I Was Drowning in Opportunities. So I Built a Compass.

Beryl Ghany — Mon, 01 Jun 2026 04:45:12 +0000

This is a submission for the Hermes Agent Challenge: Build With Hermes Agent

What I Built

Lodestone is an AI accountability agent that helps ambitious students stay aligned with their long-term goals.
Most people don't fail because they lack opportunities. They fail because they slowly drift away from the future they originally chose.
I'm a Computer Science student originally from Cameroon, studying at an HBCU in the United States. I founded my school's first student-led hackathon and have been part of programs ranging from a State Department exchange to ISACA mentorships. The problem I kept running into wasn't finding opportunities. It was knowing which ones actually mattered for the future I was trying to build.
Lodestone was built to solve that problem, not just for me, but for every ambitious student drowning in options with no compass.

The application helps users:

Discover a personal North Star from natural language input
Evaluate decisions against long-term goals with alignment scoring
Track alignment over time with a live trend
Detect goal drift before it becomes a habit
Generate personalized reflections and weekly action plans powered by Hermes

Demo

Goal Discovery

Users don't need to write a perfect life mission statement. They just talk.

Hermes analyzes the input, identifies recurring themes, and generates a structured North Star with a stated motivation and long-term horizon.

The user reviews and locks it in. Now Lodestone has a committed direction to measure everything else against.

Decision Evaluation

Users log decisions as they happen in real life, no structured input is required here.

Lodestone scores each decision against the North Star and explains exactly why it helps or hurts, not a generic percentage but a reasoned breakdown of tradeoffs.

Drift Detection

Lodestone doesn't just evaluate single decisions. It detects patterns.
When alignment drops meaningfully across recent decisions, a drift warning surfaces automatically -- naming the specific decisions that contributed and how far alignment has fallen. This is the feature that makes Lodestone feel like a compass rather than a calculator.

Reflection Generation

This is the centerpiece :)

The user clicks Generate Reflection. Hermes runs a visible three-phase sequence:

Reading memory
Reasoning across decisions
Building a plan

The output references the user's actual decisions by name, identifies behavioral patterns over time, and ends with a concrete weekly recommendation. It is not generic advice. It is personalized accountability.

Code

beryl-ghany / lodestone.ai

My Tech Stack

Hermes Agent (running locally via WSL/Ubuntu)
Gemini (connected to Hermes as the underlying model)
React + TypeScript
Vite
Tailwind CSS
Node.js

How I Used Hermes Agent

Hermes Agent is the reasoning engine at the center of Lodestone. Every meaningful feature runs through it.

Memory

Hermes stores and retrieves the user's North Star, motivations, and planning horizon across sessions. This means decisions logged today are evaluated against goals set months ago -- not just the last message in a chat window.

Multi-Step Reasoning

When generating reflections, Hermes doesn't evaluate a single interaction. It reasons across the full decision history, identifies trends, detects drift, and compares recent behavior to the user's intended direction. That multi-step process is what separates Lodestone from a chatbot with a scoring widget.

Planning

Hermes produces actionable next steps grounded in the user's actual history and long-term objectives. It doesn't just describe what happened. It generates a plan for what should happen next.

Agentic Workflow

The reflection flow makes the agentic behavior visible and legible to the user, with three explicit phases: memory, reasoning, and plan. This was a deliberate design choice. The goal was for users to see Hermes working, not just producing output.

Challenges I Ran Into

The hardest problem was the cold start, a compass is useless without a direction. Most productivity tools fail because they demand a perfectly articulated goal upfront. The insight that unlocked Lodestone was letting Hermes extract a North Star from natural, fragmented input. That single design decision made the whole system feel accessible instead of intimidating.
The second challenge was making the agentic behavior legible. It's not enough for Hermes to reason well internally; users need to see it happening. Designing the three-phase reflection flow around memory, reasoning, and planning solved that.

What I Learned

The most valuable part of Hermes wasn't text generation. It was the combination of memory, reasoning, and planning working together across time.
Building Lodestone changed how I think about what AI products can be. The future isn't assistants that answer questions. It's systems that help people maintain direction -- that hold the thread between who you said you wanted to be and what you're actually doing today.

What's Next

Weekly autonomous reflections triggered without user input
Proactive drift alerts before the drop are significant
Voice-based goal discovery
Calendar and task integrations
Long-term goal forecasting across 6 and 12-month horizons

Most AI tools help people do more.
Lodestone helps people remember why they're doing it in the first place.
For students drowning in opportunities, that's not a nice-to-have. That's the whole game.

DEV Community: Beryl Ghany