Case StudiesBulwark
Authentication & Agent Governance

Bulwark

Open-source governance layer for AI agents

AI agents are powerful but ungoverned. They can access any tool, leak any credential, and leave no audit trail. Bulwark sits between AI agents and external tools — enforcing policies, managing credentials, inspecting content, and maintaining a complete, tamper-evident audit trail. One policy governs all your agents.

487
Unit tests
10
Rust crates
13
Detection patterns
3
Integration modes
The Challenge

AI agents operate
without guardrails

When AI agents interact with payment processors, compliance systems, privacy-sensitive APIs, and regulated infrastructure, the stakes are existential. A single leaked credential or unauthorized API call can trigger regulatory violations, data breaches, and financial loss.

No credential isolation

Agents receive raw API keys and tokens, with no boundary between access and exposure.

No policy enforcement

Every agent has implicit access to every tool. No per-agent, per-session, or per-operator controls.

No content inspection

Sensitive data flows through agent pipelines unscanned — PII, secrets, and injection attacks pass unchecked.

No audit trail

When something goes wrong, there is no verifiable record of what happened, when, or why.

Capabilities

Six layers of governance

Every request passes through a multi-stage pipeline. Each layer enforces a different security boundary.

Policy Enforcement

YAML-based rules control which tools agents can use. Glob patterns, scope-based precedence (global/operator/session), priority ordering, and hot-reload without restart.

Credential Management

Agents never see real secrets. Bulwark injects credentials at the last mile before tool invocation. Encrypted at rest using age encryption.

Content Inspection

13 built-in detection patterns scan for AWS keys, GitHub tokens, private keys, PII, and prompt injection. Automatic blocking or redaction.

Audit Logging

Every action recorded in a tamper-evident SQLite database with Blake3 hash chains. Real-time tailing, search, export, and cryptographic verification.

Rate Limiting

Token-bucket rate limits per session, operator, tool, or globally. Cost tracking with budget enforcement to prevent runaway spending.

MCP-Native

Works as an MCP gateway (stdio or HTTP) or HTTP forward proxy. Governance metadata attached to every tool call response.

Architecture

Request pipeline

Every agent interaction flows through a deterministic, auditable pipeline before reaching upstream tools.

Agent Request
Claude, Codex, OpenClaw
Session Validation
Identity & TTL
Content Inspection
Secrets, PII, Injection
Policy Evaluation
YAML rules engine
Credential Injection
age-encrypted vault
Upstream Tool
API / MCP Server

Response path mirrors the pipeline in reverse — content inspection and audit logging on every response.

Integration

Three modes, any agent

Bulwark adapts to your agent architecture. Local development, remote multi-agent systems, or legacy HTTP clients — one governance layer handles all.

ModeTransportUse Case
MCP Gateway (stdio)JSON-RPCLocal agents — Claude Code, OpenClaw
MCP Gateway (HTTP)Streamable HTTPRemote agents, multi-agent setups
HTTP ProxyHTTP/HTTPS + TLS MITMAny HTTP client
Under the hood

Built in Rust, 10 crates

A modular Rust workspace where each security boundary is its own crate — independently testable, auditable, and replaceable.

cli/
CLI and subcommands
proxy/
HTTP/HTTPS forward proxy with TLS MITM
mcp/
MCP protocol gateway and routing
config/
Configuration parsing and schemas
policy/
Rule engine with YAML evaluation
vault/
Encrypted credential storage and sessions
audit/
Tamper-evident logging system
inspect/
Pattern matching and content scanning
ratelimit/
Token-bucket rate limiter
common/
Shared types and error definitions
Our Approach

How Honto
engineered Bulwark

Bulwark represents Honto's philosophy in practice: production-grade AI infrastructure built with engineering discipline. Every design decision prioritizes security, auditability, and operational reliability.

01

Threat Modeling

Mapped every attack surface where AI agents interact with sensitive systems — payments, compliance, privacy, and credentials.

02

Zero-Trust Architecture

Designed a pipeline where agents never directly access secrets or tools. Every interaction is mediated, inspected, and logged.

03

Modular Rust Workspace

10 independent crates, each owning a security boundary. 487 unit tests ensure correctness at every layer.

04

Open-Source Release

Apache 2.0 licensed. Transparent, auditable, and community-driven — because security tools must be verifiable.

Need agent governance
for your organization?

Bulwark is open-source and ready to deploy. For enterprise deployments, custom policy design, or integration support — Honto's engineering team is here to help.