Personal Assistant — LangGraph

Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (LangGraph stateful graph with a human checkpoint.)

Id: langgraph/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

Code for LangGraph. Daily capture → prioritized plan with stop rules. Local-first; does not spend money or send mail alone. (LangGraph stateful graph with a human checkpoint.)

How this runtime fits

This LangGraph implementation is a graph-style runtime for the parent AI Team. Agent orchestration and multi-agent workflow language fit when nodes split work and gates; it is not automatically identical to every multi-agent system.

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. (LangGraph stateful graph with a human checkpoint.)

Who for

Builders working on Productivity jobs who can run LangGraph themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Python 3.10+
LangGraph in a venv
Local model binder

How to use

Install LangGraph in a venv (pin versions).
Wire produce() to your local model client.
Run the file once with Example in.
Keep human_gate approval defaulting to False; enable revise only intentionally.

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.
Do not attach billing cloud LLM nodes without a human budget check.

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

graph_personal_assistant.py — LangGraph nodes + interrupt
README.md — Run notes

Full prompt / config / code

# graph_personal_assistant.py — Personal Assistant (LangGraph sketch)
# pip install langgraph langchain-core (pin yourself)
# Use a local chat model binder; do not embed secrets.

from typing import TypedDict, Literal
from langgraph.graph import StateGraph, END

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"""

class State(TypedDict):
    user_input: str
    draft: str
    approved: bool
    notes: str

def produce(state: State) -> State:
    # Pseudo: call your local model with SYSTEM + state["user_input"]
    draft = "[MODEL OUTPUT PLACEHOLDER — wire your local LLM here]\n" + state["user_input"][:500]
    return {**state, "draft": draft, "notes": "awaiting human"}

def human_gate(state: State) -> State:
    # In real use: interrupt / input() / UI approval.
    # Default False so nothing auto-publishes.
    return {**state, "approved": False}

def route_after_gate(state: State) -> Literal["done", "revise"]:
    return "done" if state.get("approved") else "done"  # stage-1: always end after gate

g = StateGraph(State)
g.add_node("produce", produce)
g.add_node("human_gate", human_gate)
g.set_entry_point("produce")
g.add_edge("produce", "human_gate")
g.add_conditional_edges("human_gate", route_after_gate, {"done": END, "revise": "produce"})
app = g.compile()

if __name__ == "__main__":
    out = app.invoke({"user_input": "PASTE_EXAMPLE_IN", "draft": "", "approved": False, "notes": ""})
    print(out)

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

Graph includes an explicit human checkpoint. Stage-1 ends after gate (no infinite revise loop).

Canonical Team

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

GitHub source

teams/personal-assistant/langgraph · 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)