vector-memory

🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Claude/Cursor等任意AI智能体

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.

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.

Dreaming plugin for OpenClaw memory-lancedb — Light/REM/Deep sleep phases with narrative generation and memory promotion.

autonomous web developer orchestration with python. now has hierarchical RAG using vector databases

An Eggdrop IRC bot script that pipes LLM intelligence into classic chat

Cortex — self-evolving memory and agent fleet for Claude Code

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. 🐴✨

Agent memory runtime: short/long-term context, vector persistence, compression, and personalization primitives.

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.

A self-evolving, tri-brain autonomous AI agent featuring local subconscious memory, generative SVG art, and conscious reasoning.

🧠 ViBo — save 50-150× tokens: persistent memory for AI agents (L1/L2/L3) + web search compression (96.2%). One skill, two products. $5/mo.

AIOS is an operating system for language models and human users that runs like a text-based adventure game for intelligent agents. It is feature-rich with a working memory pipeline.

Lilith CLI - terminal-first AI workspace with a Textual IDE, durable missions, orchestration, and vector memory.

A tool-calling AI agent with a hand-written loop: sandboxed code execution, scoped file I/O, web search, long-term vector memory, and failure guardrails (circuit breaker, iteration limits). Keyless mock LLM or Groq. Python/FastAPI.

Telegram-бот с долговременной памятью в Pinecone: чат, RAG и фильтр дубликатов по косинусному сходству

Autonomous multi-agent orchestration framework using LangGraph, Groq/Llama3, and vector-memory retrieval for goal-driven AI execution workflows.

Session memory & context enhancer for chat.z.ai — MCP server (12 tools), local vector memory, token saver, smart skills, GitHub private-repo cloud DB. Built with GLM 5.3 Flash.

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.