Skip to content
View PIsberg's full-sized avatar
🤖
🤖

Block or report PIsberg

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
PIsberg/README.md
T-800 heads-up display. PETER ISBERG. Guardrails for the machines that write the code. Power cell: Java 26. Location: Gothenburg, SE. Directive: no fate but what we compile.

Developer by profession. Vibecoding after hours.

Website Email Followers Profile views

>> FIELD_MANUAL

Cover of Vibe Architecture, the book on designing, scaling, and guardrailing large-scale systems in the age of AI orchestration

Vibe coding gives you speed. Vibe Architecture gives you scale.

When syntax is free, structure is your only asset. The book on designing, scaling, and guardrailing large-scale systems in the age of AI orchestration.

Buy Vibe Architecture on Amazon

>> MISSION_PARAMETERS

  • ACTIVE Building vibetags, Java annotations that tell Claude, Cursor and Codex which code they are not allowed to touch
  • LAB Making concurrency bugs reproducible instead of lucky with async-test-lib
  • SHIELD Running a local prompt injection firewall between my tools and every LLM API
  • UPLINK Ask me about Java, AI guardrails, static analysis, MCP servers, and why a green test suite is not proof
  • COMMS Reach me at isberg.peter@gmail.com or deversity.se

>> WEAPONS_SYSTEMS

PRIMARY Java Spring Boot Gradle Maven
SIDEARMS Rust TypeScript Go Python
SUPPORT Docker GitHub Actions Claude Model Context Protocol Linux IntelliJ IDEA

>> PRIMARY_TARGETS

RepoStarsWhat it does
vibetags stars Java annotations as AI guardrails. Mark the code an agent must not rewrite, and it stops rewriting it.
async-test-lib stars Forces concurrency bugs to happen using synchronized barriers, then names the one that fired.
llm-fw stars Local prompt injection firewall. Malicious prompts are blocked and logged, clean ones pass through.
skill3 stars Relearns a technical skill for an agent, anchored to a target model cutoff, and vets the result.
codekoll stars Static analyzer for Java that finds the bugs which compile perfectly and detonate in production.
codekarta stars Parses Java source and emits SVG maps: call graphs, exception flow, state machines.
axiom stars The codebase as a live queryable graph, so an agent can see what it just broke.
blindbean stars Homomorphic encryption hidden behind ordinary Java objects and annotations.
ghost-mcp stars MCP server that exposes OS level UI automation to AI clients.

>> COMBAT_TELEMETRY

Commit streak Languages by repo Languages by commit Profile stats

Come with me if you want to ship.

A thumbs-up slowly sinking into molten steel. I will be back.

Pinned Loading

  1. async-test-lib async-test-lib Public

    @AsyncTest (async-test-lib) is an enterprise-grade test framework that makes concurrency bugs reproducible and detectable. Rather than hoping random thread scheduling will expose bugs, async-test f…

    Java 8 1

  2. vibetags vibetags Public

    VibeTags is a Java annotation processor that acts as AI guardrails for code generation tools like Cursor, Claude, Gemini, and Codex CLI. It allows developers to control AI behavior through simple a…

    Java 22 4

  3. bashful-cli bashful-cli Public

    Bashful gives your CLI tools a REST API — no code required

    TypeScript 5 1

  4. blindbean blindbean Public

    BlindBean is a developer-first Java 26 library that makes Homomorphic Encryption (HE) invisible to the end user. It allows you to perform secure, private arithmetic on encrypted data using standard…

    Java 4 1

  5. llm-fw llm-fw Public

    A local prompt injection firewall that intercepts traffic between your tools and every major LLM API before it leaves your machine. Malicious prompts are blocked and logged; clean ones are forwarde…

    TypeScript 5 1

  6. skill3 skill3 Public

    Skill3 is a lightweight Java CLI that relearns a technical skill for an AI agent. It discovers documentation sources, scores them for authority and freshness (anchored to a target model's knowledge…

    Java 6 1