MCP-enabled AI conversation engine with MCTS analysis, FastAPI backend, and async operations for building advanced LLM applications

DevContext is a cutting-edge Model Context Protocol (MCP) server designed to provide developers with continuous, project-centric context awareness. Unlike traditional context systems, DevContext continuously learns from and adapts to your development patterns and delivers highly relevant context providing a deeper understanding of your codebase.

It is a simple, fast, and hard-durable embedded database designed specifically for AI agent memory. It provides a single-file-like experience (no server required) but with native support for vectors, graphs, and temporal search.

Cursor10x is a comprehensive suite of tools that enhances the A.I. agent's capabilities within the Cursor IDE, providing persistent memory across sessions, standardized task management, and enforced best practices through cursor rules.

ATM-Bench: A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data (images, videos, emails). Features referential queries, evidence-grounded answering, and multi-source reasoning. Paper: "According to Me: Long-Term Personalized Referential Memory QA"

PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory

memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown files

Decentralized memory-sharing protocol for AI agent

Embedded database for agentic memory — relational, graph, and vector under unified MVCC transactions

A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten

Unified memory for all your A.I. agents. Knowledge graph hybrid retrieval of important context.

FalkorDB graph store plugin for Mem0

Treating AI agent memory as a living, evolving system rather than a database. It forgets, consolidates, detects contradictions, abstracts patterns, and retrieves differently based on context - inspired by how the human brain actually works.

Stop your AI agent from repeating same mistake and learn from previous failures

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

Portable Agent Memory. Connect your AI conversations. Remember everything. Everywhere.

OpenClaw + Mem0 + FalkorDB — Persistent Graph Memory for AI Agents

LangGraph integration with Kusto as the persistent memory layer

Belief-centric memory AI — chat, extract beliefs, build a knowledge graph about yourself.

Offline-first cognitive operating system for synthetic intelligence. Features belief ecology, RL-based goal evolution with differential privacy, contradiction tracing, HMAC-signed audit logs, sandboxed execution, and local LLM inference. Designed for air-gapped, adversarial environments.