broomva.tech

Reliability engineering for complex systems.

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

Start here

I build autonomous software systems: a Rust Agent OS stack with orchestration, governance, and kernel layers that turn LLM capability into reliable, controllable workflows. This page is the shortest route to my best work.

What I build

A Rust-native Agent OS stack: Symphony for orchestration, a control metalayer for governance, and aiOS as the kernel. Plus harness engineering patterns that make agents reliable in production.

Why it matters

Most failures are not model failures. They are harness failures. I focus on the systems-level primitives that make agents controllable, observable, and useful under real constraints.

Best projects

All projects

Life

Active

The Agent OS monorepo — 8 Rust workspaces, 50+ crates, 136K lines, 1045 tests. Arcan, Lago, aiOS, Autonomic, Haima, Praxis, Vigil, and Spaces unified under one roof.

March 15, 2026

Autoany

Active

Evaluator-Governed Recursive Improvement (EGRI) — turn ambiguous goals into safe, measurable, rollback-capable optimization loops over any mutable artifact.

March 12, 2026

Symphony

Active

Rust-native orchestration runtime for composable agent workflows with deterministic scheduling and fault isolation.

March 10, 2026

Best writing

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

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

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

Recent 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.

Where to follow

Link hubGitHubLinkedInX

February 17, 2026