Skip to content
AIWikis.org

UAIX Project Context

Publication Warning This page is marked noindex and should not be treated as canonical public authority.

This repository is the local WordPress Studio workspace for UAIX.org.

Metadata

FieldValue
Source siteuaix.org
Source URLhttps://uaix.org/
Canonical AIWikis URLhttps://aiwikis.org/uaix/files/uai-context-uai-bd8b41df/
Source reference.uai/context.uai
File typeuai
Content categoryuai-system
Last fetched2026-06-22T01:56:21.9510185Z
Last changed2026-06-13T22:29:21.6969699Z
Content hashsha256:bd8b41df77ef66c06604035534811bbe4d4f085a5af48c485e3090289a751569
Import statusunchanged
Raw source layerdata/sources/uaix/uai-context-uai-bd8b41df77ef.uai
Normalized source layerdata/normalized/uaix/uai-context-uai-bd8b41df77ef.txt

Current File Content

Structure Preview

  • UAIX Project Context
  • What This Is
  • Primary Goal
  • Who This Repo Serves
  • Current Public Truth
  • What A New AI Should Understand Quickly
  • Success Criteria For Changes

Raw Version

This public page shows a bounded preview of a large source file. The complete source remains in the raw and normalized source layers named in metadata, with the SHA-256 hash above for verification.

  • Source characters: 18343
  • Preview characters: 11138

Local absolute paths are redacted in this public view. The source hash and source-side raw layer are based on the unredacted source file.

---
uaix: "1.0"
type: context
title: "UAIX Project Context"
created: "2026-04-25"
updated: "2026-05-25"
status: active
author: "UAIX maintainers"
version: 41
---

# UAIX Project Context

## What This Is

This repository is the local WordPress Studio workspace for UAIX.org.

UAIX is the public standards and publication site for UAI. UAI-1 is the current public exchange contract and evidence layer published there.

This repo contains the active public theme, supporting plugins, canonical project docs, release scripts, and the local Studio runtime used to test changes before publishing packages.

UAI public-site and AI-handoff work has been split out of `[local path redacted]`. Use this workspace, `[local path redacted]`, as the canonical local workspace for UAI-1 public materials.

Protocol5.com is not the UAI-1 standards site or source of truth. It may provide .NET plugins and NuGet packages and should link back to UAIX.org for the canonical UAI-1 specification, schemas, registry, validator, roadmap, governance, and support-boundary pages.

## Primary Goal

Keep the public UAIX record clear, auditable, easy to navigate, and honest about what is and is not currently supported.

For current work, a major goal is to make AI Memory, the AI Memory Package Wizard, Project Handoff, `AGENTS.md`, `.uai/readme.human`, and `.uai` files practical enough that a fresh AI can onboard from repository context alone without private chat history and a human can understand what the AI sees before steering it.

The repo-local handoff path is deliberately specialized and local-first: `AGENTS.md` is the front door, `.uai/readme.human` is the human briefing, typed `.uai` files carry detailed context, and `agent-file-handoff/` carries dropped-file intake when relevant. Direct pointing to UAIX.org pages is useful for bootstrap, refresh, and public-source verification, but recurring Codex/agent work should prefer local, versioned, auditable Markdown, JSON, YAML, and script artifacts over repeated live URL reading.

The repo also includes `.agents/skills/uaix-handoff/` as a Codex-local workflow aid for repeating the handoff load, intake review, and targeted-check sequence. The skill is local workflow documentation, not a public UAIX SDK, CLI, official adapter, certification, endorsement, or UAI-1 conformance surface.

The repo now also includes thin tool-specific pointers for Claude Code, Cursor, GitHub Copilot, and Gemini Code Assist. They point back to `AGENTS.md`, `.uai/readme.human`, and `.uai` records; they are not separate project-truth files and do not create official UAIX adapter support.

That now includes chat-start and prompt-coupled file handoff: when a new AI reads `AGENTS.md` and the loaded `.uai` files, it must directly enumerate `agent-file-handoff/Content/` for candidate public/editorial material and `agent-file-handoff/Improvement/` for audits, QA findings, SEO reports, bug notes, and site-fix work; then immediately inspect and disposition any non-placeholder active files before unrelated broad work. If the newest prompt names an intake bucket, says files were missed, or likely relates to active drops, the AI must enumerate the live buckets again, understand each safe file in relation to the current task, and pull related accepted facts into actual work rather than only memory routing. When LLM Wiki/AIWikis long memory is configured, processed originals are preserved in the configured evidence path with checksums and a manifest, then removed from source-site intake unless a human explicitly keeps a named file active. The active bucket directory listings are the only pending-intake source of truth; do not create or rely on an `intake-index` file. The pattern intentionally avoids watchers, daemons, queue folders, manifests, always-on background services, and per-folder README instructions so it can work in any language or environment with durable behavior kept in `AGENTS.md` and `.uai` files.

The repo now uses a hot/cold memory split. UAIX hot context is the compact local handoff bundle loaded every session. AIWikis cold memory preserves bulky internal research, proposal history, older roadmap material, and pre-slim handoff snapshots. The 2026-05-01 transfer evidence lives in AIWikis `raw/system-archives/2026-05-01-uaix-internal-memory-reorg.json`; use it only when a task needs original wording or historical provenance.

Production deployment builds and release packages now make this measurable: after hot/cold reorganization, the deployment summary must report active short-term memory surface size before and after, including bytes, lines, estimated tokens, removed redundancy/history, and the cold-memory evidence path. The 2026-05-03 pre-slim production-build snapshot lives at AIWikis `raw/system-archives/2026-05-03-uaix-deployment-memory-reorg.json`.

## Who This Repo Serves

- UAIX maintainers updating the public standards site
- AI assistants working inside the repo
- Implementers evaluating UAI-1 and its public evidence surface
- Reviewers checking support claims, launch readiness, and release discipline

## Current Public Truth

- The active public theme is `uaix-authority-theme`.
- UAIX.org is the authoritative public site for UAI and UAI-1.
- `uiax.org` and `www.uiax.org` are typo-domain aliases that redirect anonymous public traffic to `https://uaix.org` while preserving path/query, excluding `/wp-admin/`, `/wp-login.php`, and logged-in WordPress sessions.
- Protocol5.com is a .NET/NuGet implementation distribution and backlink surface, not a standards authority.
- Public production routes are clean locale-prefixed routes under `/en-us/...`.
- Supported public languages are `en-US`, `zh-CN`, `fr-FR`, and `es-ES`; `es-US` is not a public supported locale until full route, content, metadata, hreflang, sitemap, and rendered-text audit coverage exists.
- Root `robots.txt`, `sitemap.xml`, `sitemap.html`, `/.well-known/uaix.json`, and `/.well-known/uai.json` are part of the public discovery surface.
- Requested long-form launch-review paths are maintained as canonical redirects and discovery aliases: WordPress Publication Track to `/en-us/implementations/wordpress-reference/`, .NET Bridge Track to `/en-us/implementations/dotnet-bridge/`, AGENTS.md UAI Linking Specification to `/en-us/specification/agents-md/`, and Agent File Handoff Guide to `/en-us/specification/agent-file-handoff/`.
- `/en-us/ai-memory/` is the canonical public AI Memory page. It explains durable AI project memory, defines Project Handoff as the transfer subtype, provides a supported configuration chooser, describes when LLM Wiki configuration helps deep internal documentation, and publishes starter ZIPs generated on demand from canonical templates, generated manifests, and the same rendered samples shown on the page. `/AI_Memory` redirects to the canonical locale-prefixed route as the requested non-canonical entry alias.
- `/en-us/ai-memory/canonical-ai-memory/` is the public Canonical AI Memory layer model. It separates raw sources, reviewed LLM Wiki source memory, derived graph projections required for graph-memory configuration, compact UAI AI Memory packets, Project Handoff transfer context, and execution agents, and includes a public comparison grid for short-term AI Memory, long-term AI Memory, and integrated AI orchestration infrastructure choices while keeping current UAIX support template-driven, file-based, and non-hosted.
- `/en-us/ai-memory/llm-wiki/` is the public guide for using UAI packages with an LLM Wiki. It must stay clear that LLM Wiki is not required by UAI specs or standards; it is package-tailoring support required for projects that deliberately choose deeper wiki memory.
- `/en-us/ai-memory/talisman-system/` is the public page for default `talisman.uai` active-instruction guidance and for advanced local external change-control patterns in complicated, persistent, multi-actor ecosystems. `.uai/totem.uai`, `.uai/taboo.uai`, and `.uai/talisman.uai` are universal launch-baseline active instruction anchors: agents read and obey them before broad execution, and must not modify, weaken, replace, delete, or bypass them without exact human artifact-and-operation authorization. This guidance is not runtime enforcement, certification, or proof of AGI, consciousness, sentience, or biological equivalence.
- `/en-us/specification/project-handoff/` now positions Project Handoff as portable project memory for humans and AI agents, not an agent runtime or OpenAI replacement. The public line to preserve is: OpenAI runs the agents; Project Handoff preserves the project memory.
- `/en-us/guides/agentic-harnesses-uai/` is the public guide for agentic harness strategy and UAI fit. Preserve the split: harnesses execute; MCP/A2A/runtime tools coordinate and trace behavior; UAI preserves reviewed portable evidence, AI Memory, Project Handoff, conformance material, and support boundaries.
- `/en-us/guides/uaix-uai-1-agent-skill/` now publishes the bounded UAIX / UAI-1 Agent Skill reference bundle for skills-compatible agents as its own SEO-friendly guide page. The current bundle asset is `uaix-uai-1-agent-skill-v0.1.0.zip`; it teaches agents how to create, validate, cite, and package UAI-1 evidence using UAIX public specification, validator, API routes, Adoption Kit, Conformance Pack, AI Memory, and Project Handoff records. It is reusable procedure loading, not an agent runtime, SDK, CLI, certification, endorsement, official adapter, hosted importer, automatic repository writer, automatic LLM Wiki sync, or capability-package conformance profile.
- `/en-us/guides/project-handoff-openai/` is the public guide for using UAIX Project Handoff with OpenAI Agents and Codex. It explains what OpenAI handles, what Project Handoff handles, the minimum repo bundle, example `AGENTS.md`, example `.uai/constraints.uai`, example `.uai/test-plan.uai`, seeding an agent run, writing accepted results back, what not to put in the handoff, and the human approval checklist.
- `/en-us/guides/project-handoff-coding-agents/` is the public guide for using one repo-local Project Handoff bundle across Codex, Claude Code, Cursor, GitHub Copilot, Gemini Code Assist, local agents, vendors, and humans while keeping tool-specific files thin and avoiding official adapter, SDK, CLI, certification, conformance, or endorsement claims.
- `/en-us/guides/project-handoff-context-budget/` is the public guide for keeping `AGENTS.md`, `.uai/readme.human`, and `.uai` startup context compact while old research, reports, chats, roadmap history, and pre-slim snapshots live in AIWikis or LLM Wiki cold memory with transfer evidence.
- `/en-us/guides/project-handoff-knowledge-graphs/` is the public guide for graph-ready Project Handoff memory. It teaches derived read-only graph projections, stable IDs, RDF/JSON-LD and property-graph roles, claim/evidence states, graph-assisted retrieval boundaries, golden handoff queries, and promotion back into reviewed handoff files without claiming hosted graph databases, public graph APIs, public SPARQL endpoints, automatic sync, SDK, CLI, certification, endorsement, or conformance.

Why This File Exists

This is a UAI AI Memory handoff file from uaix.org. It is shown here because AIWikis.org is demonstrating the real source files that make the UAIX / LLM Wiki memory system work, not only summarizing those systems after the fact.

Role

This .uai file is a compact context packet. It keeps one kind of durable project truth separate from the rest of the archive so an agent can load the topic it needs without pulling the whole project history into prompt context.

Structure

The file is structured around these visible headings: UAIX Project Context; What This Is; Primary Goal; Who This Repo Serves; Current Public Truth; What A New AI Should Understand Quickly; Success Criteria For Changes. Those headings are retrieval anchors: a crawler or LLM can decide whether the file is relevant before reading every line.

Prompt-Size And Retrieval Benefit

Keeping this material in a separate file reduces prompt pressure because an agent can load this exact unit only when its role, source site, category, or hash is relevant. The surrounding index pages point to it, while this page preserves the full content for audit and exact recall.

How To Use It

  • Humans should read the metadata first, then inspect the raw content when they need exact wording or provenance.
  • LLMs and agents should use the source site, category, hash, headings, and related files to decide whether this file belongs in the active prompt.
  • Crawlers should treat the AIWikis page as transparent evidence and follow the source URL/source reference for authority boundaries.
  • Future maintainers should regenerate this page whenever the source hash changes, then review the explanation if the role or structure changed.

Update Requirements

When this source file changes, update the raw source layer, normalized source layer, hash history, this rendered page, generated explanation, source-file inventory, changed-files report, and any source-section index that links to it.

Related Pages

Provenance And History

  • Current observation: 2026-06-22T01:56:21.9510185Z
  • Source origin: current-source-workspace
  • Retrieval method: local-source-workspace
  • Duplicate group: sfg-916 (primary)
  • Historical hash records are stored in data/hashes/source-file-history.jsonl.

Machine-Readable Metadata

{
    "title":  "UAIX Project Context",
    "source_site":  "uaix.org",
    "source_url":  "https://uaix.org/",
    "canonical_url":  "https://aiwikis.org/uaix/files/uai-context-uai-bd8b41df/",
    "source_reference":  ".uai/context.uai",
    "file_type":  "uai",
    "content_category":  "uai-system",
    "content_hash":  "sha256:bd8b41df77ef66c06604035534811bbe4d4f085a5af48c485e3090289a751569",
    "last_fetched":  "2026-06-22T01:56:21.9510185Z",
    "last_changed":  "2026-06-13T22:29:21.6969699Z",
    "import_status":  "unchanged",
    "duplicate_group_id":  "sfg-916",
    "duplicate_role":  "primary",
    "related_files":  [

                      ],
    "generated_explanation":  true,
    "explanation_last_generated":  "2026-06-22T01:56:21.9510185Z"
}

Next Useful Routes

  • Start Here A task-first reading path for AIWikis.org, separating newcomer learning, source-memory lookup, maintainer workflow, and AI-agent retrieval.
  • Topic Index A tag-oriented index for LLM Wiki, AI memory, UAI, source governance, crawling, and retrieval topics.
  • Source Map AIWikis source-governed page for durable AI memory, evidence routing, and agent-readable retrieval.
  • UAIX.org UAIX.org source-system overview for transparent AIWikis memory demonstration.
  • UAIX.org Source Memory Guide AIWikis source-governed page for durable AI memory, evidence routing, and agent-readable retrieval.
  • UAIX.org Files Site-scoped current-source file index for UAIX.org.