Euraika-Labs
A European AI research lab building sovereign-by-default systems.
Euraika-Labs is where Euraika writes about what it builds. The systems — Aegis, Hermes, Vane, and the Pan family of open-source projects — are for organisations whose data, compliance posture, or jurisdiction makes US-cloud LLM stacks a non-starter. The writing lives here.
Recent writing
All postsEngineering · 2026-09-16
A redactable hash chain, as a design pattern
An audit log that is append-only, tamper-evident, and redactable looks contradictory at first reading. The contradiction dissolves when you separate the manifest from the content. A short note on the pattern, independent of any specific application.
Engineering · 2026-08-19
How Pan gates dangerous tool calls
Pan never takes a destructive or external-network action without an explicit approval. The mechanism is smaller than it sounds — an in-memory store, a three-level classifier, and a blocking goroutine. Here is what the gating layer actually looks like.
Engineering · 2026-08-05
OpenTelemetry traces when most of the latency is in someone else's GPU
A request that spends fifty milliseconds in our gateway and several seconds inside a provider's inference is hard to instrument with the usual OpenTelemetry patterns. Here is the small set of conventions that, after some iteration, produce a trace worth reading.
Open source
All projectsCode is the proof. Everything we publish lives at github.com/Euraika-Labs.
Stable · Go + TypeScript
Pan
Self-hosted AI workspace. Desktop agent with full PC control, web UI, native shell, 3D engine — all on your hardware.
Beta · Python
Hermes-Agent
The agent that grows with you. Long-running, memory-aware, schedulable.
Stable · Python
ai-slopcheck
Deterministic scanner for AI-style code failures. 72 rules.
pip install ai-slopcheck.