Skip to main content
Drop a repoSign up
NEWvicrodh/qbzjust droppedNEWkowalski-ptr/compass-before-compactjust droppedNEWlastmile-ai/mcp-agentjust droppedREPOxai-org/grok-build+2097 stars 24hREPOmsitarzewski/agency-agents+659 stars 24hREPOsafishamsi/graphify+599 stars 24hREPOstablyai/orca+566 stars 24hREPOjamiepine/voicebox+537 stars 24hNEWvicrodh/qbzjust droppedNEWkowalski-ptr/compass-before-compactjust droppedNEWlastmile-ai/mcp-agentjust droppedREPOxai-org/grok-build+2097 stars 24hREPOmsitarzewski/agency-agents+659 stars 24hREPOsafishamsi/graphify+599 stars 24hREPOstablyai/orca+566 stars 24hREPOjamiepine/voicebox+537 stars 24h
Nexis-AI/NexBenchpublicTypeScriptgithub.com/Nexis-AI/NexBench
Nexis-AI avatar

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.

AI AGENTSLLM INFRAAIAI TOOLSBENCHMARKBENCHMARK FRAMEWORKTRENDING #369

// OWNER · Nexis-AI · REPO SNAPSHOT

github.com/Nexis-AI

Nexis-AI

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.

STARS164+164 · 7d
FORKS56+0 · 7d
CONTRIBUTORS0maintainer graph thin
OPEN ISSUES · PRS0· 0 
LICENSEno license file
LANGUAGETypeScript 
FOUNDED
LOCATION
MEMBERS
PUBLIC REPOS
TOTAL STARS
FOCUS
FUNDING

//STAR HISTORY · 12M

+164 all-time-window
Stars · cumulative164 · today
//WHY IT'S TRENDING· narrative synthesis · medium confidence

Nexis-AI/NexBench is sitting at #369 on the trending leaderboard with a pulse of 22/100 with no cross-source channels firing yet — GitHub-stars-only signal so far.

The 7-day star delta is +164 (+—) against a base of 164, a meaningful uptick on its own base. What's actually moving is the AI agent / LLM tooling stack.

Watch-outs: no tagged release on record (treat as pre-stable).

↻ refreshed 55m ago· next sync in 10m· sourced from 0 channels · 0 mentions / 24h

FAQ · answers from the data spine

What is Nexis-AI/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.
Who maintains NexBench?
Maintained by Nexis-AI (the owner) on GitHub.
What language is NexBench written in?
Primarily TypeScript.
When was NexBench created? When was the last update?
Created July 11, 2026 · last commit July 17, 2026.
How do I install NexBench?
Clone the repo:
git clone https://github.com/Nexis-AI/NexBench.git
Then follow the README in the cloned directory.
Is NexBench actively maintained?
stalled — no commits for an extended period

//COMMENTS · 0

live thread · operators only

Sign in to join the discussion

Be the first to comment.
Created
Updated
Last commit