GoPlus AgentGuard
MIT-licensed runtime guard for AI coding agents: hook-level action blocking, a 24-rule skill scanner, and a per-skill trust registry.
- Sato Score80
GoPlus AgentGuard is an open-source security tool, with last code activity on 2026-10-19 (Active). Latest release on 2026-10-19. Sato Score 80/100 (how open, active and verifiable it is, not a safety grade), as of 2026-11-05. How the score works →
See how to install GoPlus AgentGuard →Last commit Oct 19, 2026 · Last release Oct 19, 2026 (v1.2.4) · ★ 470
Listed from github.com/GoPlusSecurity/agentguard on 2026-09-22. Install: reproduced by Sato Hub on 2026-09-25. Evidence →
Next step
Watch GoPlus AgentGuard
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/mcpRun Sato Hub Preflight on goplussecurity/agentguard before I use it.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
AgentGuard installs as a hook layer around an AI coding agent and evaluates actions before they execute, blocking destructive shell commands, writes to credential files such as .env and .ssh, and outbound posts to Discord, Telegram and Slack webhooks, while recording which installed skill initiated each action. A second layer statically scans a skill or GitHub repository against 24 detection rules, including Web3 patterns such as wallet draining, unlimited approvals, reentrancy and proxy exploits. The README states the local runtime guard needs no cloud account or network connection. The rules describe what was detected in the code they read; they are not an assurance about code they did not read.
Sato Score
80/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 19/20
- Interface verifiability
- 8/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 9/15
- Independent verification
- 3/10
Deploy path reproduced — install verified in an isolated container (proves installability, not runtime safety).
Sato Check
v1.2.1 · as of 2026-10-02- Does it take your key?
- No key read found
- Does your key leave?
- Not yet run
- Can it move funds on its own?
- Unknown
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 github.com/GoPlusSecurity/agentguard on 2026-09-22. Install: reproduced by Sato Hub on 2026-09-25.
| Claim | Value | Evidence | Source | Checked |
|---|---|---|---|---|
| Chains supported | not stated | self-reported | github.com/GoPlusSecurity/agentguard | as of 2026-11-05 |
| Verification status | Unverified — not independently reviewed | self-reported | github.com/GoPlusSecurity/agentguard | as of 2026-11-05 |
| Recent activity | last release 2026-10-19 · last commit 2026-10-19 | observed | github.com/GoPlusSecurity/agentguard | 2026-11-05 |
| Install works | reproduced — install and entry both completedshows the install path works as written; not a statement about runtime behaviour | ✓ reproduced | github.com/GoPlusSecurity/agentguard | 2026-09-25 |
| Website answers | answered (HTTP 200) | observed | github.com/GoPlusSecurity/agentguard | 2026-11-05 |
| Daily check record | 44 of 44 daily checks since 2026-09-22 succeededa success rate of our checks, not uptime; the source is this listing's own history | observed | — | 2026-11-04 |
| Takes your key | no private-key read found in what we read | traced | satohub.ai | 2026-10-02 |
| Key leaves the machine | not yet run with planted test keysthe sandbox lane has not run on this version | observed | satohub.ai | not dated |
| Moves funds on its own | unknown — could not read what it exposes | traced | satohub.ai | 2026-10-02 |
| Works with | Claude Code, Codex, OpenClaw, Hermes, QClaw, DSHconfidence 0.80 | self-reported | github.com/GoPlusSecurity/agentguard | as of 2026-09-23 |
| Sato Score | 80/100 (High)how open, active and verifiable — not a safety or quality grade | computed | satohub.ai | 2026-11-05 |
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 — reproduced in a container Sep 25, 2026
Runtime: Node.js >=18
npm install -g @goplus/agentguard agentguard status
You supply: `agentguard init` to configure hooks for a supported agent host (Claude Code, Codex, OpenClaw, Hermes, DSH), AgentGuard Cloud connection is optional; the local runtime guard needs no account or network
MCP invocation: agentguard-mcp (stdio, from the same package)
Read from the project’s own docs as of 2026-09-25. What a deploy spec is →
Observed record — 45 daily checks since 2026-09-22
- Succeeded
- 45
- 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.
Last 30 days — to 2026-11-05, one point per UTC day
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
- Skill, Infrastructure
- Open source
- Yes
- Works with
- Claude Code, Codex, OpenClaw, Hermes, QClaw, DSH
- Last checked
- 2026-11-05
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.
Where GoPlus AgentGuard fits
Related concepts: What Are Onchain Agents?, Onchain Agents vs Offchain Agents
Recent Activity
All news →Releases and posts from GoPlus AgentGuard, pulled from its GitHub and X.
agentguard v1.2.4
AgentGuard 1.2.4 AgentGuard commands and installer results no longer trigger post-tool blocking or redaction. Execution-time approval remains in place. Routine events stay local; reportable events send only concise, redacted summaries to Cloud. Fixed Cloud reporting for blocked batch findings and recognition of partial installer output.
agentguard v1.2.2
version patch
agentguard v1.2.1
Added Added opt-in, local-first LLM traffic privacy protection with PII and relay detection, semantic prose analysis, capability-aware enforcement across supported agents, and redacted Cloud synchronization. Enable semantic analysis with agentguard privacy enable ; it is off by default and never applies to live prompts. Added native Windows scheduled jobs and DSH threat-feed subscriptions, self-ch
Listing History
Recorded changes to GoPlus AgentGuard's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Oct 19, 2026New release published
- Oct 16, 2026New release published
- Sep 29, 20263 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Sep 26, 2026Edited: entity class, resource type
- Sep 25, 2026Sato Score tier: Medium → HighScore 68 → 77.
- Sep 25, 2026Verified: deploy spec
- Sep 23, 2026Auto-enriched: supported integrations
- Sep 22, 2026Listed on Sato Hub
- Sep 22, 2026Sato Hub began tracking this listing
Compared with
Appears in
Related Resources
COTI
ActivePrivacy infrastructure that gives MCP-compatible agents private wallets, encrypted messaging, and confidential smart contracts using Garbled Circuits.
Turnkey
ActiveSecure key management infrastructure with policy controls, commonly used for agent wallets.
ChainAware
ActivePre-built MCP blockchain capability modules giving agents fraud detection, AML scoring, wallet profiling, and token analysis.
Reference
QuestionsWhat people ask about this pageShowHide
Questions people ask about GoPlus AgentGuard
- Is GoPlus AgentGuard open source?
- Yes. GoPlus AgentGuard is open source under the MIT license; the repository is https://github.com/GoPlusSecurity/agentguard. Checked as of 2026-11-05.
- Which chains does GoPlus AgentGuard support?
- Sato Hub has no confirmed chain list for GoPlus AgentGuard as of 2026-11-05; treat chain support as unknown.
- Is GoPlus AgentGuard still maintained?
- The most recent code activity Sato Hub observed was on 2026-10-19 (last commit 2026-10-19, last release 2026-10-19), 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 GoPlus AgentGuard?
- Node.js >=18. Install: npm install -g @goplus/agentguard. Entry: agentguard status. Sato Hub reproduced this install in a container on 2026-09-25. It runs as an MCP server (agentguard-mcp (stdio, from the same package)).
- Is GoPlus AgentGuard verified on Sato Hub?
- Sato Hub holds one earned check for GoPlus AgentGuard: Deploy path reproduced — install verified in an isolated container (proves installability, not runtime safety). Its Sato Score is 80 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pagePlain text, APA or BibTeXShowHide
Cite this page
Sato Hub. "GoPlus AgentGuard — Sato Hub." Sato Hub, updated 2026-11-05, accessed 2026-11-06. https://satohub.ai/resources/goplus-agentguardData last refreshed 2026-11-05; 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.