AgentNode
An open package registry where AI agents detect missing capabilities and install trust-scored skills on demand.
Last release Jun 9, 2026 · Last commit Jun 8, 2026 · ★ 1
Overview
AgentNode is an open package registry for AI agent capabilities where agents detect missing capabilities and install verified skills at runtime, with sandboxed execution and a 0-100 trust score gating auto-upgrades. It uses a portable package format (ANP) compatible with LangChain, CrewAI, MCP, and plain Python, exposing typed tool functions per package. Trust tiers and confidence scores are computed by the platform's own sandbox testing and are self-reported, not independent audits. Not crypto-specific.
Details
- Chains
- Unknown
- Agent types
- Agent Framework Tooling, Developer Tooling
- Open source
- Yes
- Last checked
- 2026-06-10
Marketplace Signals
No marketplace signals recorded for this resource yet.
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Recent Activity
All news →Releases and posts from AgentNode, pulled from its GitHub and X.
agentnode v0.11.4
Prepare 0.11.4 publish confirm gate
agentnode v0.11.3
Prepare 0.11.3 test hygiene and multi-tool guidance
agentnode v0.11.2
Prepare 0.11.2 CLI run resolution fixes
agentnode v0.11.1
Prepare 0.11.1 bugfix and agent gate hardening
v0.11.0: Add agentnode CLI alias for 0.11.0 release
Reachability fix found during release-artifact verification: the help text, agentnode sandbox doctor output, and CHANGELOG all tell users to run agentnode ... , but the package only installed the agentnode-sdk console script. A user doing pip install agentnode-sdk and then agentnode sandbox pull (the key command to make the sandbox usable) would hit "command not found". Add an agentnode console-sc
Related Resources
Hyperliquid
ActiveOnchain perpetual futures and spot DEX running on its own L1 with an HyperEVM smart-contract layer.
Coinbase AgentKit
ActiveCoinbase's toolkit for giving AI agents wallets and the ability to take onchain actions.
Model Context Protocol (MCP)
ActiveAnthropic's open standard for connecting AI systems to external tools and data sources.
Join the Sato Hub Briefing
Get the weekly briefing on onchain agents, MCPs, skill repos, tools, and autonomous crypto infrastructure.