tethr-engine 0.3.0

Local-first behavioral intelligence engine with collectors, AI agent, and task executor

tethr-engine

TETHR is a local-first behavioral intelligence engine. It passively observes your devices, detects behavioral patterns without cloud processing, and serves real-time presence context to AI agents in under 300 tokens.

pip install tethr-engine
tethr start

---

What it does

• Passive observation — watches active windows, typing cadence, system state via background POTS process
• Pattern detection — identifies focus areas, app clusters, work rhythms from local data only
• Agent-ready API — /identity/context returns a compact behavioral summary, ready to inject into any system prompt
• MCP server — native Claude Desktop integration via python -m tethr_engine.mcp_server
• Zero cloud — everything stays on your device; Groq API used only for LLM inference calls

---

Quick start

pip install tethr-engine
tethr start          # first run prompts for Groq API key, then serves on :8001
tethr status         # confirm health
curl http://127.0.0.1:8001/identity/context

Full walkthrough → docs/quickstart.md

---

Agent integration

import requests

context = requests.get("http://127.0.0.1:8001/identity/context", timeout=3).json()["context"]
system_prompt = f"{your_base_prompt}\n\n[User context]\n{context}"

Query once per session, inject into system prompt. ~200–300 tokens.

Full guide → docs/integration.md

---

CLI

Command	Description
tethr start	Start server on localhost:8001
tethr start --host 0.0.0.0	Network accessible
tethr start --reload	Dev mode
tethr status	Health check
tethr version	Print version

---

Configuring data storage

By default TETHR stores data in the package directory. To use an external drive set data_path in config.yaml:

data_path: D:\tethr-data

Or set it during first-run setup when prompted. TETHR creates the directory if it does not exist.

---

Links

• PyPI
• Quickstart
• Integration guide