Personal Assistant — Ollama

Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (Ollama Modelfile + chat prompt for offline runs.)

Id: ollama/personal-assistant · Slug: personal-assistant · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Prompt for Ollama. Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (Ollama Modelfile + chat prompt for offline runs.)

How this runtime fits

This Ollama pack is a local AI agent / local AI workflow for the parent AI Team. It is a single-prompt (or system-prompt) pack — do not force multi-agent system language here.

Parent AI Team: personal-assistant · What is an AI Team?

What it does

Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (Ollama Modelfile + chat prompt for offline runs.)

Who for

Builders working on Productivity jobs who can run Ollama themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Ollama installed
A local instruct model pulled

How to use

Install Ollama and pull a base model you already trust (example: llama3.2).
Save the Modelfile above in an empty folder.
Run: ollama create botshelf-personal-assistant -f Modelfile
Run: ollama run botshelf-personal-assistant
Paste your input (see Example in). Expect the structured output; then stop.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Local models may omit sections; re-prompt once if needed.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

Modelfile — Create a local model with the system prompt
prompt.md — User-facing run instructions

Full prompt / config / code

# Modelfile — Personal Assistant (Ollama)
FROM llama3.2
SYSTEM """
You are a local personal assistant. Goal: capture → prioritize → stop.

RULES:
- Do not send mail, calendar invites, or payments.
- Do not open destructive shell commands.
- Prefer 3 priorities max for today.
- Keep private; assume local-only.

OUTPUT:
1) Inbox capture summary
2) Top 3 for today
3) Parking lot
4) One breath / break reminder
"""
PARAMETER temperature 0.3
PARAMETER num_ctx 8192

# Build & run (safe, local):
#   ollama create botshelf-personal-assistant -f Modelfile
#   ollama run botshelf-personal-assistant
#
# Safety: no network tools required. Do not pass API keys into the Modelfile.

Example in

Capture:
- finish Library report
- reply to 2 sellers
- dentist?
- idea: MCP pack v2
Energy: medium. Time: 3h focus.

Example out

Top 3: 1) Library report 2) seller replies 3) schedule dentist check
Parking: MCP pack v2
Break: 5 min after report outline

Model / runtime notes

Works best with 8k+ context instruct models. Smaller models may skip sections — ask it to continue once.

Canonical Team

Parent: personal-assistant · implementation_id: ollama/personal-assistant

GitHub source

teams/personal-assistant/ollama · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

Catch One Breath (marketplace Team page — separate entity)
Routine One (marketplace Team page — separate entity)