Havuz

VoiceMem, voice agent’lara ses ve metinden bilgi ile duygu odaklı uzun süreli bellek sağlayan bir Python kütüphanesidir.

Neden yükseliyor · 41 günde 2.111 yıldız alması görünür ilgiye işaret ediyor; son 28 gündeki 49 commit ve 5 farklı yazar da geliştirme faaliyetinin sürdüğünü gösteriyor. Ancak yıldızlar gerçek kullanımın veya performans iddialarının doğrulaması değil.

Memanto, farklı AI agents arasında kalıcı bilgiyi derleyip güncel tutmayı ve ihtiyaç anında paylaşmayı amaçlayan bir memory agent sistemidir.

Neden yükseliyor · Veriler güçlü bir yakın dönem geliştirme hareketliliğine işaret ediyor: 28 günde 123 commit ve 46 farklı yazar. 192 günlük yaşı için 2306 yıldız da dikkat çekici; ancak bu ölçümler ilginin nedenini veya gerçek kullanım yaygınlığını tek başına açıklamıyor.

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

神经元记忆网络 让 DSH 记住「为什么这么决定」，而不只是结论。思维链记忆插件：8 个池分级遗忘、每轮注入、神经元 3D 星云浏览、夜巡自动整理。

A powerful browser extension that supercharges DeepSeek Chat with custom tooling, persistent memory, and seamless project scaffolding. Gener

LLM agent 的有界自纠错长期记忆层：把连续、含矛盾的项目交互日志蒸馏成有界、可自更新的记忆库。Bounded, self-correcting long-term memory for LLM agents — candidate pool + value dynamic

Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

A linked-list discipline for knowledge, memory and pointer hygiene in large projects: five laws plus portable Python engines (declarative ru

Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.

MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib

玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置

Free, open-source CleanMyMac alternative for macOS. Preview disk cleanup by path and size, inspect memory by app, and quit idle apps after r

Shared memory across your team and your AI agents — with judgment about what's worth keeping.

Free, open source Mac menu bar app for memory and disk. See what uses your RAM, keep a week of history, pause idle apps, find large files, a

Local-first MCP memory server for AI agents. Zero dependencies, SQLite on your own disk, 52 MCP tools with Mem0-compatible names. MIT.

Convert Hermes / OpenClaw agent memory (JSONL sessions, MEMORY.md) to markdown for gBrain ingest

TERSE - a hierarchical state language for humans and AI agents.

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

AI remembers, you find. File-based long-term memory and project maps for any AI coding tool, plus a zero-dependency governance CLI for chang

Engram Alpha - Inspectable graph memory for AI coding assistants

The open engine behind Aedelgard: a persistent, self-hosted AI agent with a verbatim memory palace and a model-agnostic brain. Swap Claude,

🏗️ AI Agent 九维基础设施框架 - 9个架构维度、11个插件、21个Hooks、30条基准评测

Your AI finally remembers your codebase

The open memory layer for collective agent awareness — a vendor-neutral MCP service for shared AI-agent memory.

Durable, repo-native project memory for coding agents, without context bloat.

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team co

QiJu(起居) Local-first, lossless session records for AI coding agents.

Framework-agnostic, local-first memory lifecycle for AI agents: Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve a

SGME 拾光记忆引擎：AI 全面接管记忆、技能库、WIKI 知识库三大模块，跨会话、多智能体共享记忆，AI 会一直记得你的偏好。ShiGuang Memory Engine · AI takes full charge of three core modules — memor

Memory layer for AI Agents and OpenClaw powered by Rust

A desktop workspace for coding agents: browse local session history, chat with agents live, and orchestrate multi-agent threads.

🌀 MUSE — Memory-Unified Skills & Execution. A pure-Markdown OS for AI pair programming with lossless cross-conversation context management.

A modular C++ CLI tool demonstrating dynamic memory allocation, strict pointer manipulation, and safe resource management.

Battle-tested utilities for AI coding assistants. Self-guard hooks, memory GC, pitfall tracking.

Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Op

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

MCP-compatible context and memory system: paged code navigation for AI assistants, plus a recorded, verified theory of what is known about t

SOUL.md governance framework for Hermes Agent — structured memory, skill management, and operational rules

A human-like memory for AI Agent

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

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

Agentic Memory System records work performed into strict schema making it actionable