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.
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  |
See how knowledge connects — a real relationship graph, not a file list  |
Capture anything — files, whole folders, notes, screenshots, web pages  |
Automate with review — agent changes become proposals you approve first  |
Pick a model in one click — recommended local models for your hardware  |
Stay in control — audit, roles, retention in a separate admin surface  |
Watch a file become memory — three named steps, not a pipeline diagram  |
Say how much it may do alone — one dial in plain words; dangerous actions stay blocked either way  |
Why Lattice AI
- Own your memory — knowledge lives in a local SQLite Brain you can back up,
export, inspect, and restore (
.latticebrainencrypted 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
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.
First-run flow — wake the Brain, pick the owner, load a recommended model:
 |
 |
 |
Screenshot index and capture notes: output/release/v10.9.0/SCREENSHOT_INDEX.md
Current Release
The current release is 10.9.0 — Never Blocks:
Lattice AI runs one event loop on your computer. Several things you could ask it to do were being done on that loop, so while they ran the server could not answer anything else. Downloading a model has a fifteen-minute timeout; that is how long the whole product could be frozen by one click.
- Nothing long runs on the event loop. Model pulls, engine installs, MCP
package installs and the CPU/RAM probe behind the System screen all moved to
a worker thread.
/local/sysinfois the one most people met without knowing: it is read by the System screen and by first-run analysis, so its ~2s freeze landed exactly while an answer was streaming. Two things keep it fixed — ruff'sASYNCblocking-call rules, andtests/unit/test_event_loop_not_blocked.py, which runs a ticker coroutine during the handler and asserts the loop kept getting control. - A focus ring you can see. 10.8.0 added
border-colorto the transition on the capture pills, so keyboard focus faded in over 150ms and at the instant it landed the pill still looked idle. Focus rings may not ease. - The Brain stops thinking when it has answered. A retrieval pulse parked a 900ms timer that put the organism back into "thinking"; if the answer finished inside that window the timer still fired, and the Brain sat visibly working on a question it had already answered.
- One language, further in. Fourteen more routers moved to the message
catalog — chat, memory, graph, files, portability, review, models, tools,
MCP, setup.
models.py,mcp.pyandtools.pyhad been answering some errors in Korean and others in English on the same screen. Two gates keep them migrated, and a third fails if the two gates disagree. - The welcome screen fits. It measured 770px against a 747px viewport, so the line explaining what you are agreeing to sat under the fold. Nothing was removed; the whitespace gave back the 25px.
- The streaming answer path has tests.
useBrainChatwas 12% covered because asserting anything about a stream needs frames arriving over time.frontend/src/test/fakeChatStream.tsis that harness; eleven cases now cover the answer building up, the stop button, refusals, grounding badges and live step frames. - Evidence bound to this build.
output/release/v10.9.0/holds the twelve capture screens, walkthrough gif/webm, and the asset-manifest / mock-server fingerprints that lint re-checks before merge. 10.9.0 claims no screen redesign, andscripts/release_screen_claims.jsonsays so explicitly. - Exact artifact names only. Publish paths list
dist/ltcai-10.9.0-*andltcai-10.9.0.tgz— neverdist/*.
Release notes: RELEASE.md · Full history: docs/CHANGELOG.md
Expected artifacts for 10.9.0 release must use exact filenames:
dist/ltcai-10.9.0-py3-none-any.whldist/ltcai-10.9.0.tar.gzltcai-10.9.0.tgzdist/ltcai-10.9.0.vsixsrc-tauri/target/release/bundle/dmg/Lattice AI_10.9.0_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 for details and
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 |
|---|---|
| 10.9.0 | Never Blocks |
| 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
Documentation
- docs/WHY_LATTICE.md — product philosophy
- docs/TRUST_MODEL.md — local-first trust model
- PRIVACY.md — privacy and external communication policy
- FEATURE_STATUS.md — feature status and limitations
- SECURITY.md — security posture
- RELEASE.md — release guide and notes
License
MIT. See LICENSE.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ltcai-10.9.0.tar.gz.
File metadata
- Download URL: ltcai-10.9.0.tar.gz
- Upload date:
- Size: 2.8 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e4ffb182c526b895d29b1fd69f39ab91899504f06264dfa8fe11f5ce609880a5
|
|
| MD5 |
3d738e8f38e6832e680fd8c4cd4574ce
|
|
| BLAKE2b-256 |
0bbcf97bf26028e8cd29c30b12b1f9fb81876fe1fc773c639dba0924c418344f
|
File details
Details for the file ltcai-10.9.0-py3-none-any.whl.
File metadata
- Download URL: ltcai-10.9.0-py3-none-any.whl
- Upload date:
- Size: 2.6 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
96cdf49ee0d98b8c3279173530c3184d0010a44f6fbf06e7e58076dc630b71d7
|
|
| MD5 |
dcc3957da26290abca929b5de2d8865e
|
|
| BLAKE2b-256 |
c94a207418660591d9e6b82cc630ea2f21458a3e8ea0c5374d8e61c73c037820
|
