Overview
Hannes-Agent is a personal command-line interface agent developed by Dopamine Team. It is described as a pure CLI agent that learns from every conversation automatically, without being told to. It builds skills, remembers facts, and improves as it is used. The agent has no messaging gateway, dashboard, or cron scheduler; it operates in the terminal.
Every few turns, Hannes reviews the conversation in the background and writes lessons to memory. It can detect user corrections and perform an immediate review. Facts are stored with trust scores, entity relations, and FTS5 search. Memory grows over time and is recalled automatically at the start of each relevant conversation.
Users can inspect what the agent has learned through /brain, which shows a knowledge map in the terminal, or /brain web, which opens a local HTML graph in a browser. The agent supports custom model providers by allowing any OpenAI-compatible endpoint to be added directly from /model. Its memory uses a holographic SQLite provider that is local and has zero cloud dependency.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Users use Hannes to work with an agent directly in the terminal.
- Users use Hannes to inspect learned facts, entities, and categories in a terminal knowledge map.
- Users use Hannes to open a local HTML graph of its knowledge in a browser.
- Users use Hannes to add custom OpenAI-compatible model endpoints.
- Users use Hannes to create a skill from the current conversation.
- Users use Hannes to manually trigger memory and skill review.
Features
AI assistant
Natural language interface
Workflow automation
Reviews
No reviews yet. Be the first to share your experience!