#2222nd of 40 in Security

scopeweaver

Multi-agent LLM penetration-testing system with Go backend and Next.js UI

Releases and problems feed (RSS)

Stars
1.1k
License
AGPL-3.0
Last commit
Nov 2026
Last release
Nov 2026
Language
Go
Stars, last 7 weeks+1,118
30 Sept 2026: 5 stars7 Oct 2026: 14 stars14 Oct 2026: 585 stars21 Oct 2026: 738 stars28 Oct 2026: 831 stars4 Nov 2026: 903 stars11 Nov 2026: 972 stars18 Nov 2026: 1,123 stars

5 on 30 Sept 20261,123 on 18 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

ScopeWeaver runs LLM agents that explore targets, record assets and save confirmed findings, with task queues, report export and interception rules for tool calls. It is a rebranded, English/Korean-translated derivative of Autumn-27/ARTEX, stores data in PostgreSQL, and can import assets from ScopeSentry. Models come from Anthropic, OpenAI, GLM templates, an OpenCode SDK bridge or native Ollama.

Who it is for: Security testers running authorized LLM-driven pentests on own systems

Strengths

  • Supports keyless native Ollama, with an optional local-only network mode
  • Interception rules and approval records gate agent tool calls, with built-in destructive-command rules
  • Single Go binary with embedded frontend, plus Docker Compose and in-app updates
  • Imports assets from ScopeSentry by project or task

Weaknesses

  • Scope is prompt-level guidance, not a network boundary; egress control must be external
  • Requires PostgreSQL, and only one server per database is supported
  • Derivative of ARTEX; README says the modification date is not a release tag
  • OpenCode SDK bridge unsupported on Windows; Linux CI results pending

What it needs

  • no GPU
  • Docker + Compose
  • Needs PostgreSQL, LLM provider (Anthropic, OpenAI, Ollama or other)
  • Models: Anthropic, OpenAI, GLM (Z.ai), Ollama (native), OpenCode SDK bridge
  • port 8787

What changed

  1. v0.9.6 ↗ (opens in a new tab)Security fix

    GHSA-FC5Q-39XC-VJPF.

  2. v0.9.5 ↗ (opens in a new tab)Security fix

    GHSA-MFR8-8QWW-V76H. “Frontend security ([#99]): update Next.js 16.4.3 → 16.4.5 for [GHSA-mfr8-8qww-v76h][advisory]. Frontend dependency audit findings decreased 1 → 0; this count covers the frontend dependency graph only.”

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in Security

See all 40
Also in Security
RankProjectScore
1shannonAutonomous pentester that exploits web apps and APIs using source analysis52.1k stars+3,054 (+6.2%) in 30 daysAGPL-3.092 out of 100
2ifixaiPython CLI that audits AI agents for policy, access and reliability failures46.7k stars+17,519 (+60%) in 30 daysApache-2.087 out of 100
3StrixAutonomous multi-agent pentesting CLI that validates vulnerabilities with working PoCs76.6k stars+6,499 (+9.3%) in 30 daysApache-2.085 out of 100
#4ai-infra-guardRed-teaming platform for AI infra CVEs, MCP servers, agent skills and jailbreaks7.6k starsApache-2.084 out of 100
#5decepticonAutonomous red-team agents that run multi-stage attack chains from an approved plan Live demo ↗ (opens in a new tab)6.6k starsApache-2.084 out of 100