Tag: #agent-memory
20 packages • ⭐ 36,858 total stars
Memori is agent-native memory infrastructure. A SQL-native, LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
A lightweight, lightning-fast, in-process vector database
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
Memory library for building stateful agents
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Compact, efficient, and extensible long-term memory for LLM agents.
OpenCode plugin for Magic Context — cache-aware infinite context, cross-session memory, and background history compression for AI coding agents
The Mind Palace for AI Agents — Autonomous Cognitive OS with affect-tagged memory (valence engine), token-economic RL (surprisal gate + UBI), Hebbian learning, ACT-R spreading activation, Synapse Engi
Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git sync.
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
Multi-agent memory consistency platform. We're hiring contributors—check HIRING.md
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.
Self improving agents through iterations
The memory system your AI agent deserves. 4-stage hybrid retrieval — Vector + BM25 + Knowledge Graph + Neural Reranker — in <150ms. Self-hosted, $0/query, built for agents that need to actually rememb
AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.
Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.
Enable AI agents to autonomously create, evaluate, and evolve skills across any marketplace without user intervention.