Spaces:
Running
Download README.md from BonusLockSMith/memory-chatbot: direct link, hf CLI and curl.
- Browser
- Download file 1.63 kB
-
https://huggingface.co/spaces/BonusLockSMith/memory-chatbot/resolve/main/README.md
- Command line
-
hf download hf://spaces/BonusLockSMith/memory-chatbot/README.md
-
curl -L -o README.md https://huggingface.co/spaces/BonusLockSMith/memory-chatbot/resolve/main/README.md
title: Memory Chatbot
emoji: 🧠
colorFrom: gray
colorTo: red
sdk: docker
app_port: 7860
pinned: false
Memory Chatbot 🧠
A chatbot that remembers you across sessions. Close the tab, come back tomorrow — it still knows your name, what you're working on, and how you like things.
Project #16 of the "30 AI Projects in 15 Days" challenge. Focus: memory architecture + state.
The lesson: buffer vs long-term memory
Most chatbots only have a conversation buffer — the current session's messages. Reload and they forget you. This one adds long-term memory, in four moves:
- Extract — after each exchange, an LLM pulls durable facts about you (name, preferences, projects).
- Store — facts go to a local DB, keyed by user, deduped. This is what survives the session.
- Retrieve — on every turn, your stored facts are loaded.
- Inject — they're placed in the system prompt, so the bot recalls you.
A live 🧠 Memory panel shows exactly what it remembers, and lets you delete any fact or forget everything — memory you can see and control.
Run it
pip install -r requirements.txt
python app.py # http://127.0.0.1:7860
# Local Ollama by default (free/private); set ANTHROPIC_API_KEY for the Claude backend.
Prove the memory works
Tell it your name and what you're building, then reload the page (or come back later) — it still knows. Different browser / cleared cookies = a fresh user with its own memory.
Built by Robert Lucyk · GritAI Solutions · part of the 30-in-15 challenge.