Real-time task tracking and conversation memory for Claude Code sessions

Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

這是一個 Discord 私人助理機器人，openclaw 概念重新實作精簡版。 專為個人使用設計，具備對話記憶與排程提醒功能，讓 Claude 成為你的專屬 AI 助手。

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

This Discord bot uses OpenAI's API to generate human-like responses in chat conversations.

Official Python SDK for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

Empathetic Voice Companion CARE_SOL_AI

Empirical test of whether test-time-training fast weights can act as multi-turn conversation memory.

MemU is an agentic memory framework for LLM and AI agent backends: it ingests multi-modal data, extracts and organizes it into structured memory and supports both RAG and LLM-based retrieval.

Hermes Agent memory awareness pipeline — perception, injection, and retrieval for LLM agents

LocalMind - LIVE-OFFLINE AI Assistant with Conversation Memory | GPT4All powered, 100% offline, privacy-first AI companion for Education, Healthcare & General assistance

MemFuse offers a robust memory layer for large language models, enhancing their performance and efficiency. Join our community on GitHub to explore features, report issues, or request new functionalities! 🐙💻

🔍 Enhance Claude's learning by capturing corrections and discovering workflows, transforming them into lasting skills for efficient code development.

MemFuse Python SDK offers a simple way to integrate memory capabilities into your LLM projects. 🚀 Join the community on GitHub to explore features and contribute! 💻

Attention-routed conversation memory for LLMs.

Framework-agnostic, provider-agnostic context-window packer for LLM chat history

Offline multimodal AI system with speech, vision, and language processing. LangGraph orchestration, Phi-4-mini LLM, Vosk STT, BLIP vision. Complete privacy, zero data transmission. Inspired by Interstellar's TARS.

Gemma 3を「忘れない相棒」に。OllamaとFirestoreで長期記憶を実装したローカルLLMチャット（Terraform構成付き）

ARCHIVED - A practical hybrid safety middleware for Large Language Models. It runs both a FastAPI production endpoint and the original interactive CLI with heartbeat. For AI labs, red/blue teaming, prompt engineering

A full-stack application where a user types "What is the total revenue by channel this year?" and receives a plain English answer with an auto-generated visualization. The system uses an NLP-to-SQL pipeline powered by LLaMA 3.3 70B via Groq API, executes queries on MySQL, and returns natural language explanations with Chart.js visualizations.