jugeni@agent — ~/infra
agent infrastructure that carries its receipts
whoami

jugeni

Typed memory, decision lifecycle, process threads, write-time invariants. The layer between a model and its consequences. Every claim carries the query it came from.

01

What jugeni is

cat README

Open-source agent infrastructure for the parts most AI products skip until something breaks in production. Not a chatbot. The bookkeeping underneath one: what it decided, what it must not forget, what it refused, and on what evidence.

memory

Source-attributed atoms

Per-atom provenance, not flat conversation history. Every fact knows where it came from and when it goes stale.

decisions

Explicit lifecycle

Proposed → accepted → locked. Defended locks enforced at admission, not silently overwritten at retrieval.

threads

Process continuity

Work threads that survive across sessions: state, next step, and the trail that got there.

invariants

Write-time gates

Reject confident-but-unverified output before it propagates. Refusal is a first-class result, not a failure.

02

agile4ai

the working frame

Five primitives I keep coming back to across every engagement. The parts that read as overhead until the day they are the only reason you can answer for what your system did.

More on it post by post → dev.to/jugeni

03

Receipts

public work, every number carries its query
04

Who runs this

./whois

Mike Czerwinski. Twenty years building software: eleven writing code, nine running delivery across banks (BNP Paribas, Citi), automotive R&D, and travel-tech. Now building and auditing AI agent stacks: memory, decisions, locks, and the verification layer between a model and its consequences. Based in Poland, working in English and Polish.

Three product lanes, one obsession: making opaque AI legible enough to ship without lying to the user. Content provenance (sentixx.net), quantitative trading research (ziom), custom personal AI (jessi).

05

Contact

reply to the ones where the gap is engineering, not vibes