Agent Memory Server (AMS)

ai-memory is an open-source local server for long-term memory and session handoff among AI coding agents. It captures prompts, tool calls, and agent context through MCP integrations and lifecycle hooks, storing the material in a searchable, Git-backed Markdown wiki. When a session ends or is explicitly finalized, it generates handoff context for a subsequent session, including the project architecture, failed approaches, and open questions, so work can continue across agent vendors without restating the context; clients without a true session-end hook use explicit finalization commands. The project documents integrations for Claude Code, Codex, Command Code, Devin CLI, OpenCode, Cursor, Gemini CLI, Oh My Pi, Pi, and Crush, with agent-specific configuration, generated plugins or extensions, and capture exclusions. It runs on Linux, macOS, and Windows through WSL2, with experimental native Windows support, and is distributed through Docker images and native release binaries.

agent-memory is a local-first, agent-agnostic long-term memory runtime for AI agents. It stores memories as plain Markdown files, with a rebuildable SQLite index used as a cache rather than the source of truth. Conversation-boundary hooks trigger writes, while an independent sleep-time Manage pass consolidates, ages, and forgets memories by value; unattended deletion is limited to proposals that require confirmation, and superseded or archived material remains available. The runtime provides three recall paths: deterministic MEMORY.md injection at session start, BM25 search with progressive disclosure, and direct access through the store's directory tree using tools such as ls and grep. Memory records use frontmatter for names, abstracts, status, timestamps, links, weights, and provenance, with free-form Markdown bodies. Its CLI, MCP server, and host-agent hooks share the same validation, hash-diff, and reindexing path, and it can be used by agents that run shell commands, including Claude Code and Codex CLI. The repository documents a Python 3.12-or-later setup using uv, commands for initialization, recording, recall, rebuilding, sleep-time consolidation, and proposal approval, plus host setup for Claude Code and Codex. It does not include an LLM client; reasoning is delegated to the host agent's CLI, so the library requires no separate model keys or billing surface.

Supermemory is an AI memory and context engine with a hosted API, application, plugins, MCP server, and local runtime. It extracts facts from conversations, tracks temporal changes and contradictions, automatically forgets expired information, and maintains user profiles containing stable facts and recent activity. Its API combines memory retrieval with hybrid RAG search, allowing applications and AI agents to query personalized context and knowledge-base documents together. It also processes uploaded PDFs, images, videos, and code, and can synchronize data from services such as Google Drive, Gmail, Notion, OneDrive, GitHub, and web pages. SDKs are available for JavaScript and Python, with integrations for AI frameworks including the Vercel AI SDK, LangChain, LangGraph, OpenAI Agents SDK, Mastra, Agno, and n8n. Supermemory can provide persistent memory to compatible assistants through plugins or its MCP server. The local distribution runs as a single binary or through npx, uses local embeddings by default, supports OpenAI-compatible and Ollama-backed models, and exposes the same Memory API on localhost for offline or self-hosted use.

NAMS is a hosted, graph-native memory service from Neo4j Labs for LLM agents. Backed by Neo4j Aura, it captures messages, entities, tool calls, and reasoning traces into workspace-isolated graphs, with short-term conversation memory, long-term knowledge, synthesized observations, entity merging, hybrid vector and text search, and REST and MCP interfaces. Agents connect with a workspace API key, after which NAMS extracts and embeds memory automatically and supports graph, semantic, and three-tier context retrieval. Its skill-distillation feature runs a seven-stage Scope → Extract → Consolidate → Synthesize → Gate → Package → Publish pipeline that turns a scoped portion of the memory graph into a signed, provenance-grounded SKILL.md package. The process includes grounding, coverage, specification linting, PII redaction, human sign-off, typed procedure graphs, cryptographic attestation, composition of shared sub-procedures, and drift detection for stale or contradicted claims. A dashboard provides workspace and skill-distillation interfaces; the service also offers plugins for Claude Code, Gemini CLI, Codex, and OpenCode, and supports bring-your-own LLM keys or an external Neo4j deployment.

Neo4j Agent Memory is a graph-native memory system for AI agents developed as a Neo4j Labs project. It stores conversations and messages as short-term memory, builds long-term knowledge graphs using the POLE+O model, and records entities, relationships, reasoning traces, tool usage, decisions, preferences, and facts for later retrieval. The system combines vector and text search, entity resolution and deduplication, similar-task retrieval, multi-stage entity and relationship extraction, background enrichment, and geospatial queries. Python and TypeScript clients support hosted NAMS usage or direct connections to Neo4j and Neo4j AuraDB through Bolt. An MCP server exposes capabilities for searching memory, retrieving context, storing messages, managing entities and preferences, inspecting graph data, and recording reasoning. Neo4j Labs describes it as actively maintained but not officially supported.