Havuz

我们的港湾

Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

Local-first memory engine for AI agents

Create an AI friend and build things together!

A quiet, layered memory engine for long-term human-AI relationships.

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

Dialogue memory for AI agents (hermes plugin): auto-recall of facts across sessions, LLM fact extraction with a cheap gate, SUPERSEDE versio

Keep your decisions, projects, and context when you switch between Claude Code, Cursor, opencode, and the rest — one plain-markdown bundle i

Give Claude Code a persistent memory — it remembers you, your projects, and your decisions as plain Markdown files you own. Fully local. Jus

Mine your Claude Code and Codex logs into a local you.md agent profile.

AI agent memory you can trust

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no

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

Engram Alpha - Inspectable graph memory for AI coding assistants

Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as E

Give your AI a memory, habits, and a daily routine — with nothing but files. One-line setup for Claude Code and Codex CLI.

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.

Shared memory for Claude Code, Codex, and Cursor. Your agent recalls decisions from weeks ago — including what the other engines worked out.

Executable memory & cognitive harness for AI agents. Let your agent learn, remember, and build its own guardrails.

Knows your world. Answers to you. — the open-source personal AI agent you own.

🏛️ Memory OS for AI agents — every conversation becomes a catalog card (archive no · entities · evidence · trace back to the transcript). Fo

Cognee Rust - fast and performant AI memory engine

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No

A lightweight memory engine for AI agents using fuzzy graphs, Hebbian updates, and optional LLM gating.

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

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

Four local, file-based MCP servers for solo devs/vibecoders: persistent memory, session handoff/resume, file checkpoints, token-efficient pr

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clie

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

An LLM-powered social simulation and roleplaying engine where NPCs have their own lives too.

Salience-aware lexical trie for long-context compression.

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summari

Memory for your AI work across projects and sessions. Save decisions, rules and lessons with source and applicability. Connect over MCP.

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

A living local memory layer for your coding agents and AI tools.

Ground LLM output as provenance-tracked claims, not truths. A maximal super-ontology + native RDF-1.2 logic: reasoning engine — OWL, SHACL,

Memory OS, Hermes Agent için konuşmalar arasında kalıcı hafıza sağlayan ve ilgili bağlamı gerektiğinde prompt’a ekleyen yerel bir yazılım altyapısıdır.

Neden yükseliyor · 119 günde 1372 yıldız, projeye belirgin bir ilgi olduğunu gösteriyor. Ancak bunun nedenini veya yıldızların ne kadar yakın zamanda geldiğini verilen verilerle belirlemek mümkün değil; son 28 günde commit ve farklı yazar sayısı sıfır. README’deki kurulum kolaylığı ve çok katmanlı yaklaşım ilgi çekici olsa da benimsenme ve güncel bakım kanıtı olarak tek başına yeterli değil.

Source-backed feature comparison of memory systems for AI coding agents. No affiliation, no marketing — just facts from public docs.

Open-source CLI and Agent plugin suite for EverMe — cross-device, cross-Agent personal memory for AI Agents.

Precision-aware retrieval benchmark for LLM memory systems.

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

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

Storage engine for AI agents to navigate, store, and retrieve structured data. PostgreSQL ltree, built-in versioning, scoped queries.

A self-improving memory layer for Claude Code: captures every session, distills them nightly into a versioned knowledge vault, and surfaces

Claude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.