ScopeWeaver

ScopeWeaver is a self-hosted console that coordinates multi-agent security research and asset graphs.

ScopeWeaver is a self-hosted console that coordinates goal planning, autonomous agents, asset scope, coverage, and recorded findings for locally isolated security research. It features a Go backend, embedded Next.js, and PostgreSQL, and derives from ARTEX under the AGPL-3.0 license. The platform splits targets and testing progress into linked graphs: a shared asset graph and a per-task exploration graph. A local adapter allows coding agents like Claude Code, Codex, and Pi to create tasks and read progress through an authenticated API. Users supply their own PostgreSQL database and model providers such as Anthropic or OpenAI to run exploration locally.

ScopeWeaver at a glance

Best for: Software engineer
Runs on: Web, self-hosted, API, open source
Pricing: Free
Released: October 2026
Category: AI research tool
Website: cskwork.github.io

Key features

Coordinate goal planning and autonomous agents
Track shared asset graphs and exploration graphs
Integrate with coding agents via local adapter
Manage health, tasks, coverage, and findings
Run locally with Docker Compose or release archives
Support custom model providers and PostgreSQL

Use it for

Conduct locally isolated security research
Manage multi-agent security exploration
Coordinate tasks with external coding agents
Review asset coverage and recorded findings

Alternatives to ScopeWeaver

ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
AgentScope — Offers triple-layer security with sandboxing and tool reviews.
ARTEX — Manages autonomous penetration testing tasks and tracks vulnerability progress.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
Webwright — Enables code-based web automation with reusable and rerunnable scripts.
Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
AgentScope Java — Provides engineering scaffolding for reliable, long-running agent execution.
WebBrain — Runs locally or in the cloud with your choice of LLM and zero telemetry.
AgentDock — It coordinates multi-device workflows and provides secure environment access.
Runway — Control Claude Code and Codex sessions on local or cloud machines from any phone.
Cloudbrowser — It gives every AI agent an isolated, persistent Chrome browser with saved login states.
Agent Cockpit — It checks evidence chains deterministically so broken claims never slip by unnoticed.

All ScopeWeaver alternatives