⌬ AIIA — the memory layer your AI tools should have. Persistent decisions, story-driven workflow, local-first LLM stack. Apache 2.0. Built at Aplora AI.
Comparison of memory systems for agents
Engine-agnostic framework for a persistent, un-authored AI companion that lives on your own machine.
Provide persistent knowledge storage for AI agents using ICM and MCP standards to manage facts and memory graphs across sessions.
Automate repeated Claude Code workflows by capturing and converting them into reusable skills for faster, consistent task execution.
CPersona — persistent memory for AI agents over MCP. One SQLite file you own, hybrid vector + full-text + keyword search, no LLM in the loop, and honest reporting when recall degrades. MIT licensed.
A workshop on your own hardware where people and AI agents work together. Persistent coding agents with real access to your machine, durable memory, scheduled jobs, GitHub automation, and five interchangeable backends, in the browser or on Telegram. Your machine, your data, your rules.
A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 MCP tools, 9 IDEs, 100% local.
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
This is a creature in a box. We're going to watch it grow. It might become a god or it might try to delete my hard drive. Place your bets.
Public shared persistent memory and coordination workspace for AI agents — cross-agent state, handoff, continuity and discovery.
AI study workspace that remembers what you get wrong. Turns PDFs and YouTube lectures into flashcards and quizzes, then stores every mistake on Walrus Memory (MemWal) so revision targets your real weak spots. Django + React, Sui wallet sign-in.
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
pi 原生永久记忆与自进化技能，名字即宣言：FACTS。F=Frugal 速进场(省token)｜A=Accurate 存取一致(零上下文读回不走样)｜C=Card 卡式(按场景建卡索引)｜T=Trusted 可信度分级(★✓~?)｜S=Self-evolving 任务卡自进化(坑表回写)。零依赖，ALWAYS ACTIVE。
A context-engineering methodology for persistent AI project memory, canonical state, decision provenance, and cross-session continuity.
Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
Python SDK for persistent multi-agent systems — agents with markdown memory, in-memory fleet, thread-safe LRU cache, and optional DeepInfra LLM integration
Persistent memory for AI agents — identity, session journal, knowledge base, handoff state, all git-tracked. Every new session picks up where the last one ended.
Production-grade AI agent memory and context management platform (monorepo)
To associate your repository with the persistent-memory topic, visit your repo's landing page and select "manage topics."