Tag: #memory
38 packages โข โญ 23,621 total stars
Hindsight: Agent Memory That Learns
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
Conversation memory SDK โ query meeting transcripts, decisions, and action items from any AI agent or application
OpenClaw Supermemory lets to have long-term memory and recall for your openclaw agent.
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.
Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.
Give your AI agents persistent memory.
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other
Compact, efficient, and extensible long-term memory for LLM agents.
Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).
Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB โ just markdown + git sync.
Memory that remembers the story not just the facts. Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.
Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
Lightweight persistent memory system for Claude Code โ FTS5 search, episode batching, error-triggered recall
Personal OS agent that learns who you are, detects life patterns, and grows smarter about you every day. Memory + Cron + Atropos RL
A highly customizable personal AI assistant for Discord featuring smart agentic AI features such as memory, personas, tool usage, and more! ๏ฝ ้ทๆ่จๆถใใใซใฝใใใใผใซ้ฃๆบใๅฎๅใ ๆฌกไธไปฃใฎใ่ชๅพๅAIใจใผใธใงใณใใDiscordใใใ๏ผ
Description: Self-hosted graph-based associative memory for personal AI agents. Spreading activation, emotional weighting, zero LLM cost.
Modular multi-agent orchestration framework powered by LangGraph and FastAPI.
Multi-agent code review mesh โ orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch r
Hermes Agent rewritten in Rust: production-grade multi-platform AI agent runtime with gateway adapters, tool orchestration, MCP, memory plugins, and cost-safe autonomous loops.
Graph-based workflow enforcement and persistent memory for AI coding agents. Define structured workflows in YAML. Enforce them at tool boundaries via MCP. Build a persistent knowledge graph that grow
๐ ๏ธ Simplify your tasks with MineContext, an open-source AI tool that provides context-aware support for clarity and efficiency in work and study.
Track and manage AI personality changes, rules, and memories with full version control and easy reversibility.
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
An AI guardian that remembers, watches, and acts.
Multi-agent memory intelligence layer โ shared knowledge, expertise tracking, and conflict detection for AI agent teams
Persistent memory layer for AI agent workflows
Persistent structured memory for AI agent systems โ pluggable SQLite or Postgres backend, LLM context bridge
AI agent in your terminal โ 3-tier memory, 16 tools, automation pipeline, bring your own model. Learns who you are, remembers across sessions.
Local-first AI agent runtime. One command, your machine, your data.
TypeScript SDK for MemLib โ AI agent memory API
Context window auto-manager for free AI agent users. Your 200K context, maximized.
Long-term memory system for OpenClaw AI Agent
12 native protocol layers for AI-agent systems. No wrappers. No SDK dependencies.
Folder-as-neuron brain for any AI agent. mkdir replaces system prompts.