WHYdr/llm-memory-agent
Now is my second year of my undergraduate life hh. I am now trying to build an agent with memory. To tell the truth I know very little about Agent Building and EVEN ML/DL hhh. Anyway this try will force me to learn more about ML and make me better at python coding. Let's do it!
SUMMARY AI summary by gpt-5-mini
A learning-oriented project implementing a long-term memory AI agent with persistent semantic memory and retrieval-augmented context management. Intended for developers and researchers exploring memory systems, RAG, agent workflows and long-context interaction. Key features: - Chat interface that embeds user messages, retrieves relevant memories, injects context into prompts, and stores important information. - Modular design: Chat, LLM (Ollama), Memory, Embedding, Retrieval. - Uses local LLMs (Llama/Qwen), LangChain, ChromaDB, sentence-transformers and HuggingFace tools. Current state: basic chat implemented; long-term memory, embedding, ChromaDB retrieval and prompt assembly planned. Run: python app/main.py
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
Owner
Dates
| Created on GitHub | 2026-05-09 |
| Last push | 2026-05-09 |
| First seen here | 2026-05-09 |
| Last fetched | 2026-05-09 18:19 |