graphiti 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
时尚的图表API
macOS 和 Linux 上的 Swift GraphQL 实现
The Swift GraphQL Schema builder for macOS and Linux
Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
MiroFish的免费本地运行版本 | Graphiti+Neo4j替代付费Zep | 简易便捷本地跑通
Graphiti MCP Server
Easy setup of a GraphQL server with Vapor. It uses the GraphQL implementation of Graphiti.
基于 OpenClaw 的混合内存系统，使用 Graphiti 时间知识图谱
Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.
我们认为每个SOTA结果仅在其自身数据集上有效。RAGView提供了一个统一的评估平台，用于针对您的具体数据进行不同RAG方法的基准测试。
Transform your Obsidian vault into a powerful knowledge graph with MCP support
Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.
DataLoader is a generic utility to be used as part of your Swift application's data fetching layer to provide a simplified and consistent API over various remote data sources such as databases or web services via batching and caching.
Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.
Graphiti-based knowledge graph memory extensions for Open WebUI
AI-Generated AI Roleplay Simulator — 互动叙事与多智能体模拟引擎
This repo demonstrates Graphiti MCP integration with Cursor and Neo4j, storing AI prompts as real-time knowledge graphs for persistent memory.
Temporal knowledge graph memory plugin for OpenClaw — auto-recall & capture via Graphiti + Neo4j
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source, human-ratified. Recommended engines: Graphiti (server), LadybugDB (embedded).