Skip to content
View jmanhype's full-sized avatar
🚢
Shipping
🚢
Shipping

Block or report jmanhype

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
jmanhype/README.md

Straughter Guthrie

Systems engineer. Elixir/OTP, Erlang, Python.

Building agent infrastructure that treats LLM orchestration as a distributed systems problem, not a prompt engineering problem.

Current work

VAOS (Viable Autonomous Operating System) — an Elixir/OTP framework for epistemic agent orchestration. Three libraries, one runtime:

Library What it does Size Tests
vas-swarm Agent orchestrator. Signal classification, 3-tier routing, 48 tools, 18 LLM providers. 92K lines Elixir + 20K Rust ~3,320
vaos-ledger Epistemic engine. Claims, evidence, attacks tracked with Expected Information Gain scoring. 6,718 lines 208
vaos-knowledge Triple store. ETS-backed, SPARQL subset, 4 OWL 2 RL rules. 1,095 lines 108

The core idea: agents should reason about what they don't know (epistemic governance) rather than just executing tool chains. The investigate tool uses adversarial dual-prompt architecture with citation verification — it argues against its own findings before reporting them.

vaos.sh — SaaS interface to the VAOS runtime.

Selected repos

Repo Language What
vggt-mps Python Apple Silicon (MPS) port of Meta's VGGT visual geometry grounded transformer
MCPhoenix Elixir Model Context Protocol gateway for Phoenix applications
wf-substrate Erlang 43 workflow patterns compiled into native OTP control structures
speckit Shell Spec-driven development toolkit
cloudflare_durable_ex Elixir Cloudflare Durable Objects client for Elixir
ace-playbook Python Adaptive Code Evolution — self-modifying agent architecture

Infrastructure

4-node Tailscale mesh: Mac Mini (gateway, BEAM runtime), MacBook Pro (development), Linux GPU server (3090, training/inference), Windows workstation (Draco, orchestration). OpenClaw for cross-node agent dispatch.

Organizational theory

The architecture draws from Stafford Beer's Viable System Model (1972) — recursive autonomy with meta-systemic coordination. Each agent subsystem mirrors VSM's System 1-5 structure: operations, coordination, optimization, intelligence, policy.

References: Beer's Brain of the Firm, Ashby's Law of Requisite Variety, Wiener's cybernetic feedback loops. See the viable-systems org for the upstream VSM implementation.

Pinned Loading

  1. MCPhoenix MCPhoenix Public

    A simplified implementation of the Model Context Protocol (MCP) server using Elixir's Phoenix Framework.

    Elixir 67 6

  2. vggt-mps vggt-mps Public

    VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

    Python 86 8

  3. ace-playbook ace-playbook Public

    Self-improving LLM system using Generator-Reflector-Curator pattern for online learning from execution feedback

    Python 28 6

  4. wf-substrate wf-substrate Public

    Pure Erlang/OTP workflow substrate. 43 workflow patterns compiled into native executable control structures. 1182 LoC.

    Erlang 1 1

  5. vaos-knowledge vaos-knowledge Public

    ETS-backed triple store for Elixir. SPARQL subset (5 operations), 4 OWL 2 RL rules, 3-way indexing. 11 modules, 1095 lines, 108 tests.

    Elixir

  6. vaos-ledger vaos-ledger Public

    Epistemic governance framework for Elixir. Claims, evidence, EIG scoring, 7-layer adversarial defense, experiment loops. 18 modules, 6718 lines, 241 tests.

    Elixir