Metadata-Version: 2.4
Name: ltcai
Version: 10.8.0
Summary: Lattice AI — local-first Digital Brain that keeps your knowledge durable across any AI model.
Author: TaeSoo Park
License-Expression: MIT
Project-URL: Homepage, https://github.com/TaeSooPark-PTS/LatticeAI
Project-URL: Repository, https://github.com/TaeSooPark-PTS/LatticeAI
Project-URL: Documentation, https://github.com/TaeSooPark-PTS/LatticeAI/blob/main/README.md
Project-URL: Issues, https://github.com/TaeSooPark-PTS/LatticeAI/issues
Project-URL: Changelog, https://github.com/TaeSooPark-PTS/LatticeAI/blob/main/docs/CHANGELOG.md
Keywords: ai,llm,mlx,mcp,rag,vscode
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Web Environment
Classifier: Framework :: FastAPI
Classifier: Intended Audience :: Developers
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi<1,>=0.110
Requires-Dist: uvicorn<1,>=0.29
Requires-Dist: pydantic<3,>=2.7
Requires-Dist: httpx<1,>=0.27
Requires-Dist: pillow<13,>=10
Requires-Dist: openai<3,>=1.30
Requires-Dist: python-docx<2,>=1.1
Requires-Dist: openpyxl<4,>=3.1
Requires-Dist: python-pptx<2,>=0.6.23
Requires-Dist: python-multipart<0.1,>=0.0.9
Requires-Dist: keyring<26,>=24
Requires-Dist: authlib<2,>=1.3
Requires-Dist: cryptography<49,>=42
Requires-Dist: pdfplumber<0.12,>=0.11
Requires-Dist: pypdfium2<6,>=4.30
Requires-Dist: watchdog<7,>=4
Requires-Dist: psycopg[binary]<4,>=3.2
Provides-Extra: ann
Requires-Dist: sqlite-vec<1,>=0.1; extra == "ann"
Provides-Extra: postgres
Requires-Dist: psycopg[binary]<4,>=3.2; extra == "postgres"
Provides-Extra: local
Requires-Dist: mlx-vlm>=0.6.3; extra == "local"
Requires-Dist: mlx-lm; extra == "local"
Provides-Extra: voice
Requires-Dist: openai-whisper; extra == "voice"
Requires-Dist: SpeechRecognition; extra == "voice"
Requires-Dist: pydub; extra == "voice"
Provides-Extra: all
Requires-Dist: mlx-vlm>=0.6.3; extra == "all"
Requires-Dist: mlx-lm; extra == "all"
Requires-Dist: openai-whisper; extra == "all"
Requires-Dist: SpeechRecognition; extra == "all"
Requires-Dist: pydub; extra == "all"
Requires-Dist: sqlite-vec<1,>=0.1; extra == "all"
Requires-Dist: psycopg[binary]<4,>=3.2; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest-cov<8,>=7; extra == "dev"
Requires-Dist: mypy<2,>=1.14; extra == "dev"
Dynamic: license-file

# Lattice AI

**Your model is the voice you use today. Your Brain is the asset you keep.**

**모델은 갈아타도, 내 지식은 내 컴퓨터에 남는 로컬 우선 AI 브레인.**

[![PyPI Version](https://img.shields.io/pypi/v/ltcai?label=PyPI)](https://pypi.org/project/ltcai/)
[![npm Version](https://img.shields.io/npm/v/ltcai?label=npm)](https://www.npmjs.com/package/ltcai)
[![VS Code Marketplace Version](https://vsmarketplacebadges.dev/version-short/parktaesoo.ltcai.svg)](https://marketplace.visualstudio.com/items?itemName=parktaesoo.ltcai)
[![Open VSX Version](https://img.shields.io/open-vsx/v/parktaesoo/ltcai?label=Open%20VSX)](https://open-vsx.org/extension/parktaesoo/ltcai)
[![CI Status](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml)
[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)

![v10.8.0 Living Brain walkthrough](output/release/v10.8.0/gifs/v10.8.0-living-brain-walkthrough.gif)

Chat, files, folders, notes, and web pages all flow into one durable knowledge
graph on your computer. Any model — local MLX or cloud — can speak with that
memory. Nothing leaves your machine without explicit consent.

대화·파일·폴더·웹페이지가 전부 내 컴퓨터 안의 지식 그래프로 쌓이고, 어떤
모델이든 그 기억을 이어받아 대화합니다.

## What You Can Do

| | |
| --- | --- |
| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v10.8.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.8.0/screenshots/05-memory-graph.png) |
| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.8.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.8.0/screenshots/12-review-center.png) |
| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.8.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.8.0/screenshots/10-admin-console.png) |
| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v10.8.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v10.8.0/screenshots/08-system.png) |

## Why Lattice AI

- **Own your memory** — knowledge lives in a local SQLite Brain you can back up,
  export, inspect, and restore (`.latticebrain` encrypted archive).
- **Model-independent** — switch between local MLX models and cloud models
  without rebuilding context from zero.
- **Honest by design** — the Brain tells you when retrieval context is limited,
  when captured pages extracted poorly, and when the vector index is catching up.
- **Safe automation** — automations are consent-first drafts; edits to existing
  content always pass through a reviewable proposal with a diff.

매번 AI에게 프로젝트 맥락을 다시 설명하고 있다면, 지식이 여러 서비스에 흩어져
있다면, 그 기억을 특정 회사가 아니라 내가 소유하고 싶다면 — Lattice AI가 그
브레인입니다.

## Quick Start

```bash
pip install ltcai        # or: npm install -g ltcai
LTCAI                    # then open http://127.0.0.1:4825/app
```

Apple Silicon local models: `pip install "ltcai[local]"`. Desktop app (Tauri)
ships as a dmg on each [GitHub Release](https://github.com/TaeSooPark-PTS/LatticeAI/releases).

First-run flow — wake the Brain, pick the owner, load a recommended model:

| | | |
| --- | --- | --- |
| ![Login](output/release/v10.8.0/screenshots/01-login.png) | ![Model install](output/release/v10.8.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.8.0/screenshots/07-model-library.png) |

Screenshot index and capture notes:
[output/release/v10.8.0/SCREENSHOT_INDEX.md](output/release/v10.8.0/SCREENSHOT_INDEX.md)

## Current Release

The current release is **10.8.0 — Within Reach**:

10.7.0 rearranged all twelve screens. 10.8.0 is about the things that were
already there but out of reach: a button below the fold, a message in a
language you did not choose, a file a small model nearly produced.

- **The first three screens fit on the screen.** Onboarding rendered a 390px
  decorative Brain above *every* step, so on a 1440×900 display the login
  form, the recommended model and the install progress all began below the
  fold — the first thing the product asked a new person to do was scroll. The
  organism is a hero on the welcome step and a 104px mark after it; the
  welcome screen itself went from 1175px of content to 770px, so its primary
  button is visible without scrolling.
- **One language per screen, including the ones the server writes.** API
  messages were literals at the raise site, written in whichever language the
  endpoint's author was thinking in — Korean from `auth.py`, English from
  `browser.py`. `latticeai/core/messages.py` is a catalog with both, resolved
  from `X-Lattice-Language` (falling back to `Accept-Language`); the browser
  extension, which showed English and Korean in the same popup, has one too.
  `tests/unit/test_server_messages.py` fails on a message that exists in only
  one language, and on a router that reverts to a hardcoded literal.
- **A small model's near-miss is no longer thrown away.** File generation
  picked the *longest* rejected reply to repair, so a 900-character apology
  beat a truncated-but-real HTML document; it now scores candidates by how
  close they are to being a file. A byte-identical repeated reply buys one
  extra attempt with a prompt that names the repetition. Prose file types
  (`.md`, `.txt`) had no validation at all and would save "Sure! Here is the
  document:" as the document.
- **Re-indexing costs what changed.** The incremental vector rebuild
  materialised every node and chunk in memory and asked one `SELECT` per item
  whether it had changed. It streams now, with a single prefetched hash map —
  and a settled index performs zero embeddings, asserted rather than assumed.
- **More ground under the frontend.** Statement coverage 47.35% → 52.26%,
  424 → 504 tests, including the app shell (`App.tsx`, previously 0%), the
  admin console (0%), the folder picker (2.7%) and the API client.
- **Evidence bound to this build.** `output/release/v10.8.0/` holds the twelve
  capture screens, walkthrough gif/webm, and the asset-manifest / mock-server
  fingerprints that lint re-checks before merge.
- **Exact artifact names only.** Publish paths list `dist/ltcai-10.8.0-*` and
  `ltcai-10.8.0.tgz` — never `dist/*`.

Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)

Expected artifacts for 10.8.0 release must use exact filenames:

- `dist/ltcai-10.8.0-py3-none-any.whl`
- `dist/ltcai-10.8.0.tar.gz`
- `ltcai-10.8.0.tgz`
- `dist/ltcai-10.8.0.vsix`
- `src-tauri/target/release/bundle/dmg/Lattice AI_10.8.0_aarch64.dmg`

Do not use wildcard artifact uploads. Package registry publishing remains owner-run.

## Architecture At A Glance

FastAPI on localhost is the source of truth; the React/Vite frontend and the
Tauri desktop shell sit on top; the independent `lattice_brain` package owns
the graph, memory, ingestion, and portability. Local-first by default — cloud
calls, downloads, Telegram, and update checks are opt-in.

See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
[docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) for the developer workflow
(`npm install && npm run dev`, validation via `npm run lint`,
`npm run test:unit`, `npm run test:visual`).

## Known Limitations

- External package registries are owner-published and can lag behind GitHub.
- PostgreSQL/pgvector is optional scale/migration tooling. SQLite remains the
  live local Brain store in 10.3.0.
- Docker, model downloads, cloud model calls, Telegram, Brain Network, and
  update checks require explicit user action.
- Conversation does not fabricate answers when no model is loaded. Agent and
  workflow simulation without a loaded LLM is deterministic and LLM-free (it
  does not call a model) — labeled as such, never presented as autonomous
  model success.
- Some backend-generated messages (for example the Postgres DSN notice) are
  produced server-side in English and are shown as-is; server-side i18n is not
  part of 10.3.0.

## Release History

| Version | Theme |
| --- | --- |
| 10.8.0 | Within Reach |
| 10.7.0 | Plain Surface |
| 10.6.4 | Loud Limits |
| 10.6.3 | Loud Limits |
| 10.6.2 | Ask First |
| 10.6.1 | First Things |
| 10.6.0 | Promoted Panels |
| 10.5.0 | Everyday Words |
| 10.4.0 | Named Ground |
| 10.3.0 | Measured Ground |
| 10.2.0 | Load-Bearing Fixes |
| 10.1.1 | Reachable Boundary |
| 10.1.0 | Hybrid Brain |
| 10.0.1 | One Source of Truth |
| 10.0.0 | Plain Language |
| 9.9.9 | Lean Shell |
| 9.9.8 | Autonomy Dial |
| 9.9.7 | No Gaps Left |
| 9.9.6 | Same Brain Everywhere |
| 9.9.5 | Closed Gaps |
| 9.9.4 | Durable Loops |
| 9.9.3 | Closed Loops |
| 9.9.2 | Artifact Trust |
| 9.9.1 | Clean Foundations |
| 9.9.0 | Fail-Closed Trust |
| 9.8.0 | Honest Knowledge Pipeline |
| 9.7.0 | Proactive Hybrid Brain |
| 9.6.0 | Trusted Agent Loop |
| 9.5.0 | Command Center |
| 9.4.0 | Question-Driven Everyday Automation |
| 9.3.0 | Proactive Brain Intelligence |
| 9.2.0 | Model-Agnostic File Generation |
| 9.1.0 | Code Review Completion & Fail-Closed Runtime |
| 9.0.0 | Code Review Closure & Runtime Cleanup |
| 8.9.0 | Scoped Memory & Tool Policy Hardening |
| 8.8.0 | Brain Core Extraction & Recall Proof Hardening |
| 8.7.0 | Runtime State Hygiene & Release Evidence Refresh |
| 8.6.0 | Desktop Capture & Navigation Reliability |
| 8.5.0 | Tool Registry Readiness & Config DI |
| 8.4.0 | Action-Aware Brain Chat |
| 8.3.0 | Orchestrated Brain Readiness |
| 8.2.0 | Brain Brief |
| 8.1.0 | Intuitive Brain Home |
| 8.0.0 | Runtime Architecture Contract |

Per-release details: [RELEASE_NOTES.md](RELEASE_NOTES.md)

## Documentation

- [docs/WHY_LATTICE.md](docs/WHY_LATTICE.md) — product philosophy
- [docs/TRUST_MODEL.md](docs/TRUST_MODEL.md) — local-first trust model
- [PRIVACY.md](PRIVACY.md) — privacy and external communication policy
- [FEATURE_STATUS.md](FEATURE_STATUS.md) — feature status and limitations
- [SECURITY.md](SECURITY.md) — security posture
- [RELEASE.md](RELEASE.md) — release guide and notes

## License

MIT. See [LICENSE](LICENSE).
