Sato Hub
Developer Tool

AgentNode

An open package registry where AI agents detect missing capabilities and install trust-scored skills on demand.

  • Sato Score75
ActiveSelf-ReportedActive · today

AgentNode is an open-source developer tool by AgentNode, with last code activity on 2026-10-23 (Active). Latest release on 2026-09-07. Sato Score 75/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-24. How the score works →

See how to install AgentNode →

Last commit Oct 23, 2026 · Last release Sep 7, 2026 (v0.24.1) · ★ 4

Listed from agentnode.net on 2026-06-08. Install: not attempted. Evidence →

Next step

Watch AgentNode

One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.

Check it from your agent

Add Sato Hub’s MCP server (no key), then ask:

https://satohub.ai/api/mcp
Run Sato Hub Preflight on agentnode-ai/agentnode before I use it.
Full setup: Claude Code, Cursor, others →

Your project?

Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.

Claim this listing →

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.

Sato Score

75/100· High

How open, active & verifiable — not a safety or returns grade.

Maintenance & liveness
35/35
Code transparency
17/20
Interface verifiability
0/10
Docs & demo
6/10
Listing transparency & provenance
14/15
Independent verification
3/10

Sato Check

v0.24.1 · as of 2026-09-29
Does it take your key?
No key read found
Does your key leave?
Not yet run
Can it move funds on its own?
Unknown
Full profile, evidence and limits →

A profile describes what we read and ran, with dates. It is not a safety rating, an audit or an endorsement, and "not found" is not "not there".

Evidence — listed vs checked · what the words mean

Listed from agentnode.net on 2026-06-08. Install: not attempted.

ClaimValueEvidenceSourceChecked
Chains supportednot statedself-reportedagentnode.netas of 2026-10-24
Verification statusSelf-Reported — not independently reviewedself-reportedagentnode.netas of 2026-10-24
Recent activitylast release 2026-09-07 · last commit 2026-10-23observedgithub.com/agentnode-ai/agentnode2026-10-24
Install worksdocumented by the project, not run by Sato Hubnot attempted: no falsifiable install+entry probe from deploy_specself-reportedagentnode.netas of 2026-09-14
Website answersanswered (HTTP 200)observedagentnode.net2026-10-24
Daily check record90 of 90 daily checks since 2026-07-26 succeededa success rate of our checks, not uptime; the source is this listing's own historyobserved—2026-10-23
Takes your keyno private-key read found in what we readtracedsatohub.ai2026-09-29
Key leaves the machinenot yet run with planted test keysthe sandbox lane has not run on this versionobservedsatohub.ainot dated
Moves funds on its ownunknown — could not read what it exposestracedsatohub.ai2026-09-29
Built byAgentNodeconfidence 0.85self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-24
Creator profilehttps://github.com/agentnode-aiconfidence 0.75self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-25
Deploys aspip, npm, MCP server, Docker, Self-hostedconfidence 0.85self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-24
Works withLangChain, CrewAI, MCP, OpenAI Functions, Pythonconfidence 0.90self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-24
Agent typesAgent Framework Tooling, Developer Tooling, Registryconfidence 0.85self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-24
Tagsagent-skills, package-registry, anp, langchain, crewai, mcp, trust-scoring, dev…confidence 0.85self-reportedgithub.com/agentnode-ai/agentnodeas of 2026-06-24
Sato Score75/100 (High)how open, active and verifiable — not a safety or quality gradecomputedsatohub.ai2026-10-24

Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.

Install — not run by us — no falsifiable install+entry probe from deploy_spec

Runtime: Python (agentnode-sdk >=0.16)

pip install agentnode-sdk
agentnode setup
agentnode install word-counter-pack
agentnode CLI (package manager + runtime for agent skill packs)

Read from the project’s own docs as of 2026-09-14. What a deploy spec is →

Observed record — 91 daily checks since 2026-07-26

100%of 91 checks since 2026-07-26 succeeded
Currently responding for 91 days
Succeeded
91
Failed
0
Their error
0
Unattributed
0

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 37 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.

Last 30 days — to 2026-10-24, one point per UTC day

Share of OUR checks that succeeded
100%
7-day rolling; unattributable days are gaps · 30/30 days
Tools listed
fewer than 2 points—
from the server's own tools/list · 0/30 days
Sato Score
75
as snapshotted that day · 29/30 days

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Details

Chains
Unknown
Agent types
Agent Framework Tooling, Developer Tooling, Registry
Open source
Yes
Deploys as
pip, npm, MCP server, Docker, Self-hosted
Works with
LangChain, CrewAI, MCP, OpenAI Functions, Python
Last checked
2026-10-24

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.

#agent-skills#package-registry#anp#langchain#crewai#mcp#trust-scoring#developer-tools#ai-agents#python
See something inaccurate or outdated?Submit a correction →

Recent Activity

All news →

Releases and posts from AgentNode, pulled from its GitHub and X.

Releaseagentnode-ai/agentnodeSep 7, 2026

agentnode-sdk 0.24.1 — the sandbox does what it said

agentnode-sdk 0.24.1 — the sandbox does what it said Released 2026-09-07 from candidate 82c96cc8028568c0ff024baabc4911e369ec0a73 , tagged v0.24.1 at merge commit 2c513e743a393f242904b39f75d25b55f671493c , under founder authorisation. Three defects in the local sandbox runtime, found by the backend conformance suite measuring a real container rather than reading its configuration. Each was a proper

GitHub ↗
Releaseagentnode-ai/agentnodeSep 2, 2026

agentnode-sdk 0.24.0 — The container is the boundary

This release makes the execution boundary real rather than advisory. Third-party code that is merely trusted no longer runs on your host by default, a community agent's own entrypoint cannot run on the host at all, and the lockfile that decides what may run is integrity-checked at run time. It also repairs a defect that breaks fresh installs of 0.23.0. Please read the migration section before upgr

GitHub ↗
Releaseagentnode-ai/agentnodeJul 12, 2026

agentnode v0.23.0

agentnode-sdk 0.23.0 — MCP ownership CLI verbs (publish-challenge)

GitHub ↗
Releaseagentnode-ai/agentnodeJul 9, 2026

agentnode v0.22.0

SDK 0.22.0 — MCP from the terminal + refreshed compatibility

GitHub ↗
Releaseagentnode-ai/agentnodeJul 9, 2026

agentnode v0.21.0

SDK 0.21.0 — community agents run sandboxed by default

GitHub ↗
Releaseagentnode-ai/agentnodeJul 7, 2026

v0.20.0: Merge pull request #42 from agentnode-ai/sdk-version-sync-0.20.0

Sync version to 0.20.0 (agentnode --version reported 0.19.0)

GitHub ↗

Listing History

Recorded changes to AgentNode's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.

  1. Sep 7, 2026
    New release published
  2. Sep 3, 2026
    Sato Score tier: Medium → High
    Score 65 → 75.
  3. Sep 2, 2026
    New release published
  4. Aug 24, 2026
    Sato Score tier: High → Medium
    Score 72 → 62.
  5. Jul 27, 2026
    Sato Hub began tracking this listing
  6. Jul 20, 2026
    Edited: deploy spec
  7. Jun 25, 2026
    Enriched: creator profile url
  8. Jun 24, 2026
    Auto-enriched: creator name, supported integrations, deployment options, tags +1 more

Compared with

Appears in

Related Resources

Reference

QuestionsShowHide

Questions people ask about AgentNode

Is AgentNode open source?
Yes. AgentNode is open source under the MIT (SDK & Packs); BSL-1.1 (backend) license; the repository is https://github.com/agentnode-ai/agentnode. Checked as of 2026-10-24.
Which chains does AgentNode support?
Sato Hub has no confirmed chain list for AgentNode as of 2026-10-24; treat chain support as unknown.
Is AgentNode still maintained?
The most recent code activity Sato Hub observed was on 2026-10-23 (last commit 2026-10-23, last release 2026-09-07), which Sato Hub labels "Active". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
How do I install or run AgentNode?
Python (agentnode-sdk >=0.16). Install: pip install agentnode-sdk && agentnode setup && agentnode install word-counter-pack. Entry: agentnode CLI (package manager + runtime for agent skill packs). This is taken from the project's own documentation and has not been reproduced by Sato Hub.
Is AgentNode verified on Sato Hub?
No independent verification is on record for AgentNode; its verification status is "Self-Reported" and its Sato Score is 75 of 100. Self-reported is not verified, and the score is not a safety, quality or returns grade.
Cite this pageShowHide

Cite this page

Sato Hub. "AgentNode — Sato Hub." Sato Hub, updated 2026-10-24, accessed 2026-10-24. https://satohub.ai/resources/agentnode

Data last refreshed 2026-10-24; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.

Join the Sato Hub Briefing

Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.