Projects

Systems with operational weight.

This is a public-safe map of what I am actively building: MSP command planes, CWM execution patterns, billing/runtime proof loops, memory-backed agent workflows, and API tooling that works against real platforms.

Evidence Basis

Not scraped from a resume.

Local project surfaceThe current workstation includes the local-agent-tooling control plane, AlgaPSA/vArida billing lanes, Portainer deployment work, stakeholder renderers, and MSP operational artifacts.

Work accountingCWM and timesheet artifacts show member 346 time-entry reconciliation, internal development backfill review, and status-gated posting behavior.

Delivery governanceGitHub Project 4, issue hierarchy, control-validate checks, proof comments, and audit-project output are part of the operating model.

MSP Operations Active

MSP Command Plane

Eight-platform MSP operations tooling across PSA, RMM, Microsoft 365, documentation, security, remote access, vCloud, and billing workflows.

Problem: Service work spans tickets, time entries, RMM state, Microsoft Graph evidence, project records, stakeholder artifacts, and approval gates.
System: A CLI and skill-based command plane that turns live platform state into reviewed actions, CWM task structures, GitHub Project 4 governance, and reusable handoff artifacts.
Proof: CWM ticket-control-plane registers, time-entry reconciliation artifacts, control-validate gates, live runtime checks, and public-safe session-harvest maps.

Evidence Signals

Eight TypeScript CLI packages and 250+ orchestration skills are represented in the local local-agent-tooling repo.
CWM tickets are treated as execution surfaces with tasks, notes, status, schedules, documents, and time entries reconciled after writes.
Internal development effort was reconciled against member 346 time entries, GitHub Project 4, git activity, browser history, and Codex session traces.

TypeScript Python GitHub Projects ConnectWise Microsoft Graph

Financial Agent Systems Research / Paper Trading

Financial-Agent Paper Runtime

Research infrastructure for paper-trading decisions, risk gates, reconciliation, forecasting, and runtime evidence.

Problem: Financial-agent systems need explicit safety boundaries, reproducible runs, and evidence before any operator trusts the output.
System: Paper-runtime components for decision policy, ledger checks, broker status reads, forecast scoring, and delivery gates.
Proof: Test suite results, paper-run logs, reconciliation checks, and configuration gates.

Evidence Signals

Research framing stays paper/runtime only, with safety language separated from operational MSP claims.
Runtime outputs are treated as evidence bundles rather than opaque recommendations.
Reconciliation and broker-state checks are part of the operating model before any downstream decision.

Python TypeScript Alpaca Paper Forecasting Risk Gates

TradingAgents-FinBots

Agent Runtime Active

Agent Memory and Runtime Infrastructure

Local agent runtime, memory, recall, and skill infrastructure that preserves operator context across interrupted sessions.

Problem: Agent work loses value when decisions, proof locations, tool state, and blockers disappear between sessions.
System: Qdrant-backed mem0 recall, checkpoint/replay helpers, session-harvest maps, repo-native skills, and explicit handoff prompts.
Proof: Hermes memory search results, Qdrant checkpoint guidance, session-log harvest artifacts, and validation notes tied back to GitHub control-plane items.

Evidence Signals

Local mem0 recovered Project 4 and local-agent-tooling effort history during this portfolio pass.
Session harvest maps convert raw Codex logs into skills, docs, CLI gaps, and Project 4 issue graphs.
Checkpoint wrappers are used when direct Qdrant writes are unreliable from sandboxed agents.

Python Qdrant mem0 Docker MCP

hermes-mem0

Operator Interfaces Active

AlgaPSA and Operator Interfaces

Deployed platform and dashboard work for billing review, SPLA, client-scoped operations, stakeholder review, and demo-safe proof capture.

Problem: Operators and stakeholders need to see what the platform actually does, not infer readiness from backend logs.
System: AlgaPSA/vArida demo lanes, billing sync previews, SPLA readiness, UI route audits, stakeholder briefing renderers, and screenshot-backed validation.
Proof: UIUX gap analysis, stakeholder YAML-to-HTML/XLSX and YAML-to-PPTX pipelines, runtime proof captures, and GitHub Project 4 issue gates.

Evidence Signals

The repo explicitly gates May 10 readiness on live AlgaPSA behavior, not backend proof alone.
Stakeholder artifacts are generated from structured sources and verified instead of hand-built one-offs.
UIUX analysis ties billing, tickets, devices, reports, and notifications into a client-scoped operating model.

TypeScript React NestJS ConnectWise ITGlue

MCP and API Tooling Active

MCP and Platform API Toolchain

API adapters, MCP tools, and platform CLIs that let AI agents work against real operational systems through controlled boundaries.

Problem: Assistants need structured access to CWM, CWA, Graph, Sophos, Cavelo, Meraki, vCloud, Portainer, and GitHub without leaking secrets or bypassing approvals.
System: Generated CLI contracts, platform-specific fetchers, safety-gated write paths, Graph/CWA/Sophos investigation workflows, and MCP-style tool boundaries.
Proof: CLI contract generation, help-json surfaces, smoke tests, package builds, read/write gates, and public-safe investigation summaries.

Evidence Signals

The local-agent-tooling command surface prefers platform CLIs over raw APIs and emits JSON for agent consumption.
High-risk writes require preview tokens, explicit confirmations, or status-gate handling before execution.
Service investigations use Graph, CWA, Sophos, Meraki, CWM, and ticket/time evidence together before closure.

TypeScript Node.js MCP Microsoft Graph HaloPSA

n8n-mcp-tools halopsa-workflows-mcp

Publication boundary

Private and organization-adjacent systems are intentionally abstracted. Links are included only for public repositories or public-safe references.