Search awesome repositories

Universal memory layer for AI Agents

The best-benchmarked open-source AI memory system. And it's free.

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

#1 Persistent memory for AI coding agents based on real-world benchmarks

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Hindsight: Agent Memory That Learns

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

Memory for 24/7 proactive agents like OpenClaw.

Agent S: an open agentic framework that uses computers like a human

Cross-platform lib for process and system monitoring in Python

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

Your favorite self-hostable alternative to Google Timeline (Google Location History)

Self-evolving memory across Agent and platform.

Your super agent for work: local-first, learn your working context in mins and never forget it.

MimiClaw: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Agent Skills as a Memory Layer

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

An open source approach to locally record and enable searching everything you view on your Mac.

Free system monitor for OSX and macOS. See all system information at a glance in the menu bar.

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Research project. A Memory solution for users, teams, and applications.

The paper list of "Memory in the Age of AI Agents: A Survey"