local-first / ai-ready
Your work leaves traces.
YZOS turns them into knowledge your AI can use, entirely on your machine.
$ git clone https://github.com/StringKe/yzos && cd yzos && mise run dev-installmcp { "mcpServers": { "yzos": { "url": "http://127.0.0.1:17432/mcp" } } }How it works
Observe
Screen recording with OCR, clipboard history, microphone transcription and AI tool sessions are captured passively in the background. You never operate YZOS directly; it watches while you work.
Crystallize
A local LLM condenses raw traces into people, projects, tasks and first-person memory points. Knowledge lives in plain Markdown files you can read and edit.
Supply
Claude Code, Codex and any MCP client connect to a local HTTP endpoint and query your activity, entities, knowledge and clipboard, with real data instead of guesses.
| tool | returns | source |
|---|---|---|
| activity | ||
| yzos_activity_summary | day digest | screen ocr |
| yzos_activity_sessions | session list | window focus |
| yzos_ai_sessions | ai tool sessions | agent logs |
| entity | ||
| yzos_entity_list | entities by kind | postgres |
| yzos_entity_get | entity detail | postgres |
| yzos_entity_search | ranked matches | pgvector |
| knowledge | ||
| yzos_knowledge_search | okf sections | okf markdown |
| yzos_knowledge_read | markdown source | okf markdown |
| clipboard | ||
| yzos_clipboard_recent | redacted history | pii model |
| yzos_clipboard_search | redacted matches | pii model |
# Your AI assistant asks YZOS, not you
$ claude "what was I working on this morning?"
yzos_activity_summary -> 3 sessions: cluster autoscaling fix,
model registry refactor, PR review for auth module
YZOS.app (menu bar, single process)
|- observe screen / clip / mic / ai
|- crystallize llama.cpp -> entities + okf
|- postgres ~/.yzos/pg (pgvector)
\- http 127.0.0.1:17432 /mcpWhy YZOS
Everything stays local
Recording, OCR, inference and storage all run on your Mac. Embedded PostgreSQL, bundled llama.cpp, no cloud account, no telemetry.
Five model slots
Reasoning, vision, speech, embedding and PII detection each run their own model. Swap any of them from the built-in Hugging Face marketplace.
Privacy by default
A dedicated PII model redacts passwords, names, phone numbers and ID numbers before anything is stored or served.
Free and open source
MIT licensed. No paid tier, no feature gates. Build it, run it, fork it.
# 1
$ git clone https://github.com/StringKe/yzos && cd yzos
# 2
$ mise trust && mise install && mise run dev-install
# 3
$ claude mcp add --transport http yzos http://127.0.0.1:17432/mcp
ready state=observing pg=up llm=ready mcp=:17432