AI agent memory using Modern Hopfield Networks — no LLM calls, no database, one matrix multiply. MCP server for Cursor, Claude Code, and other AI coding agents.
-
Updated
May 31, 2026 - Python
AI agent memory using Modern Hopfield Networks — no LLM calls, no database, one matrix multiply. MCP server for Cursor, Claude Code, and other AI coding agents.
Talk to Houdini in plain English and it builds — an AI copilot living inside Houdini. In-process against hou: every action undo-wrapped, provenance-recorded, held to a truth contract (results never claim what wasn't observed) across 112 tools — studio-operable: doctor diagnostics, crash-surviving telemetry, bounded autonomy with a real kill switch.
An Eggdrop IRC bot script that pipes LLM intelligence into classic chat
A functionally operational, mathematically unhinged system for achieving 10× effective memory amplification on Apple Silicon using quantized fractal compression, complex-plane KV decomposition, and Euler-aligned swap geometry.
Vendor-neutral memory layer for AI agents. Give ChatGPT, Claude, Cursor, Gemini, and Grok shared persistent memory. TypeScript SDK, MCP server, REST API.
Self-hosted personal AI assistant on Telegram. Powered by OpenCode + Claude Sonnet (free big-pickle). OpenClaw skills compatible. SQLite + MCP live memory with optional Ollama vector search.
A sturdy, multimodal AI desktop companion for Windows. Features long-term memory, multi-profile personas, voice interactions, and local tools. Powered by Gemini 2.5. 🐴✨
🔒 Archived — use Neboy72/nexus-memory instead
An Fully local, privacy-first AI chat application. It features persistent vector memory, website crawling & Q&A, and fully customizable chatbot persona.
EVM — Evolution Vector Memory: deterministic interaction-state continuity and bounded identity evolution framework for AI systems.
Agent memory runtime: short/long-term context, vector persistence, compression, and personalization primitives.
Cortex — self-evolving memory and agent fleet for Claude Code
Dreaming plugin for OpenClaw memory-lancedb — Light/REM/Deep sleep phases with narrative generation and memory promotion.
A core cognitive library for AI agents managing state, memory, and tool invocation loops.
Autonomous multi-agent orchestration framework using LangGraph, Groq/Llama3, and vector-memory retrieval for goal-driven AI execution workflows.
A self-evolving, tri-brain autonomous AI agent featuring local subconscious memory, generative SVG art, and conscious reasoning.
Plug-and-play Qdrant vector memory plugin for Hermes Agent — 8 tools, 10 modules, 58 tests. Semantic long-term memory via local Qdrant + any OpenAI-compatible embedding API. Self-healing. One-minute install.
Local AI coding assistant for macOS with voice commands, vector memory, and Gemini-style surgical editing.
DIKW Memory Plugin - 基于 DIKW 模型的智能记忆管理系统 for Hermes Agent
Add a description, image, and links to the vector-memory topic page so that developers can more easily learn about it.
To associate your repository with the vector-memory topic, visit your repo's landing page and select "manage topics."