Tag
The article describes Skynet, an Elixir-based framework using OTP GenServers to build persistent cognitive architectures for LLM agents. It implements a layered memory stack inspired by neuroscience, addressing the amnesia problem in long-running agents.
An open-source persistent memory layer for AI coding agents that stores and retrieves project decisions and context using Postgres and pgvector, aiming to reduce context window size and improve agent consistency.
Hermes Agent by Nous Research is an open-source autonomous AI agent that runs persistently on a server, remembers every conversation across sessions, and autonomously creates skill files, making it a fundamentally different category of agent compared to session-based coding tools like Claude Code and Cursor.
Introduces an open-source tool that provides persistent memory for Claude Code, avoiding context limits and significantly reducing token consumption.
The article introduces Hermes Agent as a persistent, 24/7 AI operations officer, distinct from Codex/Claude in positioning, emphasizing automation, memory, and remote command capabilities, representing the evolution of AI agents from tools to partners.
Intel's discontinued Optane persistent memory technology is finding a second life in AI workloads, enabling a user to run a 1 trillion parameter model locally at ~4 tokens/second using cheap second-hand Optane modules. The article highlights Optane's lower latency compared to SSDs, making it suitable for large model inference despite being slower than DRAM.
ArcRift is a local-first AI memory layer that shares persistent memory between browser chats and IDE tools via a Chrome extension and MCP Server, avoiding repeated context explanations.
The author tested Persistent Sage's long-term memory feature, finding it accurately recalled personal facts like colorblindness and a spouse's name from a week earlier without explicit prompting, demonstrating effective persistent memory for AI agents.
Maven is an open-source personal AI agent harness that runs locally or on personal hardware, featuring persistent memory, modular extensions, and proactive task management for a JARVIS-like experience.
Hexis is an open-source Postgres-native cognitive architecture that wraps any LLM to provide persistent memory, autonomous behavior, and identity, enabling agents to remember and pursue goals across sessions.
Anthropic is planning a major memory update for Claude, introducing a dual-mode system with Memory Files that distribute user notes across structured documents by topic, potentially enhancing persistent memory for Claude Managed Agents and related features like Dreams and Conway.
This thread argues that AI's fundamental problem is memory, not intelligence, and highlights GBrain as a system designed to provide persistent, synthesizing memory for AI agents, featuring uncertainty surfacing and biological-like memory consolidation during sleep.
Anthropic AI engineer demonstrates a free 4-step method to give AI agents persistent memory across sessions, including memory stores and dreaming, achieving 95% cache hit rate.
A guide on setting up persistent memory for Codex using Obsidian by copying a prompt and custom instructions for the AI assistant.
gBrain is an open-source persistent memory layer for AI agents that ingests daily signals like emails, meetings, tweets, and docs into a typed knowledge graph, using Markdown, Postgres, and pgvector for hybrid retrieval.
AI memory systems often recall outdated or incorrect information over time, highlighting the challenge of maintaining trust in long-term memory for AI agents.
A developer introduces Invoko, an AI assistant for Mac that maintains persistent context via a local 'soul.md' file, eliminating the need to re-explain projects and preferences across sessions.
A critical take arguing that so-called 'persistent memory' in AI agents is merely sophisticated retrieval, not actual memory or state, questioning what real persistent memory would look like.
agentmemory is an open-source tool that provides persistent memory for AI coding assistants. It silently records code changes and context, automatically extracts and compresses them into structured memory, reduces Token consumption, and supports multiple mainstream platforms such as Claude Code and Codex.
Hermes Agent is an AI agent tool with 140k+ GitHub stars, top-ranked on OpenRouter, featuring one-command setup, persistent memory, and evolving agents. A beginner walkthrough explains the setup in under an hour.