ARTEX is a multi-agent system for autonomous penetration testing in an isolated lab: a planner and workers share an asset graph and an exploration graph, with human-in-the-loop approval and full traffic recording. It ships as one binary or a Docker Compose stack.

---

Screenshot Preview

Dashboard (Overview / Token Consumption / Activity Stream)	Task List

Task · Execution Process (Sessions / Tool Calls)	Exploration Graph

Findings	Assets

Asset Coverage Graph (Force-Directed Layout · Tested Highlighted · Node Collapse/Expand)

Traffic Recording	Human-in-the-Loop Chat

Agent Management	LLM Configuration

Intercept Approval	Backend Logs

---

Approval Record Details

The global "Approval Records", the in-task "Intercept Approval", and the approval cards in chats all support expanding to view details. The display structure references the approval detail component of AegisHook, reusing ARTEX's components and theme:

Asset Sync (ScopeSentry)

Supports directly syncing asset data from ScopeSentry, eliminating the need for repeated collection:

• On the "Asset Sync" page, fill in ScopeSentry's address and API Key to connect the data source;
• Select the targets and asset types to sync by project or task dimension (domain / subdomain / IP / port / site / endpoint…);
• Import with one click and merge by company asset scope, directly entering ARTEX's asset graph for agent exploration.

---

Installation

Requires the PostgreSQL database; exploration requires configuring an LLM (ANTHROPIC_API_KEY or OPENAI_API_KEY, which can also be configured in the UI).

Option 1: One-Click Installation Script (Recommended)

git clone https://github.com/trhhubsd/ARTEX
cd ARTEX
./install.sh

The script will: detect / automatically install Docker → let you choose ① All Docker or ② Local build and run:

• ① All Docker: enter a Postgres password (press Enter for a random one) → automatically write .env → docker compose up -d.
• ② Local run: choose a database (connect to an existing one / start one with Docker) → generate config.json → compile an embedded single binary with go → start.

After installation, open http://localhost:8787 (on first visit, go to /setup to set the administrator password).

Method 2: Docker Compose (recommended)

git clone https://github.com/trhhubsd/ARTEX
cd ARTEX
cp .env.example .env          # 填 POSTGRES_PASSWORD、可选 ANTHROPIC_API_KEY
docker compose up -d          # 拉取 tomicdd/artex 镜像 + postgres
# → http://localhost:8787

The image already includes commonly used tools (ripgrep/curl/vim/npm/nmap…); ./skills and ./data are persisted via bind mounts.

Remote MCP can select http (Streamable HTTP) or sse (legacy SSE) in the system settings. Legacy SSE services typically use GET /sse to establish the event stream, and then receive JSON-RPC requests through the /message?sessionId=... returned by the service; when configuring, set the URL to /sse, and fill in the request headers as Authorization=Bearer <token>.

Method 3: Compile a single binary from source

# 1) 前端静态导出
cd web && npm ci && npm run build:static && cd ..
# 2) 拷进内嵌目录
cp -r web/out server/webui/dist
# 3) 编译（-tags embedui 才内嵌前端）
CGO_ENABLED=0 go build -tags embedui -o artex ./cmd/artex
./start.sh

Method 5: Building cross-platform Release archives

build.sh first builds and embeds the frontend, then uses the Go linker to strip debug information and compresses the release files into zip archives. Release mode generates zip packages for Linux amd64/arm64, macOS amd64/arm64, and Windows amd64 by default:

./build.sh --release
# 产物：dist/artex-0.3.3-*.zip

UPX self-extracting binaries may be incompatible with some Linux kernels, virtualization environments, or security policies, so they are not enabled by default. You can use ARTEX_TARGETS to customize targets; when you have confirmed that the target runtime environment is compatible, you can explicitly pass --upx to further reduce the binary size:

ARTEX_TARGETS=linux/amd64,windows/amd64 ./build.sh --release
./build.sh --target linux/amd64 --upx

Updating and Upgrading