Xpansion Framework

Xpansion.
Where your visions take root.

Every session sharper than the last.

Every decision remembered. Every judgment learned. Every mistake caught — before it ships. Xpansion isn't a tool Claude Code reaches for. It's the platform Claude Code runs on. Install it once. It gets smarter every session, for as long as you build.

Connect with GitHub — it's free See how it works →

7-day free trial — full Pro  ·  Founding Pro: $15/mo (first 250)  ·  Pro: $29/mo  ·  Team: $34/seat/mo

● ● ●
Status line ● Xpansion Framework  ready
▲ Above the bar — events as they fire (transient) ▼ The bar — session state (persistent, always current)

Anyone who builds with AI knows this feeling.

It's not a skill problem. It's a structural one. The model is powerful — but it doesn't remember what you decided, doesn't learn your judgment, and doesn't catch its own drift. It has to.

It said it was done. It wasn't.

Claude reports success. The output looks right. Three steps later, something is broken — or missing — and tracing it back costs more time than the original task. There was no checkpoint. There was no verification. There was just trust.

Change one thing. Break three others.

Nothing in the model knows what depends on what. A change lands. Something else breaks. Fix that — break another. Fix that — break yet another. This is whack-a-mole with your own codebase, and there's no natural exit unless something outside the model is tracking the connections.

The session ends. So does everything in it.

The decision you landed on. The tradeoff you reasoned through. Why you chose this approach. Gone. Tomorrow you start from the beginning — not from where you were. Every session starts at zero, for as long as you use the tool.

Xpansion was built by someone who lived this — not an observer diagnosing from the outside, but a builder inside the loop. The frustration isn't unique to developers. It belongs to anyone building real things with AI: products, content, systems, decisions. Powerful tools. No accountability layer. Until now.

This is built for them.

Three things you stop worrying about.

Did it do what I meant?

XFFI defines your intent as a finite, verifiable spec before work begins. XFXA checks every terminal before you ship. You stop guessing and start knowing.

What did I miss?

XFFI's discovery phase asks the questions about your brief that you didn't know to ask. Boundaries surface before work begins — not after something breaks.

Where was I?

XFMT builds a memory tree that compounds across every session. Every decision, every context, every tradeoff — searchable, permanent, always carried forward.

Whatever you're building, XF runs the same enforcement.

XF started in code. It didn't stay there. The thesis — code enforces what the LLM can't be counted on to do alone — applies anywhere AI is doing structured work. The four session modes map to any domain.

Code
Build

Implementation, debugging, refactoring. Contract violations caught before they land. Blast radius mapped before you commit.

Create
Understand

Writing, product definition, design. Intent defined as deliverables. Verified against what was actually produced.

Concept
Specify

Research, architecture, strategic analysis. Design decisions formally specified. Grounded in verified data, not inference.

Operate
Operate

Deployment, configuration, incident response. System state verified. Changes tracked against intended configuration.

The only limitation is the scope of what you're trying to accomplish.

Thirteen modules. Six categories. One tree.

Intent defined. Execution enforced. Delivery verified. Memory compounded. Six categorizations feed the platform — every module lives inside one.

Catch mistakes before they ship
Quality Gates — XFBA · XSIA · XFSA · XFVE

Four gates: three on every code edit (contract violations, cascade impact, security exposure) and one on every response (plain language, actionable, recommendation-first).

See the gates →
Remember everything, every session
Memory Layer — XFMT · XFMTR · XFCD · XFPA

An organic memory tree that compounds across every session, retrievable semantically, self-reconciling, learning your judgment over time.

Explore the tree →
Define done. Verify done.
Decomposition Engine — XFFI · XFXA

Finite MECE specs before work begins. Binary terminal verification before work ships. No more "I think it's done."

See how it works →
Surface the right tool — before Claude picks the wrong one
Routing — Dispatch (XFTD)

Dispatch scans 16,500+ MCPs, plugins, and skills in real time, routing by AI intent detection so you never default to the wrong tool.

See routing →
Manage the session before it manages you
Context — XFTC

Real-time context hygiene: 60% compact nudges, 85% enforcement, token-hog detection. No silent compaction. No lost work.

See XFTC →
Pick the right model for every task
Model Source — XFMS

Stated purpose in, ranked shortlist out — weighted by quality, cost, latency, and capability against eight independent evaluators. Hosted MCP endpoint, one-line install.

See XFMS →

Three things only XF does.

Other Claude Code frameworks give Claude more skills. More things it can reach for. XF is the layer between you and the mistake — the enforcement, the routing intelligence, and the memory that compounds.

Tool Routing
16,500+ tools. AI-classified. Real time.

Other frameworks surface a fixed skill catalog. XF routes across 16,500+ MCPs, plugins, and skills using AI intent detection — matched to your task and your stack, on every shift, without you asking.

Enforcement
The only layer that catches breaks before they land.

XFBA catches code contract violations at edit time. XSIA maps what else breaks before you commit. Other tools help you ship faster. XF ensures what you ship doesn't take down something else on the way out.

Memory Tree
A tree that grows. Not a log that accumulates.

XFMT builds an organic memory tree — each concept finds its branch, decisions surface with temporal precision, contradictions flagged automatically. Every session makes the tree smarter. Nothing is ever lost.

Not a feature set. A communication protocol.

Most AI tools add capabilities. Xpansion Framework adds structure — the missing layer between AI-generated output and verified execution.

Finite Boundary

Every session begins with a defined boundary — what this task is, what it touches, and what it must not break. XFBA and XSIA enforce the edges. The AI doesn't guess where the walls are. They're defined.

Recursive Discovery

From every change, XF maps every branch — every caller, every dependency, every downstream effect. Not a static checklist. A live graph that updates as Claude Code works, surfacing what you didn't know to ask about.

Terminal

Nothing ships without a terminal — a binary, verifiable outcome that defines what done actually means. Not a feeling. Not a test that passed once. A finite result, enforced by XFXA before every commit.

This is the structure that makes Human-to-AI communication reliable at scale. Boundaries contain the blast radius. Recursive discovery surfaces what's hidden. Terminals replace assumption with verification. Together, they make Claude Code something you can deliver with confidence — not just speed.

The only limit is what you set out to build.

XF enforces intent. It doesn't care what domain that intent lives in.

Code

"I finally shipped without second-guessing it. XFXA said 9 of 9 terminals met. That was my sign-off."

A founder building their first product. XFFI defined every deliverable before a line was written. XFBA caught violations at edit time. XFXA confirmed everything before push. No more "I think it's done."

Create

"I briefed Claude on a 12-piece campaign. Two weeks later, every deliverable traced back to the original brief — not what felt right in the moment."

A marketer running a product launch. XFFI scoped the campaign before Claude wrote a word. XFMT carried the brief across every session. Nothing drifted.

Concept

"Every claim in the report was traceable to data we actually had. XFFI wouldn't let a terminal reference anything we hadn't confirmed."

A researcher synthesizing a complex analysis. Roots grounded the spec in real data sources. No hallucinated citations. No drifting into inference. Grounded work from the first terminal.

Operate

"Nothing advanced until the previous phase was confirmed. We ran a zero-downtime migration across three environments with no surprises."

An ops team running a critical production deployment. XFFI defined the phase gates. XSIA mapped what would break if sequence was violated. Every step earned the next one.

These are four worlds. The enforcement is the same in all of them. XF doesn't know what you're building — it only knows how to make sure you delivered what you intended. The scope of what it can enforce is bounded by exactly one thing: your vision.

A living platform that gets smarter every time you use it.

Every module is both a service and a sensor. What the platform catches, what you approve, what you override — all of it becomes training signal for the next release. Not a snapshot. A living system.

Per-User Learning
XFPA learns your judgment.

Every approval and override trains a per-rule confidence score. Once a pattern earns trust, it auto-applies. The guardrails fade where they don't need to fire — without losing the enforcement where they do.

Cross-User Aggregation
Every session feeds the whole.

Anonymized signals from every install — which prompts converge, which rules false-positive, which resolutions earn approval — feed back into the next platform release. You benefit from everyone else's sessions, even the ones you'll never see.

Release-Over-Release
Thursday's XF beats Monday's.

The platform you installed last week is quantitatively better today. Module thresholds retune. Prompts sharpen. Heuristics learn. Static AI tools ship once and rot. XF closes the loop between what happens in your session and what ships in the next release.

Start your 7-day trial — it's free

Start your trial. Pick your tier.

Full Pro access for 7 days. After that, subscribe or we stop — no reduced free tier, no ads, no surprises. Clean uninstall available anytime.

Pro
For solo builders on Claude Code
$29 / mo
7-day free trial — no card required
  • All 13 modules across 6 groupings
  • 16,500+ tool catalog
  • XFMT + XFXA included
  • Session dashboard
  • Cancel anytime
Start 7-day trial →
Team
For teams building with Claude Code
$34 / seat / mo
Minimum 3 seats · Annual billing
  • Everything in Pro
  • Shared catalog view
  • Team memory tree
  • Admin console + SSO
  • Priority support
Contact us →

Common questions

What is Xpansion Framework?
Xpansion Framework is a thirteen-module living platform for Claude Code, organized into six groupings: Quality Gates (XFBA, XSIA, XFSA, XFVE) catch contract violations, cascade impact, security exposure, and enforce plain-language responses; Memory Layer (XFMT, XFMTR, XFCD, XFPA) saves sessions, searches semantically, reconciles contradictions, and learns your judgment; Decomposition Engine (XFFI, XFXA) defines a finite MECE spec before work begins and verifies every terminal before it ships; Routing (Dispatch/XFTD) surfaces the right tool from 16,500+ MCPs, plugins, and skills; Context (XFTC) keeps the session healthy with compact nudges and token-hog detection; Model Source (XFMS) picks the right LLM for every task against eight independent evaluators. Every session makes the platform smarter.
How is Xpansion Framework different from Claude Code plugins or skills?
Plugins and skills give Claude new capabilities. Xpansion Framework protects the session itself — it's the guardrail layer that runs before and after every tool call, not a tool Claude reaches for. You install both; they serve different purposes.
Does it work with any Claude Code project?
Yes. XF is language and framework agnostic — it works with any stack Claude Code supports. Stack detection auto-configures tool recommendations for your specific project.
Does XF only work for software development?
No. XF works for any Claude Code session — writing (Create mode), research and analysis (Concept mode), deployment and configuration (Operate mode), and software development (Code mode). XFFI classifies your intent at the start of every session and routes to the right mode automatically. XFBA, XSIA, XFMT, and XFXA work the same way regardless of what you're building.
Can I self-host Xpansion?
Xpansion is a managed hosted service. The managed API keeps the 16,500+ tool catalog scored and current with fresh install data from thousands of sessions — that intelligence can't be self-hosted. One tier, one flow: sign in, trial for 7 days, subscribe or leave clean.
How does the 7-day free trial work?
Sign up with GitHub — no card required. You get full Pro access for 7 days: all thirteen modules across all six groupings, unlimited detections, XFMT, XFXA, and the 16,500+ tool catalog. Seven days is enough for 20-30 Claude Code sessions, plenty of time to feel what XF catches.
What happens after the free trial ends?
Xpansion stops. No reduced free tier, no ads, no surprise charges. You either subscribe to restart (Pro $29/mo, Founding Pro $15/mo locked for life for the first 250 subscribers, Team $34/seat/mo) or run /dispatch-uninstall in Claude Code for a clean removal. Your project .xf/ folders and XFMT snapshot history stay on disk — your data, your call.
How does XFMT prevent context loss?
XFMT grows an organic memory tree — every concept from every session is decomposed, placed in its branch, and retrievable with temporal precision. XFTC nudges at 60% to snapshot and compact. At 85% an enforcement block fires — snapshot, compact, or continue with eyes open. Snapshots and embeddings stay on your disk — no setup required. XFMTR queries (semantic retrieval plus LLM synthesis) run through your Pro session — routed, not retained.
How does XF compare to Claude Code skill frameworks?
Skill frameworks give Claude more things it can do — more skills to reach for. XF is the enforcement and routing layer between you and the mistake. XFBA catches code contract violations before they ship. XSIA maps cascade impact before you commit. Dispatch routes across 16,500+ tools by AI intent detection. XFMT grows a living memory tree. These capabilities don't exist in skill frameworks — most XF users run both. They serve different purposes.
Does Xpansion Framework slow down Claude Code?
XFTD classification runs in ~100ms on every message. Pre-tool interception adds <200ms on Pro (catalog is pre-ranked, no LLM at hook time). The 10-second hard timeout enforced by Claude Code means XF can never hang your session.
How do I install it?
git clone https://github.com/XpansionFramework/Dispatch && cd Dispatch && ./install.sh Takes about two minutes. Start a new Claude Code session after install.

Your vision is the only limit.

Code, content, research, deployment — XF enforces the full contract, whatever you're building. One install. Every session. Automatically. The ceiling is yours.

Connect with GitHub — it's free