# AI-FW

> AI-FW is an AI firewall and governance gateway. It self-hosts between your people, agents, and applications and the model APIs they call, and it provides identity, prompt and response inspection, semantic policy, model routing, cost controls, and metadata-only audit. It runs as a Docker container in your own environment and is fail-closed by design.

## Key pages

- [Product](https://aifw.io/product): how the gateway works, layer by layer
- [Comparison](https://aifw.io/comparison): AI-FW vs other vendors, feature by feature
- [Pricing](https://aifw.io/pricing): free Community Edition and custom Enterprise
- [Community Edition license](https://aifw.io/community-edition/license): 100,000,000 tokens per month, rolling 30-day window
- [License document](https://aifw.io/community-edition/license.json): machine-readable allowance the gateway reads
- [Contact](https://aifw.io/contact): technical plan, proof of concept, sales
- [About](https://aifw.io/about): AI-FW is built by Securetron Inc. (Toronto, Canada), from phishing-resistant identity for non-human operators
- [Trust](https://aifw.io/trust): ISO/IEC 27001 and ISO/IEC 42001 certifications with IAF verification links, security posture and data handling
- [Media](https://aifw.io/media): launch video, screenshots, architecture diagram, source and release links
- [Glossary](https://aifw.io/glossary): plain-language definitions of AI governance and security terms
- [What is an AI firewall?](https://aifw.io/what-is-an-ai-firewall): the category explained, plus the questions to ask any vendor

## Documentation

### Getting Started

- [What is AI-FW?](https://aifw.io/docs/getting-started/what-is-aifw): An overview of the AI-FW gateway, what it does, how it fits into your stack, and why it is fail-closed by design.
- [Quick start](https://aifw.io/docs/getting-started/quick-start): Get an AI-FW gateway running in minutes, start the service, configure a model, and inspect your first prompt.

### Guides

- [Prompt & response guardrails](https://aifw.io/docs/guides/prompt-response-guardrails): How AI-FW inspects every prompt and response, built-in rules, custom rules, evaluation order, and rule actions.
- [Model routing & registry](https://aifw.io/docs/guides/model-routing): How AI-FW decides which model handles a request, the model inventory, default model and backend, strict mode, and conditional routing rules.
- [Semantic intent analysis](https://aifw.io/docs/guides/semantic-intent-analysis): Judge the meaning of AI traffic, not just its text, natural-language policies, block and flag thresholds, and three scoring engines.
- [Identity & access](https://aifw.io/docs/guides/identity-access): Authentication modes, API keys, key precedence, streaming modes, mTLS, Kerberos, OIDC SSO, SCIM, and admin roles.
- [Risk profiles & auto-block](https://aifw.io/docs/guides/risk-profiles): Rolling risk scores for users, agents, and IPs, with automatic blocking, category risk cards, and a metadata-only audit trail.
- [Reliability & caching](https://aifw.io/docs/guides/reliability-caching): Per-model resilience (retries, failover, distribution) and the opt-in completion cache, exact and semantic, with strict tenant isolation.
- [Prompt compression](https://aifw.io/docs/guides/prompt-compression): Cut upstream token spend with semantic-gated prompt compression, rule, aggressive, and LLM tiers that never change the meaning.
- [Claude inference hooks](https://aifw.io/docs/guides/claude-inference-hooks): Act as the AI security server for Anthropic's Inference Hooks - verified, scanned, and machine-actionable verdicts before inference proceeds.
- [Observability & dashboard](https://aifw.io/docs/guides/observability-dashboard): The AI-FW dashboard - traffic stats, latency, guardrail snapshot, 24-hour metrics, and the live Activity view.
- [Audit logs & export](https://aifw.io/docs/guides/audit-logs-export): The metadata-only audit trail - logging policy, retention, audit events, and exporting to your SIEM via pull API or syslog.
- [Admin-issued API keys](https://aifw.io/docs/guides/agent-api-keys): Issue API keys for agent and tool access - hashed storage, immediate revocation, and per-key identity in the audit trail.

### Solutions

- [Block prompt injection in production](https://aifw.io/docs/solutions/block-prompt-injection): How to detect and block prompt injection and jailbreak attempts before they reach a model provider, using rule ordering, semantic scoring and fail-closed inspection.
- [Mask PII before prompts leave your network](https://aifw.io/docs/solutions/mask-pii-before-providers): Detect and mask personal data in prompts before they reach a model provider, while keeping the answer usable and the audit record content-free.
- [Govern MCP tool calls by identity](https://aifw.io/docs/solutions/govern-mcp-tool-calls): Decide which MCP tools an agent may call, with what arguments, and under whose identity, and keep an auditable record of every tool invocation.
- [Find and stop shadow AI usage](https://aifw.io/docs/solutions/stop-shadow-ai): Discover unregistered models and ungoverned clients, then close the gap with a strict model registry, per-identity policy and a record of every attempt.
- [Give agents real identities with mTLS](https://aifw.io/docs/solutions/agent-identities-mtls): Issue certificates to agents through a CSR enrollment flow, then authorize every model call against that identity instead of a shared API key.
- [Cut LLM token costs without a safety hole](https://aifw.io/docs/solutions/cut-token-costs-safely): Reduce token spend with semantic-gated prompt compression and inspection-gated caching, without letting cost controls bypass guardrails.

### Tutorials

- [Connect an OpenAI SDK](https://aifw.io/docs/tutorials/connect-openai-sdk): Point an OpenAI-compatible client at the gateway, endpoint mode for full inspection, proxy mode for convenience.
- [Claude Code, Cursor & MCP tools](https://aifw.io/docs/tutorials/claude-code-cursor-mcp): Route Claude-native clients, Cursor, and MCP tools through the gateway, Anthropic protocol support, facades, and the MCP compliance interface.
- [M365 Copilot admin & agent sync](https://aifw.io/docs/tutorials/m365-copilot-bridge): Manage Microsoft 365 Copilot admin surfaces from AI-FW with app-only auth - agent catalog, agent registry, usage reports, and interaction export.
- [Agent self-enrollment (CSR + mTLS)](https://aifw.io/docs/tutorials/agent-self-enrollment): Walk an AI agent through the full enrollment round-trip, discover, register, request a certificate with a CSR, and authenticate with mTLS.

### How-To

- [Configure models & API keys](https://aifw.io/docs/how-to/configure-models-keys): A recipe for the Model Inventory, add models, set per-model keys, enable them, and understand key precedence.
- [Create rules with AI assistance](https://aifw.io/docs/how-to/create-rules-with-ai): Draft guardrail rules from a plain-language objective, the Rules Manager generates, validates, and lets you review before enforcing.
- [Deploy on Azure Container Apps](https://aifw.io/docs/how-to/deploy-azure): A production-shaped deployment recipe, PostgreSQL, the gateway container, secrets, environment configuration, and health checks.

### API Reference

- [OpenAI-compatible API](https://aifw.io/docs/api-reference/openai-compatible-api): The /v1 endpoints, chat completions, request headers, error codes, streaming, and cache headers.
- [Anthropic Messages API](https://aifw.io/docs/api-reference/anthropic-messages-api): The /v1/messages endpoint, Anthropic-native chat, x-api-key auth, facades, and streaming.
- [A2A agent protocol](https://aifw.io/docs/api-reference/a2a-agent-protocol): The Agent2Agent (A2A) surface, the agent card, registration, task-based certificate operations, MCP, and webhooks.
- [OpenAI-compatible models & endpoints](https://aifw.io/docs/api-reference/openai-compatible-endpoints): 200+ OpenAI-compatible models and their vendor endpoints - Claude, OpenAI, Azure, Grok, Meta Llama, DeepSeek, AWS Bedrock, Qwen, Z.ai, and more.

### Admin Reference

- [Settings reference](https://aifw.io/docs/admin/settings): Every tab of the Settings page - General, Access, Identity, Model, Routing, Guardrails & Inspection, Performance, Audit, Export, Integrations, and Licensing.
- [Model Inventory reference](https://aifw.io/docs/admin/model-inventory): The Model Inventory page and every option: filters, enable/disable, add/edit/delete, protocols, resilience, compression, advanced parameters, groups, and routing rules.
- [Rules Manager reference](https://aifw.io/docs/admin/rules-manager): Built-in rules, custom rules, rule types and actions, per-rule options, priority, and AI-assisted rule creation.
- [Risk Profiles reference](https://aifw.io/docs/admin/risk-profiles): User, agent, and IP risk leaderboards, category risk cards, risk auto-block, and reset actions.
- [Audit Logs reference](https://aifw.io/docs/admin/audit-logs): The transaction log, filters, the Events tab, and page-size settings.
- [Dashboard reference](https://aifw.io/docs/admin/dashboard): Every card and control on the AI-FW Dashboard - traffic stats, latency, guardrail snapshot, 24-hour metrics, and charts.
- [M365 Copilot admin reference](https://aifw.io/docs/admin/m365-copilot): The M365 Copilot page - agent catalog, agent registry, usage analytics, and interaction export with app-only authentication.
- [Users reference](https://aifw.io/docs/admin/users): Local users, roles, passwords, SSO, SCIM provisioning, and user groups.
- [Agent API keys reference](https://aifw.io/docs/admin/agent-api-keys): The Agent API Keys page - add, generate, label, and revoke keys with hashed storage and per-key identity.
- [Agents reference](https://aifw.io/docs/admin/agents): The agent registry admin page - onboarding modes, identity proof, approval, groups and tags, webhooks, and deboarding.
- [CA integrations reference](https://aifw.io/docs/admin/ca-integrations): SCEP and ACME enrollment, the central CA trust store, and server-certificate enrollment.
- [Agent Trust reference](https://aifw.io/docs/admin/agent-trust): The Agent Trust dashboard - agent inventory, approvals, tasks, and trust settings.

### Community Edition

- [Community Edition license](https://aifw.io/docs/community-edition/license): The AI-FW Community Edition is free with a published monthly allowance of 100,000,000 tokens, enforced by the gateway against a machine-readable license document.

## Notes

- Model IDs and vendor endpoints are listed at https://aifw.io/docs/api-reference/openai-compatible-endpoints
- Full documentation text for retrieval is available at https://aifw.io/llms-full.txt
- Documentation source is mirrored at https://github.com/securetron-gh/aifw