Skip to content
View electricwolfemarshmallowhypertext's full-sized avatar
🦄
🦄

Block or report electricwolfemarshmallowhypertext

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

Tionne Smith

Creative Technologist | AI Engineer 🫧 Multidisciplinary Nerd

I research, design, build, test, and ship across applied AI, backend systems, web, digital products, and visual design.

My work spans AI runtimes, memory/context systems, governance and verification, front-end architecture, back-end architecture, digital experiences, brand systems, and print/digital design.

Open source

Microsoft Agent Governance Toolkit

AgentMesh audit integrity
Fixed audit export completeness, Merkle-root consistency, failed-append atomicity, and concurrent reader consistency.
→ #4096 · #4135 · #4138 · #4140

EU AI Act compliance
Updated applicability guidance for Regulation (EU) 2026/1744, including revised high-risk system timelines.
→ #3719

Hypervisor API
Made the session API synchronous where appropriate and tightened Saga failure handling and regression coverage.
→ #3645

agt verify runtime evidence
Extended verification toward evidence-backed runtime posture with safer parsing, path validation, and file-size protections.
→ #969

Nanocoder

Provider initialization reliability
Fixed a post-configuration state bug where a stale provider preference caused initialization to fail after rewriting the active config; restored successful provider resolution without changing the explicit-provider contract.
→ Merged PR #477

Selected work

A context-governance runtime for AI agents that makes memory, policies, evaluations, and execution receipts executable, validated, versioned, and auditable.

Replayable causal audit traces for high-risk financial AI decisions.

Research

I publish and test ideas around stateful AI, persistent identity, context architecture, governance, agent behavior, and human–AI interaction.

Recent work includes graph-structured memory for long-horizon LLM context and experiments around agent behavior under different task and deadline conditions.

AI Mental Health Collective

I collaborate with clinicians on research and public-facing resources exploring AI and mental health through AIMHC.

Creative + technical practice

  • Applied AI and agent runtimes
  • Back-end architecture and API integration
  • Front-end architecture and production web
  • Digital product and UI/UX implementation
  • Brand systems, art direction, and creative direction
  • Print and digital design
  • Runtime verification, evals, and governance
  • Memory and context systems

Links

Personal · Coexi · Design · LinkedIn · ResearchGate · ORCID

Pinned Loading

  1. agentmd-runtime agentmd-runtime Public

    AgentMD is a context governance runtime for AI agents. It makes AGENTS.md, skills, memory, policies, evals, and execution receipts executable, validated, versioned, and auditable.

    Python 1

  2. c-dag c-dag Public

    C-DAG: replayable causal audit traces for high-risk financial AI decisions.

    Python 1