Neo4j Agent Memory Service (NAMS)

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.

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ages, and forgets memories by value; unattended deletion is limited to proposals that require confirmation, and superseded or archived material remains available.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.

Agent Memory Repo is an open standard and agent skill for carrying context between coding-agent sessions in a separate Git repository. Agents load a short MEMORY.md entry point, follow links to Markdown notes, projects, queries, and scripts, then update and commit memories as they learn. The repository can support personal memory, shared team knowledge, and agent swarms; Git provides version history and flags conflicting edits when multiple agents update the same files. The skill can be installed for Devin CLI or through the skills installer for Claude Code, Cursor, and other agents, and requires Node.js and Git for the latter. A separate persistent local or remote repository is needed for memory across machines or cloud sessions. The specification was developed by Cognition, is open to ecosystem contributions, and is licensed under MIT.

Agent Memory Server (AMS) is an open-source memory server built on Redis for AI applications. It provides short-term session memory and long-term vector memory, with support described in the source material for multi-tenant post-filtering, query compression, few-shot examples, reranking, summarization, token-window management, and semantic caching. It was used behind an Alexa skill to test memory handling in an assistant under an eight-second response constraint.

TencentDB Agent Memory is a self-hostable, team-level memory hub for AI agents. It extracts conversations and tasks into reusable Chat Memory and Skills, and converts documents and code into an LLM Wiki and CodeGraph. These assets can be reviewed, versioned, governed, shared, routed, and reused across agents, frameworks, and team members; existing documents, codebases, and agent sessions can also be imported to reduce cold-start work. The system provides a shared memory server and a proxy that preserves the agent protocol, so supported clients can use the same memory by pointing their base URL at the proxy without plugins, hooks, or an MCP server. The repository deploys memory-core, memory-hub, and the proxy together, with a local management panel and configuration for separate memory and proxy LLM parameters. Documented integrations include DeepSeek Harness, Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes, and OpenClaw.