Agent-readable docs
PentAGI Documentation
Self-hosted autonomous penetration testing platform: Docker deployment, multi-agent flows, BYOK LLM providers, REST and GraphQL APIs, sandbox tools, and optional observability stacks for security engineers and operators.
Pages
- OverviewWhat PentAGI exposes: autonomous multi-agent pentests in Docker, BYOK LLM providers, web UI, REST and GraphQL under /api/v1, and the shortest path from deploy to first flow.
- InstallationPrerequisites, Docker Compose core stack, .env from .env.example, SSL and data volumes, and compose overlays for observability, Langfuse, and Graphiti.
- QuickstartFirst successful run: set at least one LLM key, docker compose up, open https://localhost:8443, change admin@pentagi.com defaults, create a flow, and verify provider and UI health.
- Interactive installerTUI installer wizard: system checks, .env generation, LLM and search setup, SSL hardening, compose deploy, and admin password reset maintenance paths.
- Flows, tasks, and subtasksExecution hierarchy: Flow lifecycle and StatusType states, Task objectives, Generator and Refiner subtask plans, Assistant mode, and putUserInput, stopFlow, finishFlow boundaries.
- Agents and supervisionSpecialist agents (primary, pentester, coder, installer, searcher, memorist, adviser, reflector, reporter), execution monitor, planning step, and tool-call hard limits.
- Tools and sandbox executionTool categories, Docker-isolated terminal and file tools, network search tools, barrier tools done and ask, timeouts, and default images for general vs pentest work.
- Memory and knowledgepgvector memory tools, embeddings config, chain summarizer budgets, user knowledge documents API, flow files and resources under /work, and optional Graphiti graph search.
- Configure LLM providersWire OpenAI, Anthropic, Gemini, Bedrock, DeepSeek, GLM, Kimi, Qwen, and Ollama via env keys and server URLs; UI provider profiles for per-agent models; test providers before flows.
- Local and custom providersOpenAI-compatible custom endpoints (LLM_SERVER_*), Ollama local or cloud, config path YAML, legacy and preserve reasoning flags, and aggregator endpoints such as OpenRouter and DeepInfra.
- Search enginesEnable and configure DuckDuckGo, Google CSE, Tavily, Traversaal, Perplexity, Sploitus, and Searxng; scraper URLs; proxy and timeout constraints that gate network search tools.
- Authentication and API tokensLocal session login, OAuth Google and GitHub, default admin account, password change, Bearer API tokens for REST and GraphQL, and permission-scoped token lifecycle.
- Observability and LangfuseOptional OpenTelemetry path to Grafana, VictoriaMetrics, Jaeger, and Loki; Langfuse LLM analytics compose stack; OTEL_HOST and LANGFUSE_* keys; what each stack measures.
- Knowledge graphEnable Graphiti with Neo4j via docker-compose-graphiti.yml, GRAPHITI_* settings, graphiti_search tool behavior, and failure modes when the graph backend is down.
- Docker sandbox and worker nodesDocker socket and network options, DOCKER_INSIDE and NET_ADMIN, default and pentest images, custom OpenVAS image, and multi-host worker_node deployment constraints.
- Environment variablesAuthoritative Config struct and .env.example: core, Docker, server, providers, embeddings, summarizer, search, OAuth, proxy, supervision, Graphiti, Langfuse, and DB pool keys with defaults.
- REST APIGin routes under /api/v1: auth, flows, tasks, subtasks, files, resources, containers, toolcalls, assistants, logs, knowledge, providers, settings, users, tokens; Swagger at /api/v1/swagger.
- GraphQL APIschema.graphqls surface: Query, Mutation, and Subscription operations for flows, assistants, providers, prompts, API tokens, knowledge, usage stats, and real-time log streams over WebSocket.
- Provider configuration schemaPer-agent YAML and AgentsConfig fields: model, temperature, top_p, top_k, max_tokens, json mode, reasoning, price, extra_body; built-in provider config.yml baselines and UI testAgent/testProvider.
- Tools referenceNamed tool registry: terminal, file, browser, search engines, memory store/search, agent delegation tools, result tools, barrier tools, and assistant flow-control tools with argument shapes.
- Prompts and templatesPromptType enum, embedded .tmpl templates, validation via validatePrompt, user prompt CRUD, and how agent templates bind to execution context variables.
- Example provider configsCopy-paste YAML from examples/configs for vLLM, Ollama, OpenRouter, DeepInfra, Azure, and cloud-compatible endpoints mapped to agent config keys.
- Sample pentest promptsReady flow inputs from examples/prompts: base web pentest checklist and scope-of-work style engagement prompts with expected report-oriented outcomes.
- Deploy with vLLM and QwenAir-gapped style local inference: hardware matrix, vLLM serve flags, LLM_SERVER_* wiring, thinking vs non-thinking provider YAML, and supervision flags recommended for sub-32B models.
- Development and testingBackend go build and test, frontend pnpm scripts, gqlgen and graphql:generate, ctester container tests, etester embeddings, ftester tool calling, and local compose for contributors.
- ContributingLicense-compatible dependency policy, generate-licenses.sh, PR expectations, and contributor workflow boundaries for backend and frontend changes.
Complete Markdown
The complete agent-readable Markdown files are published separately from this HTML page.