Claude Skill

suyoumo/ClawProBench

ClawProBench 是一个以实时执行为优先的基准测试框架，用于在 OpenClaw 运行时环境中评估 LLM 代理，具备确定性评分和重复试验可靠性。

概览

Stars540
Forks47
语言Python
最后更新2026-04-26
最近同步2026-04-27
前往 GitHub

仓库信息

拥有者suyoumo
仓库ClawProBench
完整名称suyoumo/ClawProBench
Repo ID941,429,098
GitHub 地址https://github.com/suyoumo/ClawProBench

🚀 安装这个 Skill

openclaw install suyoumo/ClawProBench
⭐ GitHub

项目简介

ClawProBench 是一个以实时执行为优先的基准测试框架，用于在 OpenClaw 运行时环境中评估 LLM 代理，具备确定性评分和重复试验可靠性。

英文描述

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

话题

agentbenchmarkevaluationharnessleaderboardllmopenclaw

探索更多

拥有者: suyoumo语言: Python

相关技能

你可能也会感兴趣的 Claude Skill 项目。

infiniflow/ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

⭐ 78981🍴 8940Python
agentagenticagentic-ai

volcengine/OpenViking

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system ...

⭐ 23150🍴 1695Python
agentagentic-ragai-agents

icip-cas/PPTAgent

An Agentic Framework for Reflective PowerPoint Generation

⭐ 4176🍴 511Python
agentagentic-aillm

dataelement/Clawith

OpenClaw for Teams

⭐ 3412🍴 558Python
agentllmmultiagent

aiming-lab/MetaClaw

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

⭐ 3388🍴 423Python
agentai-agentcontinual-learning

casdoor/casdoor

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google W...

⭐ 13494🍴 1669Go
agentagentic-aiagi

数据来自 GitHub，同步时间：2026-04-27