broomva.tech

Reliability engineering for complex systems.

  • Pages
  • Home
  • Projects
  • Writing
  • Notes
  • Tools
  • Chat
  • Prompts
  • Link Hub
  • Social
  • GitHub
  • LinkedIn
  • X

Building systems
that last

Lead AI at Stimulus. Databricks expert. Rust Agent OS builder. From scalable data pipelines to autonomous agent infrastructure — reliability engineering across software, body, and craft.

GitHubLinkedInXLink hub

AI can make mistakes. Please check important information.

Scroll

Get Started

Install

One command installs the Broomva CLI, the broomva.tech skill, and the full bstack (24 agent skills across 7 layers).

cargo install broomvacrates.ioSource

Agent OS Stack

The stack

10 Rust crates, 24 agent skills, 500+ tests. A control-theory-native ecosystem for autonomous software development.

01

bstack

Agent skills platform

24 curated agent skills across 7 layers — install the full Broomva development workflow with one command.

02

Symphony

Orchestration

Dispatch, lifecycle, and hook management for coding agents across issue trackers.

03

Control Kernel

Governance & safety

Typed setpoints, safety shields, and multi-rate control loops that keep agents bounded.

04

Life

Agent OS monorepo

Arcan runtime, Lago persistence, Vigil observability, Praxis tool execution, Haima finance, and Spaces networking — unified in one Cargo workspace.

05

Autoany

Recursive improvement

Evaluator-Governed Recursive Improvement (EGRI) — safe, measurable, rollback-capable optimization loops.

06

aiOS

Kernel contract

The canonical type system — state vectors, event taxonomy, trait interfaces, and operating modes for all Agent OS crates.

Latest Writing

Read all

The Agentic Control Loop: Re-Engineering LLMs as Supervisory Controllers

Why treating LLMs as supervisory controllers — not autonomous agents — produces systems that scale, recover from failure, and improve over time.

March 26, 2026 · 9 min read

BitNet: 1-Bit LLMs for Agentic Edge Inference

Microsoft's BitNet proves that ternary-weight models can match full-precision performance while running on any CPU. A hands-on tutorial with benchmarks, scaling projections, and implications for building agents that run anywhere.

March 26, 2026 · 11 min read

Autonomous Development Workflows: From Terminal to Pull Request

A practical guide to wiring persistent agent sessions, parallel task execution, remote chat interfaces, and self-improving PR feedback loops using the bstack control harness.

March 25, 2026 · 14 min read

Recent Notes

Browse notes

Autonomy is governance

The degree of autonomy you can grant an agent is directly proportional to the quality of your governance infrastructure.

March 14, 2026

Harness over prompting

Prompt quality matters, but harness quality is what keeps agent outputs reliable once stakes increase.

February 17, 2026

A release rhythm that works

One weekly long-form post plus short daily notes creates enough surface area for learning, distribution, and iteration.

February 14, 2026