Skip to main content
Avatar for Reacher Zhang from gravatar.com

Reacher Zhang

Username    reacher-z
Date joined   Joined

34 projects

clawbench-eval

Last released

Benchmarking framework for evaluating AI web agents on real-world online tasks

autoresearch-gym

Last released

AutoResearchGym: Can AI Agents Automate AI Research? — placeholder; code release in progress.

autoresearch-2

Last released

E = AutoResearch²: Scaling the Research Process — placeholder; code release in progress.

harness-bench

Last released

HarnessBench: compare agentic harnesses on everyday online tasks (sister project to ClawBench).

scaling-law

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

r2-harness

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

harness-hub

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

nail-group

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

nail-eval

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

nail-agent

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

nail-bench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

video-judge

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

vlm-judge

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

mcq-bench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

video-mcq

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

task-harness

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

web-harness

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

realtask-bench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

life-bench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

everyday-agent

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

everyday-bench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

claw-eval

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

claw-agent

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

claw-ai

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

r2agent

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

harnessos

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

nail-clawbench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

claw-harness

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

clawbench-harness

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

openclawbench

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

clawbench-cli

Last released

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

gpuwatch

Last released

Lightweight NVIDIA GPU monitor — 20 notification channels (Slack, Discord, Telegram, ntfy, Teams, PagerDuty, Zulip, OpenClaw, and more), Prometheus/InfluxDB/Datadog metrics, crash/ECC detection, Kubernetes, GitHub Pages dashboard

gpu-watchdog

Last released

Lightweight NVIDIA GPU monitor — 20 notification channels (Slack, Discord, Telegram, ntfy, Teams, PagerDuty, Zulip, OpenClaw, and more), Prometheus/InfluxDB/Datadog metrics, crash/ECC detection, Kubernetes, GitHub Pages dashboard

nvidia-gpu-monitor

Last released

Lightweight NVIDIA GPU monitor — 20 notification channels (Slack, Discord, Telegram, ntfy, Teams, PagerDuty, Zulip, OpenClaw, and more), Prometheus/InfluxDB/Datadog metrics, crash/ECC detection, Kubernetes, GitHub Pages dashboard

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page