HeepX

Build once. Learn everywhere.

Reusable AI capabilities for developers and AI agents.

$ pip install heepx

What is HeepX

HeepX builds capability repositories: a written protocol plus a deterministic evaluation suite, meant to make an AI system better at exactly one thing. Not prompts. Not a framework. Not a product.

heepx, the Python client documented here, is an independent, unofficial way to load one — download it, verify it against a content fingerprint, and read it as a typed value. It is not itself part of the capability ecosystem.

Why HeepX exists

The problem

An AI system works something out — that a claim needs checking, that a migration step cannot be undone — and then the session ends. The next session starts from nothing. The insight isn't wrong or superseded; it simply evaporates.

The honest status

One controlled benchmark exists: a placebo-controlled delta of +0.208 at p=0.125 on one small model — not statistically significant — against a prompt-length cost significant at p=0.008. Whether loading a capability measurably helps is promising and unproven, not settled.

Capabilities

Browse all →

Nine, deliberately — the ecosystem grew to nine quickly and then stopped on purpose. Each owns one boundary; none overlap.

Python

import heepx

warrant = heepx.learn("warrant")
print(warrant.name, warrant.version)

CLI

$ hx learn warrant
warrant 1.2.1
  fingerprint  a1b2c3d4e5f6a7b8

Offline

heepx.learn("warrant")
heepx.learn("warrant", offline=True)  # no network call

Multi-agent

planning = heepx.learn("planning")
verify = heepx.learn("verify")
plan = run_agent(planning, task=goal)
checked = run_agent(verify, task=plan)

Architecture

Every capability owns one boundary — a specific moment where an AI system commits to something and can get it wrong. Nine repositories, none overlapping, each independently versioned and independently falsifiable.

RepositoryBoundaryThe question at it
warrantassertionwhy is this claim true?
reasoningthoughtwhat am I building on, and what would collapse it?
verifythe checkdoes this hold against evidence?
planningexecutionin what order do I act, and what if a step fails?
memorythe sessionwhat survives a gap I did not observe?
codingthe changewhat can this change affect, and how far does my claim hold?
securitytrustwhat is this allowed to do, and on whose authority?
coordinationthe agentwhat do we hold in common, and has it been confirmed?
synthesisthe mergewhat may appear in a combined output?
Read the full architecture reasoning (workspace/ARCHITECTURE.md) →

Using capabilities with heepx-sdk (unofficial)

The Python client on this site is a separate, independent tool — not part of the diagram above. It resolves a name against the registry, downloads and caches the archive once, verifies its content fingerprint, and returns a typed value.

DeveloperPython SDKRegistryCapabilityApplication
Read how the client works →

Documentation

Phase 0 — complete

Foundation

Phase 1 — current

Evidence and rules

Phase 2–4 — future

Independence, federation, durability

Community