Skip to content
View JustinJLeopard's full-sized avatar

Block or report JustinJLeopard

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
JustinJLeopard/README.md

Justin Leopard

Software engineer building agent infrastructure: orchestration layers, safe local execution, typed memory, routing policy, evaluation, and the operator surfaces that make autonomous runs accountable.

I care about the unglamorous parts of agent systems: the queue, trace, sandbox, review gate, memory record, cost ledger, and handoff. If those pieces are weak, the model looks impressive right up until it repeats the same expensive mistake.

Current Focus

Surface What it proves
JustAi Control plane for multi-agent engineering work: intent, plan, execute, review, synthesize.
JustAi demo Browser-visible mission control for task state, memory, trajectories, agents, cost, latency, and review quality.
safe-mini Safe-by-construction local execution for mini-swe-agent-style bash-action loops.
route-mini Multi-provider LLM routing with fallback, budget, latency targets, and decision logging.
memory-mini Durable namespaced memory with upsert-first semantics, soft delete, cleanup, and optional embeddings.
lab-mini Repeatable data-science lab loop: load, profile, analyze, claim, report.

Operating Thesis

Agents get useful when the system around them is engineered like production infrastructure.

  • Sandbox the boundary, not the capability. Give the agent room to solve the task inside a scoped worktree, scrubbed environment, guarded path, and recorded trajectory.
  • Trajectories beat vibes. Every action should leave a replayable trace that can teach the next run.
  • Routing is policy. Stronger models are an escalation decision, not a default reflex.
  • Memory has lifecycle. Durable context needs namespacing, upsert, retention, and cleanup rather than chat-history luck.
  • Evaluation should change behavior. A score that does not route, block, or teach the next run is mostly decoration.

Public Proof Path

Systems I Track Closely

I keep forks and notes around projects that shape the work:

The goal is not to collect logos; it is to keep the public graph close to the ideas I am building against.

Background

  • US Navy veteran, aircraft maintenance. The useful lesson was not ceremony; it was operational seriousness.
  • Full-stack engineer across Python, TypeScript, React, Node, SQL, local Linux/WSL, and browser-visible product surfaces.
  • Building Delegate & Orchestrate around practical agent systems that can be inspected, tested, and improved.

Contact

Popular repositories Loading

  1. ai-powered-travel-planning-app ai-powered-travel-planning-app Public

    AI-Powered Travel Planner — React Native/Expo app with intelligent itinerary generation

    TypeScript 1

  2. JustinJLeopard JustinJLeopard Public

    GitHub profile README for Justin Leopard: agent infrastructure, safe execution, routing policy, typed memory, and evaluation.

  3. CarCar CarCar Public archive

    JavaScript

  4. iRentals iRentals Public archive

    JavaScript

  5. Wardrobify Wardrobify Public archive

    Python

  6. LeetCode-Problems-Solved LeetCode-Problems-Solved Public archive

    Collection of LeetCode questions to ace the coding interview! - Created using [LeetHub v2](https://github.com/arunbhardwaj/LeetHub-2.0)

    Python