NexAgent Lab · reusable capability map

Not a project graveyard—a set of product building blocks

We scanned 59 adjacent project folders and 26 Git repositories, then organized the products, delivery infrastructure, skills, and engineering standards worth carrying forward. Client data stays private; reusable methods, architectures, and product capabilities keep compounding.

59
adjacent folders scanned
26
Git repositories identified
19
core products and modules
8
reusable skills / standards

What qualifies as reusable

01

Independently deliverable

A clear user, boundary, and installation or deployment path.

02

Secure by default

Least privilege, data ownership, HITL, and rollback are design inputs—not later patches.

03

Customer exit is possible

Customer-owned accounts, exportable data, and no forced maintenance lock-in.

04

Verifiable

A README, tests, preflight, rendering checks, or human acceptance provides concrete evidence.

Products and engineering assets

These items are regrouped by reuse value. Public repositories are linked; delivery and internal components describe their boundaries without exposing client data, credentials, or private implementation.

Cloudflare delivery foundation

From zero-cost lead-generation sites to bookings, meeting intelligence, private agents, and customer-owned delivery infrastructure.

Released

Cloudflare Mobile Site Builder

An eight-stage website-building skill for small businesses working from a phone, with modular design, SEO/GEO, deployment, and domain guidance.

Reusable for
Lead generation, rapid sites, industry templates
Agent SkillWorkersPagesD1
View skill
Released

Meeting Note

Browser recording, chunked transcription, structured notes, action items, and calendar sync with passkey access in the user’s Cloudflare account.

Reusable for
Meetings, workshops, interviews, and knowledge retrieval
Workers AIQueuesD1KVPasskeys
View project
Released

Booking Site

A complete booking site for solo service businesses with schedules, passkeys, an owner dashboard, and bilingual UI on the free tier.

Reusable for
Clinics, studios, consulting, and local services
ReactWorkersD1KVWorkers AI
View project
In delivery

Telegram Cloud Agent

A white-label Telegram agent deployed per customer, with multimodal input, durable memory, management check-ins, and strict admin boundaries.

Reusable for
Executive assistants, store operations, and private workflow entry points
WorkersDurable ObjectsAI GatewayTelegram
In delivery

NextAgent Stack

A customer-owned turnkey stack combining sites, bookings, forms, portals, orders, email, support, and Telegram operations.

Reusable for
Clinic and local-business digital delivery
WorkersD1R2Service BindingsHITL
Internal reusable

Crebroker

An edge credential broker and remote MCP gateway that gives agents scoped access to search and model services without exposing upstream keys.

Reusable for
Credential isolation and shared access for agent fleets
WorkersMCPKVOAuth

Local-first AI tools

Native macOS products that prioritize privacy, file ownership, and system-level workflows.

Released

NextNote

A local-first Markdown, EPUB, PDF, and media workspace with wiki links, drawing annotations, and local or remote AI providers.

Reusable for
Personal knowledge, course materials, and AI-assisted reading
Swift 6SwiftUIMLXMarkdown
Download / source
Released

VoiceInput

Hold Fn to speak and release to type into any app, using on-device speech by default or a user-controlled speech endpoint.

Reusable for
Accessible input, support workflows, and faster writing
SwiftAppKitSpeechAccessibility
Download / source
Validated prototype

OpenClaw Pet

A pixel-art desktop companion that turns agent thinking, replies, and reminders into visible states via local events and Telegram.

Reusable for
Agent presence, reminders, and companion interfaces
SwiftSpriteKitLocal HTTPTTS

Content, knowledge, and education pipelines

Inspectable, repeatable research-to-publish systems instead of one-off prompts.

Internal reusable

Loop Engineering

One topic becomes researched copy, images, voice, vertical video, a long poster, and a QC loop, with readable artifacts at every stage.

Reusable for
Teaching demos, social content, and multi-model orchestration
PythonDeepSeekGeminiClaudeFFmpeg
Internal reusable

Obsidian Share Platform

Syncs a local Obsidian course vault into an access-controlled reading platform with assets in R2 and permissions in D1.

Reusable for
Training libraries, member content, and course delivery
Cloudflare PagesWorkersD1R2Obsidian
Internal reusable

Module Library

A governed library of reusable CRM, admin, auth, notification, and website modules with inventories, manifests, versions, and PR review.

Reusable for
Less duplicate work and consistent security boundaries
Module ManifestsGitPR Workflow
Validated prototype

Clinic No-Show ML

An end-to-end no-show risk pipeline using synthetic clinic data: features, model comparison, evaluation, calibration, and deployable inference.

Reusable for
Clinic operations analytics and explainable ML prototypes
Pythonpandasscikit-learnjoblib
Validated prototype

CA AI Grant Copilot

A seven-agent framework for Canadian SME AI-transformation grants, covering intake, workflow analysis, program matching, eligibility, one-pagers, intelligence, and red-team review.

Reusable for
Traceable application preparation, human sign-off, and policy freshness
Multi-agentProvenanceHuman GatePolicy Registry
Internal reusable

AI Film Production Harness

A seven-layer film pipeline for shot lists, reusable character assets, prompt compilation, batch generation, review, assembly, and cost tracking.

Reusable for
AI drama, branded video, and controlled batch generation
OpenArt MCPSeedanceFFmpegAsset Registry

Operations and reliable delivery

Observable, reversible, least-privilege operations for servers, agent fleets, and automated outreach.

Internal reusable

OpenClaw Fleet

Cross-host OpenClaw and memory-plugin status, compatibility preflight, and daily upgrade reporting through a deliberately read-only skill.

Reusable for
Agent fleet version governance and risk isolation
ShellSSHPreflightCron
Validated prototype

XiaoMai WeChat Automation

Task, template, scheduling, and AI copy workflows for WeChat and WeCom, with desktop execution defaulting to dry-run and human control.

Reusable for
Community operations, reminders, and local desktop automation
PythonOpenCVAppleScriptWeb UI
Internal reusable

Agent Task Audit Viewer

A local static audit dashboard for NDJSON agent-run logs, showing roles, model visibility, tool use, and token consumption.

Reusable for
Multi-agent governance, cost explanation, and delivery reporting
Static WebNDJSONLocal-firstAudit Logs
Internal reusable

Server Operations Toolkit

A unified SSH inventory, health-check, connectivity-diagnostics, and monitoring toolkit for local, cloud, and customer-site services.

Reusable for
Infrastructure inventory, incident triage, and delivery operations
SSHShellNode.jsHealth Checks

Skill library

A skill is not a magic prompt. It is an operating playbook with triggers, workflow, references, verification standards, and safety boundaries.

cf-mobile-site-builder

A complete phone-first Cloudflare site workflow with industry recipes, theme tokens, SEO/GEO, and safe deployment.

NextAgent

typographic-key-visual

Turns a word, name, or news hook into typography-first key-visual prompts and image workflows.

NextAgent

drama-topic-radar

Produces short-drama concepts through market scanning, trope analysis, opportunity detection, and weighted scoring.

NextAgent

personal-ledger

A privacy-first workspace for personal and small-business transactions, receipts, tasks, reminders, and reports.

NextAgent

longevity-pdf-report

A daily longevity, cell-tech, funding, and policy research workflow that produces a polished Chinese PDF.

NextAgent

ssat-lesson-builder

Builds a 10-slide SSAT math lesson and 30-question practice set with programmatic answer and layout checks.

NextAgent

openclaw-fleet

Read-only checks for OpenClaw hosts, plugins, compatibility, and automated upgrade outcomes.

NextAgent

CMS / SEO / Experimentation Standards

Adopted guidance for content modeling, Sanity engineering, SEO/AEO, and experimentation, with upstream attribution preserved.

Sanity · adopted

Inventory scope and disclosure

This page is based on a read-only local inventory completed on September 16, 2026. Maturity labels describe current delivery readiness; they do not imply that every item is open source. Medical and client CRM data, email authorization records, real invoices, student materials, production credentials, server addresses, and private repository paths are excluded. Third-party standards retain their original attribution.

README / manifest Git history Public-link check Privacy filter

Want to turn one building block into your operating system?

We can start with one narrow, verifiable workflow: prototype it, validate it in real use, and expand only when the evidence supports it.