OSAgent Control PlaneNEPOPSX
PricingDocs
Sign InGet Started Free
OSAgent Control PlaneNEPOPSX

NEPOPSX is Terraform for AI coding agents: one operating layer for instructions, prompts, standards, and package-based workflows across your whole team.

1 config
Policy lives in one workspace model.
10+ roles
Architect, reviewer, QA, publisher, and more.
Every repo
Ship the same behavior across the whole fleet.

Platform

  • Pricing
  • Docs
  • Get Started

Use Cases

  • Dashboard
  • Setup guide
  • Team sign in

Trust

  • Architecture notes
  • Plan limits
  • Security

© 2026 NEPOPSX. All rights reserved.

Built for platform teams standardizing AI-assisted development.

The control plane for AI coding agents

Give every coding agent the same operating model.

NEPOPSX manages the configuration, packages, and shared intelligence that sit above Copilot, Cursor, Claude, and your internal agents. It does not replace the editor. It makes the editor predictable.

Get Started FreeRead the Docs
Plan like infrastructure. Execute locally. Sync intelligence when the team is ready.
npx @nepopsx/cli init
nepopsx scan
nepopsx install feature-factory

3 managed layers

Configuration, installable agent packages, and shared platform state.

Local-first execution

Agents run inside the IDE while NEPOPSX governs how they behave.

Team-wide learning

Approved customs, skills, and patches can flow back into every repo.

Control plane model

Config in. Packages and intelligence out.

vision-led
Configure

workspace.yaml

Services, commands, conventions, databases, and execution order for the whole workspace.

Tune

agents/*.yaml

Role models, scope boundaries, workflow knobs, and knowledge per installed package.

Teach

customs/*.md

Team-authored guidance plus machine-generated customs layered on top.

sync
Generate

.github/agents + prompts

Agent definitions, prompts, shared standards, and workflow files rendered into the repo.

Install

Feature Factory / QA / Docs

Composable providers for planning, implementation, verification, and living knowledge.

Remember

Platform state

Approved learnings, versions, and audit history that teammates can sync into their own local agents.

Package deck

feature-factory live
qa-agent vision
docs-agent vision

Learning stream

custom_instruction → no-default-exports
config_patch → max_review_cycles 3 → 2
skill → qa-environment-setup

Works above the editor and the model. It standardizes behavior once AI enters your workflow.

GitHub Copilot
Cursor
Claude Code
Windsurf
Augment
Internal agents
What NEPOPSX manages

Not another assistant. A platform layer for how assistants behave.

The current market explains AI coding in terms of models and chat. Buyers need the next level up: who defines the operating rules, how those rules are distributed, and how the system gets smarter across a team.

Declarative configuration

workspace.yaml defines services, commands, conventions, and execution order. agents/*.yaml tunes models, scope, workflow, and knowledge per package.

workspace.yaml
agents/*.yaml
customs/

Installable agent systems

Packages ship orchestrators, reviewers, QA flows, prompts, and supporting standards as a coherent system instead of loose markdown files.

feature-factory
qa-agent
docs-agent

Governance and distribution

Licenses, remote sync, marketplace delivery, and dashboard state give platform teams a way to control what each team installs and shares.

licenses
marketplace
sync --remote

A learning loop

Reflectors turn repeated friction into customs, skills, and config patches that can be audited, reverted, and reused instead of rediscovered.

customs/auto
skills
agent intelligence
Agent ecosystem

The vision is bigger than a single prompt package.

NEPOPSX is moving toward an ecosystem of installable agent systems. Feature Factory is the first package. QA Agent and Docs Agent make the platform story legible even before every piece ships.

Feature Factory

Team tier package

Live now

A multi-agent SDLC system with orchestrators, architects, reviewers, QA, publication, and reflection wrapped into one package.

  • Discovery → spec → implementation → publication → reflection
  • Bias-separated reviewer flows and recovery-aware orchestration
  • OpenSpec-driven artifacts and reusable standards

QA Agent

Free tier package

Vision package

A behavioral tester that thinks like QA first: risk analysis, cheapest proving test, conclusive evidence, then structured reporting.

  • API, browser, accessibility, security, and state verification
  • Environment gates before spending time on flaky checks
  • Evidence-backed results instead of vague pass or fail claims

Docs Agent

Free tier package

Vision package

A living-memory documentation system that detects drift, repairs only stale sections, and captures decisions as architecture records.

  • Section-level drift reports instead of rewrite-everything prompts
  • Accuracy review before quality review
  • Automatic ADR capture from Feature Factory artifacts
The moat

The learning loop turns usage into leverage.

Most AI workflows reset to zero with every new developer or repo. The NEPOPSX vision keeps the useful patterns: reflect them, audit them, sync them, and let the team start from a better system next time.

How the loop actually works

From one session to team-wide behavior.

local first, team ready
01

Run locally

agent run

A developer uses the agent inside Copilot, Cursor, Claude, or an internal shell on a real task.

02

Extract learnings

custom | skill | patch

The reflector turns repeated friction into structured learnings instead of burying them inside chat logs.

03

Store by org and workspace

platform state

Custom instructions, skills, and config patches are stored against the org, workspace, and installed agent package.

04

Apply with audit

audited change

High-confidence patterns can apply automatically while low-confidence ideas stay suggested and reversible.

05

Sync back to the repo

sync --remote

Teammates pull the approved state and regenerate stronger agent files without copy-pasting prompt tweaks.

Local-only teams can stop after the first sync. The remote loop matters when you want approved learnings to move across repos and teammates.

Agent intelligence

A visible audit trail, not hidden prompt drift.

12
Applied learnings
3
Pending review
1 click
To revert

no-default-exports

Applied
custom instruction•4 occurrences

max_review_cycles: 3 → 2

Applied
config patch•2 sessions

exclude ml-pipeline

Pending
scope change•low confidence

qa-environment-setup

Pending
skill•1 occurrence
Developer workflow

What a developer actually sees in the repo.

The practical loop is simple: define the local model, install a package, sync generated assets, and review the diff. Remote sync only shows up when the team wants to share approved learnings.

CLI workflow in a real repo

These are the commands a developer actually runs.

Step 01 • Create the local model

nepopsx init

core

Writes .nepopsx/workspace.yaml and captures how the repo should be described.

Step 02 • Scan the repo

nepopsx scan

core

Enrichs workspace.yaml with repo-specific context and confirms what should be pushed to the platform.

Step 03 • Install a package

nepopsx install feature-factory

core

Adds the package definition and auto-enriches that agent's YAML when the workspace is already scanned.

Step 04 • Generate repo assets

nepopsx sync

optional

Renders .github/agents, prompts, standards, and machine-managed customs from your already-enriched local config.

Step 05 • Pull team intelligence when needed

nepopsx sync --remote

core

Optional. Pulls approved customs, skills, and config patches from the platform into the local repo.

The developer mental model is repo-first: what files do I own, what does the generator write, and what happens when the team shares learnings?

Files you own

The durable config surface that should live in git.

.nepopsx/workspace.yaml

The shared workspace model you own in git.

.nepopsx/agents/feature-factory.yaml

Per-agent knobs like models, scope, and workflow rules.

customs/*.md

Team-authored rules that should always be injected.

What NEPOPSX writes for you

Generated assets developers review in diffs and PRs.

.github/agents/*.agent.md
.github/prompts/*.prompt.md
.github/instructions/*.instructions.md
customs/auto/*.md
Example diff surface
+ .github/agents/ff-developer.agent.md
+ .github/prompts/implement.prompt.md
+ .github/instructions/review.instructions.md
+ customs/auto/no-default-exports.md

When remote sync matters

Only when you want team-shared intelligence, not for basic local use.

  • Pulls approved customs, skills, and config patches from platform state.
  • Skips fields you already set locally so local intent still wins.
  • Makes a new teammate inherit the same improved agent behavior on sync.
Start small, scale the operating model

Start with one repo. End with team-wide agent intelligence.

Use the CLI locally, install the first agent system, and generate the files your editor needs. When the team is ready, sync the shared learnings and make every new repo inherit a stronger setup.

Get Started FreeSee Pricing
First-run command deck
npm install -g @nepopsx/cli
nepopsx init
nepopsx scan
nepopsx install feature-factory
nepopsx sync
What the repo gains immediately
  • Team-shaped instructions instead of scattered markdown
  • A visible package model for agent workflows
  • A path to shared learning instead of one-off prompt tuning