Framework-agnostic memory layer for AI agents. Multi-signal retrieval, conflict detection, typed decay, checkpointing. Zero dependencies.
Agentic memory for AIGNE framework
OpenClaw memory and context-engine integration for Agentic Memory
Agentic memory manager. Best used with skill: npx skills add meharajM/agent-loop-mcp
Official Node.js SDK for Agentic Memory — persistent memory for AI agents
MCP server for Hydra DB: State-of-the-art agentic memory with recall, ingest, and knowledge graph context
Git-inspired agentic memory system — library + CLI
Self-hostable agentic memory for production agents — PRISM-based recall, calibrated decay, audit trail. Node.js bindings for the memgc Python library.
Long-Term Agentic Memory SDK for TypeScript/JavaScript
AMP (Agentic Memory Protocol) CLI - Terminal interface for AI agent memory management
Self-hosted agentic memory MCP server backed by Qdrant, inspired by supermemory. Provides semantic memory storage, entity/relation knowledge graph, and optional reranking as MCP tools.
OpenCode plugin for persistent memory using Mem-Brain - an agentic memory system with semantic search and graph relationships
OpenClaw plugin for Cortex AI — the State-of-the-art agentic memory system with auto-capture, recall, and knowledge graph context for open-claw
OpenClaw plugin for Hydra DB: The State-of-the-art agentic memory system with auto-capture, recall, and knowledge graph context for open-claw
Reactive state management with streaming operators, glitch-free diamond resolution, and an inspectable graph. 6 primitives, 70+ operators, framework-agnostic. Supports LLM token streaming, edge AI orchestration, durable workflows, and agentic memory.
WebAssembly bindings for agentic-memory — graph-based cognitive memory for AI agents
TypeScript/JavaScript SDK for the Mimir agentic memory system — archive and search with bitemporal guarantees
Universal memory layer for agentic AI tools - store and retrieve past conversations, solutions, and context
Zero-dependency, in-memory vector database for AI Agents. Supports Cosine Similarity and Persistence.
Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,
MCP server for Cortex AI — State-of-the-art agentic memory with recall, ingest, and knowledge graph context
Agentic memory framework for coding agents, business agents, and personal assistants
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
CLI and SDK for Axoniac agentic memory store
Binary graph-based memory system for AI agents
MCP server for AgenticMemory - universal LLM access to persistent graph memory
CLI tool for AgenticMemory
FFI bindings for AgenticMemory
LEX agentic memory domain: episodic, semantic, and working memory
Hierarchical persistent memory with semantic search for SwarmSDK AI agents
Memory infrastructure for agents: short-term checkpointing, long-term file-based and graph-based memory, retrieval with time decay, and maintenance jobs.
Agentf is a Ruby-native multi-agent workflow engine with an ORCHESTRATOR, role-specialized agents, provider adapters (OpenCode/Copilot), and Redis-backed semantic, episodic, and graph-style memory. It includes a unified CLI, MCP server tools, and install/update workflows for generated agent/command manifests.
SmartBrain provides commit_turn and compose_context APIs for agent memory, retrieval planning, evidence fusion, and context assembly.
Claw is an Agent framework built on ruby-mana. Adds interactive chat, persistent memory with compaction, knowledge base, and runtime state persistence.
Agent for the GC tuning webservice https://www.tunemygc.com - optimal settings for throughput and memory usage of Ruby applications
Funes provides an intelligent memory layer and knowledge base interface for AI agents, enabling persistent context storage and retrieval through a command-line interface.
A Fuzzy Associative Memory (FAM for short) is a Fuzzy Logic tool for decision making. Fuzzy logic FAMs have a wide range of practical applications: Control systems, such as governing a fan to keep a room at the "just right" temperature; Game AI, such as imbuing bots with human-like decision-making behavior; Prediction systems, linking causes with effects. A FAM uses Fuzzy Sets to establish a set of rules that are linguistic in nature. The linguistic rules, and the fuzzy sets they contain, are defined by a human "expert" (presumably, you). The rules therefore codify intelligence and map this knowledge from the human domain to the digital.
Short-term active maintenance of task-relevant information with capacity limits, decay, and rehearsal
T-cell/B-cell persistent threat recognition with secondary response amplification for the LegionIO cognitive architecture
Provision and interact with AI agents on agentd.link via a simple Ruby API or CLI.
No description provided.
No description provided.
No description provided.