Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
ClawBench
ClawBench
Bifrost
Bifrost

umanitek/agent-blackbox

Guardian Agent Blackbox: Keep your AI agents safe from being tricked or compromised

Visit GitHub
Python
64
5
0
Custom license
website
FeaturedAdvertise to 180K+ monthly visitors
ClawBench

a benchmark for personal agents

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Momentum

How fast umanitek/agent-blackbox is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 10 – Oct 24, 2026

Stars +44 in 45 days

0102030
30

Forks +2 in 45 days

01
1

Merged PRs 25 in 45 days

0510
7

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 10Sep 16Sep 22Sep 28Oct 4Oct 10Oct 16Oct 22
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Thu, Sep 10, 2026+1+00
Fri, Sep 11, 2026+0+00
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+1+00
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+1+10
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+1+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+0+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+1+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+1+00
Wed, Sep 30, 2026+0+00
Thu, Oct 1, 2026+0+10
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+02
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+05
Sat, Oct 10, 2026+1+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+02
Tue, Oct 13, 2026+4+03
Wed, Oct 14, 2026+30+04
Thu, Oct 15, 2026+2+00
Fri, Oct 16, 2026+0+01
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+07
Fri, Oct 23, 2026+1+01
Sat, Oct 24, 2026+0+00
Total+44+225
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 162 posts

    • An AI agent is about to run a command it was tricked into running. What checks the action before it executes? Threat intelligence for agents, built on the OriginTrail (@origin_trail) DKG…

      Read full on X, posted by @BullsCryptolife

      @BullsCryptolife · x.com

    • Introducing Trader Shield 🛡️ Demoed yesterday, and it just got a big upgrade. Your #AI Trading Agent keeps trading while your @NousResearch Hermes Agent uses #Blackbox to keep agents away from your…

      Read full on X, posted by @umanitek

      @umanitek · x.com

  2. Oct 142 posts

    • We gave #AI agents hands before we gave them an immune system. They run commands, install packages, open files, all on trust. Agent #Blackbox is the check between intent and action, built on…

      Read full on X, posted by @umanitek

      @umanitek · x.com

    • The shared threat reports leave out prompts, commands and file contents. Sharing is opt-in, so another agent can get the warning without receiving the user's private conversation.

      Read full on X, posted by @OTLars

      @OTLars · x.com

  3. Oct 131 post3 posts

    • "My agent only reads my prompts." It doesn't. It reads every page it fetches and every tool output. Each one can carry an instruction. Agent Blackbox watches that boundary, anchored on @origin_trail.…

      Read full on X, posted by @umanitek

      @umanitek · x.com

    • "Protects your #AI agent" is marketing fog until you name the threats. So I named all six. Prompt injection, bad deps, rm -rf, your .ssh keys, leaked secrets, malicious skills. #Blackbox checks…

      Read full on X, posted by @umojaark

      @umojaark · x.com

    • What @umanitek #Blackbox actually catches: 1. ✅ Prompt injection 2. ✅ Vulnerable dependencies 3. ✅ Dangerous commands 4. ✅ Sensitive file access 5. ✅ Secret exposure 6. ✅ Suspicious skills Plus…

      Read full on X, posted by @TriniZone

      @TriniZone · x.com

  4. Oct 111 post

    • I already told you folks the @origin_trail #DKG would show up where nobody expected. Now @umanitek #Blackbox uses it to sync verified threat intelligence to every protected agent. It's a good day…

      Read full on X, posted by @TriniZone

      @TriniZone · x.com

  5. Oct 101 post

    • Your #AI agent isn't evil. It's obedient. And obedience without a checkpoint is a liability. #Blackbox from @umanitek checks what an agent is about to run before it runs, with threat intel synced…

      Read full on X, posted by @umojaark

      @umojaark · x.com

  6. Oct 91 post

    • Why I'm heavy on @umanitek Agent #Blackbox 1. ✅ One install, every local agent 2. ✅ Catches real risks 3. ✅ Live dashboard + audit trail 4. ✅ Verified threat intel on the @origin_trail #DKG Star it…

      Read full on X, posted by @TriniZone

      @TriniZone · x.com

You might also like

Repositories close to umanitek/agent-blackbox
FeaturedAdvertise to 180K+ monthly visitors
ClawBench

a benchmark for personal agents

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

WhitzardAgent/AgentGuard

Python

AgentGuard: Zero-Trust Security Foundation for AI Agents

15416

secureagentics/Adrian

Python

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

586104

BakeLens/crust

Go

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

43735

panguard-ai/panguard-ai

TypeScript

Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。

659

AnthonySmith96/open-guardian

Rust

Stopping smart agents from doing stupid things.

7612

LucidAkshay/kavach

TypeScript

Tactical AI Workspace Monitor & EDR

26048

try-loopers/loopers-oss

Go

Firewall for the agentic era

10618

archestra-ai/OpenAPPA

Rust

Deterministic guardrails that don't break agents

1.6k68

NirDiamant/moltbook-agent-guard

Python

Real-time security for AI agents on Moltbook

6610