Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@ForgeWireLabs
ForgeWireLabs
Follow

Jeremy Shows ForgeWireLabs

Building local-first AI infrastructure, agent tooling, and technical learning systems.
  • ForgeWire Labs
  • Louisiana

Highlights

  • Pro

Block or report ForgeWireLabs

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 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
ForgeWireLabs /README.md

ForgeWire Labs — inspectable agent infrastructure, distributed execution, practical AI

Jeremy Shows

Founder & Principal Engineer, ForgeWire Labs

I build inspectable agent infrastructure, distributed execution systems, and practical AI software that stays useful under real-world constraints — when models are fallible, hardware is limited, infrastructure shifts, and real people depend on the result.

Former mechanic, race-car builder, fabricator, IT professional, and small-business owner, now building distributed systems and applied AI infrastructure. I see AI systems as machinery — assemblies of components with interfaces, tolerances, feedback paths, and failure modes — and I hold them to that standard: a convincing demo isn't enough; the system has to keep working when a part fails, the hardware is constrained, the requirements change, or an automated process exceeds its authority.

Build it. Test it under failure. Preserve the evidence. Understand its limits. Then decide whether it's useful.


Flagship Work

🧵 ForgeWire Fabric · Available — Alpha

release license

A self-hosted control plane for authenticated remote task execution — move work across machines while keeping authority, policy, provenance, and execution history explicit. Signed dispatch, scope-bound capability tokens, policy-gated runners, structured task events, and a federated overlay, with behavioral parity between Python and Rust.

agentic-ai · remote-execution · mcp · distributed-systems · rust

forgewire-fabric-cli doctor — a healthy hub on an rqlite-backed cluster

📐 Architecture diagram lives in the Fabric README.

📜 RepoPact · Available — Early Development

license

A repository-native operating system for durable work between humans and coding agents. It keeps authority, intent, work state, evidence, decisions, and project history inside the repository instead of letting them vanish with each agent session.

intent → scoped authority → work item → implementation → evidence → audit → history

coding-agents · repository-governance · agents-md · developer-tools · ai-governance

RepoPact core loop over a filesystem state machine

🎓 SkillForge Academy · Downloadable Product

release

An offline-first certification learning and exam-prep desktop app, starting with CompTIA A+. Original practice questions, performance-based questions, mock exams, spaced-repetition flashcards, readiness analytics, and local progress storage. Built with Tauri + Rust + React.

comptia · exam-prep · tauri · rust · react · offline-first

SkillForge Academy — Study Command Center


The Larger System: ForgeWire

The flagships above are public pieces of a larger, privately developed system. ForgeWire is a modular architecture for coordinating models, agents, tools, memory, knowledge, compute, and distributed execution. Its engineering thesis:

Agentic systems are systems first and models second.

A capable model can still be part of an unreliable system. ForgeWire focuses on the infrastructure around models: graceful degradation, explicit ownership, behavioral parity, audit trails, recoverable execution, bounded authority, and replaceable components. The public overview documents its direction and release status without presenting unfinished work as a product.


How I Build

  • Systems before components. A working part is not a working system. I design for the seams — failure modes, authority boundaries, and recovery — first.
  • Evidence over demos. Releases ship with documentation, tests, security context, known limitations, and architecture so they can be evaluated seriously.
  • Parity and portability. Acceleration paths get portable reference implementations; the system isn't pinned to one language, model provider, database, or cloud.
  • Research is gated. Speculative ideas move through baseline comparison, controlled evaluation, and failure analysis before they touch production — and a better question is a valid result.

Stack: Rust · Python · TypeScript · React · Tauri · GTK · SQLite · rqlite · PostgreSQL · PowerShell · GitHub Actions


Lineage & Archive

The current work descends from years of building, failure, and reconstruction:

SCOUT → SCOUT-2 → ATLAS → PhrenForge → ForgeWire

  • SCOUT-2Historical. Multi-agent assistant platform; a record of the experiments and architectural limits that led to ForgeWire.
  • Earlier public projects (SCOUT, Feed-Portal, MED.I.C.) are archived and kept for history — not current work.

Independent · founder-led · evidence-driven. Reach me through the repositories above, or open an issue/security advisory on the relevant project.

Pinned Loading

  1. forgewire-fabric forgewire-fabric Public

    Self-hosted control plane for authenticated remote task execution: signed dispatch, scope-bound capability tokens, policy-gated runners, and a federated overlay. Python/Rust parity. Apache-2.0.

    Python

  2. repopact repopact Public

    Repository-native operating system for durable work between humans and coding agents: scoped authority, work items, evidence, audits, and project history kept inside the repo.

    Python

  3. ForgeWire-Overview ForgeWire-Overview Public

    Public overview of ForgeWire — a modular system for coordinating models, agents, tools, memory, compute, and distributed execution. Agentic systems are systems first and models second.

  4. skillforge-academy skillforge-academy Public

    Offline-first certification learning and exam-prep desktop app, starting with CompTIA A+.

    TypeScript

  5. SCOUT-2 SCOUT-2 Public archive

    Second generation SCOUT (Scalable Cognitive Operations Unified Team)

    Python 52 3

AltStyle によって変換されたページ (->オリジナル) /