AI agent
NexBench
NEXBENCH measures what an autonomous agent can actually do on-chain — execute transactions, route swaps, bridge funds, manage DeFi positions, research tokens, catch drainers, reconstruct portfolios, and run treasury governance — across 214 tasks in 8 categories, each run 5 times against deterministic forked-mainnet environments.
- Rank
- #4 of 2,547
- Stars
- 120★ +91/wk
- On radar
- since 2026-07-13
Momentum
rate of rise, not size · recomputes hourly
80.9
24h· new7d· new
Hover the chart for daily values
Why it's ranked
NexBench is an AI agent ranked #4 of 2,547 on the Cresting momentum radar, with a score of 80.9. It has 120 GitHub stars, +91 in the last 7 days, and has been tracked since 2026-07-13.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.946 |
| Recency boost | 0.643 |
| Signal decay | 0.998 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+19 in window · 19 latest · 4 snapshots
github · stars+91 in window · 120 latest · 4 snapshots
Related ai agents
- yuwen-publish-precheck发布前审｜发抖音/小红书/视频号前先让 AI 审一遍：哪句踩线、依据哪条官方规则、给能直接用的改法。38 篇真实样本校准判定尺度，72 条官方原文引文可查证，你踩过的坑沉淀成本地规则库越用越准。不承诺过审，不教绕审。#1 · 206★
- deja-vuMemory layer for coding agents: search, MCP recall, auto-context, secret redaction, stats, share and sync over the session logs Claude Code, Codex and opencode already write. One zero-dep binary.#2 · 335★
- blitzosBlitzOS — Claude/Codex Cloud VMs that boot knowing your whole codebase#5 · 124★
- clodex-ideLocal-first, zero-trust agentic IDE for verifiable autonomous software development.#6 · 833★
- WorkBuddyGuideA practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。#7 · 1,047★