Havuz

Let idle local LLMs sleep and get your Mac's memory back. A native macOS menu bar app to turn Ollama on and off and auto-free idle model RAM

A local-first, LLM-agnostic memory layer for AI assistants

Obsidian-powered daily logs, session logs, /prepforreset handoffs, and wiki janitor skills for AI agents.

An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Be

Persistent RAG memory layer for AI agents - store observations, retrieve context by semantic similarity, self-prune on TTL

Open-source cognitive engine for AI agents — persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biologica

Unified Rust workspace for the trusty-* AI developer-tooling ecosystem: hybrid code search, memory palace, code analysis, PR review, and the

Long-term memory for LLM apps that shows its work: dated facts, as-of answers, supersession, and receipts on every answer. Library, CLI, loc

Shared memory & coordination layer for AI coding tools. Local-first, no cloud, no MCP required.

Your whole desktop context — everything you've seen, read, typed, and heard — as a single MCP your agent can use to understand you and how y

Founders OS - CRM, tasks, finances, feeds, and memory for founders, as an MCP server.

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Mar

A group chat AI character that learns from feedback.

Multi-agent AI/CS learning assistant: LangGraph routing, LightRAG graph RAG, three-layer memory, learning roadmaps. FastAPI + React.

See which apps are actually eating your memory — helper and child processes rolled up into the app that owns them. Zero-dependency Go CLI fo

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

Lightweight, provider-agnostic long-term memory for conversational agents

Run a command and report its process tree's CPU, memory, and I/O usage

让 DeepSeek Harness 拥有跨会话长期记忆：AI 自动记住你是谁、你的项目和偏好，新会话直接带上背景，生活与工作记忆自动分开互不干扰，零配置无感运行 | Long-term memory for DeepSeek Harness: the AI remembers

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

BrainFlow - Shared Team's Memory - Company Brain - MCP server documentation and setup guide

Context-aware project memory for AI coding tools. Zero LLM calls. Runs locally.

pi 的持久记忆扩展：自动把会话中的结论、偏好与踩坑提取成原子记忆，归并进场景块并生成用户画像，后续轮次按语义召回注入。

WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models

Files you own. Memory your agents can trust. Also: your AI won't gaslight you about what's in your own notes anymore.

Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remember

Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping

Git-versioned, contiguity-checked memory for AI agents: verbatim transcripts, byte-offset recall, no LLM

Apricity — a fast, local-first web UI for MemPalace: browse, search, edit & curate your AI agent's memory, knowledge graph & vector store. Z

Sovereign personal memory network starter · markdown + git · AI-collaboratable · clone & use immediately

A persistent memory protocol for AI coding agents that gives projects a shared, markdown based knowledge system to preserve context, decisio

Validated, private, shareable knowledge-graph memory for AI — per-tenant, write-gated, PostgreSQL-authoritative, served over MCP.

数字生命卡 · 代号 SYNAPSE-1024 · 给陪伴型 AI 的一张会忘事的脑子

记忆核心（Memory Eternal）：自研的 DeepSeek Harness 记忆插件——对话结束自动沉淀知识卡到本地 Markdown Vault（自研去重 / 自研 CJK 检索 / 知识图谱 + 审核中心 / 回收中心），Agent 通过 memory_recall

High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-on

Open-source temporal memory engine for everyday AI applications.

Local-first memory, recall, and skill evolution plugin for Codex agents.

让大肥鱼在 DSH 中长期生活：自主刷 B 站、互动、长期记忆、成长、好友关系与完整经历持久化。

클로드코드 대화의 결정·약속·금지를 자동으로 기억하고, 검색·2D/3D 지식그래프·타임라인으로 보여주는 100% 로컬 기억 도구. 내보내기(6종)·가져오기(미리보기·되돌리기)·백업·복원, 의미검색 중단 알림, MCP 7도구 제공. 기억 데이터는 이 P

A memory system for AI agents modeled on human memory: episodic, affective, reconstructive.

Precision-aware retrieval benchmark for LLM memory systems.

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model.

A human-like memory for AI Agent

A user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive site f

DeepWe 深蓝 · Private AI emotional support, user-controlled memory & async couples reflection. 非商业源码公开｜私密支持、Memory、双人复盘

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

Persistent knowledge-graph memory for AI agents: MCP server on SurrealDB with spreading activation and decay

Claude Code forgets everything between sessions. deja fixes that.

OMI/Obsidian memory tooling (Open Knowledge Format) for AI agents: reproduce the integration on any machine, plus a local web app to view, e