# TencentDB Agent Memory

A shared, team-level memory hub for AI agents that turns conversations, documents and code into reusable memory assets, shared across agents and frameworks through one proxy.

TencentDB Agent Memory is a team-level memory hub for AI agents. It turns conversations, documents and code into four reusable memory assets, described as Chat Memory, Skill, LLM-Wiki and Code-Graph, that are governed, shared and equipped across agents and frameworks, so project context and previously read documents do not need to be rediscovered in a new session.

All supported agents share the same memory server through one proxy: pointing an agent's base URL at the proxy is enough, with no plugin, hook or MCP server required. Supported agents and frameworks include DeepSeek Harness, Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes and OpenClaw, with a generic integration guide for others.

It installs by starting three services together, memory-core, memory-hub and a proxy, configured through an environment file, and includes an optional, off-by-default MongoDB storage backend and a data migration tool for upgrading from older versions. It is written in TypeScript.

Website: https://github.com/TencentCloud/TencentDB-Agent-Memory