Skip to content
Project

Architecture and Engineering

InnerWarden has a small, legible architecture. The free Community guard is open source (Apache-2.0, at inner-warden); the paid stack (Pro and Enterprise) is source-available: a deterministic sensor, an interpretive agent, and a CLI, each doing one job. These posts are how it is built and how to build on it.

8 articles in this hub

How InnerWarden approaches this

The sensor stays deterministic with no LLM in the hot path; the agent is the only layer allowed to reason and call out. That split is deliberate, it keeps detection trustworthy and response auditable. These posts cover the design decisions, the module boundaries, and how to extend it.

Articles in this hub

Announcement

Three Months of InnerWarden, July to October

Three months of InnerWarden, an AI agent security startup: 70 stable releases, Community 1.0.0 to 1.5.5, release attestation, and what comes next.

4 min read
Read
Origin Story

Why We Built InnerWarden

A first-person account of why we built InnerWarden: the pain that pushed us out of MDR contracts and DIY Wazuh stacks, and what we wanted a security agent on our own hosts to do.

5 min read
Read
Engineering

Why We Switched to jemalloc (and How glibc malloc Was Eating 1GB RAM)

The story of how glibc malloc fragmentation caused our Rust daemon to grow to 1.3GB under bot traffic, and how jemalloc fixed it with 3 lines of code.

7 min read
Read
eBPF

Aya, eBPF and Rust: Production Lessons

Lessons from shipping 74 eBPF programs (defined in source) across tracepoints, kprobes, LSM and XDP: #![no_std], CO-RE/BTF, ring buffers, verifier failures, debugging.

10 min read
Read
Validation

We Ran MITRE Caldera Against Our Own Product

5 rounds of adversary emulation with Caldera v5.3.0. From 36% detection to 67% of testable techniques. The argv truncation fix, 15+ false positive cleanups, and why mapped is not detected.

14 min read
Read
Velocity

Ship Now, Secure Now: You Can't Pick One Anymore

AI codegen made shipping faster. Attacker tooling made exploitation faster. The old ship-first-harden-later loop is dead. The case for security that defaults on.

6 min read
Read
Opinion

Ship Auto-Block in Observe Mode

A security tool that ships with auto-block on locks operators out and gets uninstalled. The case for shipping in observe mode: detect everything, log everything, escalate on confidence.

7 min read
Read
Architecture

Agent vs Agentless Monitoring: When Each Wins

Network IDS vs cloud APIs vs eBPF on host. Encrypted traffic, runtime visibility, fleet-scale config audit. When you'd choose each, not a settled debate.

7 min read
Read