repos
7
top 4 stars
1
with tool sigs
4
shown

REPOS Repos for #agent-benchmark (top 4 by stars)

AgentBenchAudit/evidence-bounds

Release repository for agent benchmark evidence-reporting artifacts and reproduction workflows.

HTML 5 AI 70 live ↗
Mazha0309/the-evil-repository

An evidence-hostile, container-isolated benchmark and behavior analysis platform for long-horizon AI software agents.

Python 2 AI 70
tolga-tom-nook/hermes-arena

Public round wall for Hermes Arena on-chain agent skill tournaments

Solidity 0 AI 70 1 sig
ReverseZoom2151/craftonomous

Craftonomous is an agent-agnostic Minecraft embodiment and evaluation substrate: an MCP-native body with a declared perception budget and reliability-tracked skills.

TypeScript 0 AI 70

RELATED Other topics · full topics ranking →

#claude-code

1,564

#ai-agents

1,160

#llm

1,071

#claude

943

#python

806

#ai

741

#developer-tools

728

#mcp

727

#codex

521

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology