AI memory
Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)
An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
Signed multiplicative key lifts for fixed-state sequence memory
Sistema de memoria local ultra liviano y portátil para Agentes de IA en Antigravity, VS Code y entornos Agentic
AI-powered Incident Response Agent that analyzes production errors, uses Hindsight persistent memory to recall similar past incidents and solutions, and recommends effective actions based on historical outcomes.
Open apparatus and preliminary results for controlled coding-agent memory evaluations
Layered persistent memory plugin for OpenCode — user preferences, project conventions & past lessons survive across sessions. Ported from Hermes agent. No vector DB, pure Markdown.
Claude Code skill: audit auto-memory by cross-verifying against live state, delete resolved incidents instead of annotating them
让 AI 编码助手从每次任务中自动学习、沉淀技能与记忆的开源系统（The agent that grows with you）— Pi / Claude Code / Codex
A local-first, Markdown-native blueprint for shared AI-agent memory, project handoffs, governance, and safe session closeout.
Self-hosted, multi-model AI companion for Web and Android with memory, voice, proactive messages, and account-isolated data.
Pi extension that reads and writes Claude Code's own memory store — one store, two agents, no sync step
Configurable AI agent orchestration, delegation, memory, and project context through MCP.
A cache-aware attention and forgetting layer for high-frequency everyday AI chat.
The coding agent that remembers your repo. CLI, gateway, one wire. Self-hostable, MIT.
Persistent memory for AI coding agents. MCP server + lifecycle hooks that give Claude Code, Codex and Cursor long-term memory across sessions — one Rust binary, one local SQLite database, no server.
.mctx is a token-optimized file format for AI persistent memory — a coding agent's long-term memory across sessions and context-window resets.
Living structure-aware code memory for AI coding agents
White paper: durable research memory on medium GPUs (≤24GB) — waste, verify, negative memory complementary to soft hubs