TencentDB Agent Memory: memory tool for Hermes Agent

Team-level memory hub that shares chat memory, skills, wiki and code graph across agents through a proxy

What TencentDB Agent Memory does

TencentDB Agent Memory turns conversations, documents and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki and Code-Graph. The assets are meant to be governed, shared and reused across agents and frameworks. The default install starts three services, memory-core, memory-hub and a proxy, and opens a panel at http://localhost:8125.

Integration works through the proxy: you point an agent's base URL at it, and no plugin, hook or MCP server is required. The README lists DeepSeek Harness, Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes and OpenClaw, and links a generic integration guide for other platforms. It labels Team Memory as Beta and the MongoDB storage backend as experimental and off by default, and provides a migration tool for data from older v1.x and v0.x releases.

Key features

Four memory assets: Chat Memory, Skill, LLM-Wiki and Code-Graph
Proxy integration by pointing an agent's base URL at it, with no plugin or MCP server
Web panel on port 8125
One memory server shared by Hermes, OpenClaw, Claude Code, Codex and other agents
Migration tool for data from v1.x and v0.x releases
Experimental MongoDB storage backend, off by default

When to use it

Sharing project context between Hermes Agent and Claude Code so it is not explained twice
Building a team of agents that reuse extracted skills and wiki pages
Moving memory data from an older release to the current version

Who it is for: Teams and solo operators who run several agents and want one governed memory server behind all of them.

How it fits with Hermes Agent

Hermes is one of the listed agents that can share the memory server by pointing its base URL at the proxy, alongside OpenClaw, Claude Code and Codex. The README links the Hermes Agent documentation from its badges.

How to install TencentDB Agent Memory

These commands are copied from the project's README. Check the repository for the latest steps before you run them.

git clone https://github.com/TencentCloud/TencentDB-Agent-Memory.git
cd TencentDB-Agent-Memory/deploy/global-images
cp .env.example .env
./start-all.sh

Requirements: Two sets of LLM parameters (a memory group and a proxy group) filled into the .env file before running start-all.sh

Note: The README marks Team Memory as Beta and the MongoDB storage backend as experimental.

FAQ

What is TencentDB Agent Memory?

TencentDB Agent Memory is a team-level memory hub for AI agents. It turns conversations, documents and code into Chat Memory, Skill, LLM-Wiki and Code-Graph assets that are governed and shared across agents.

Does TencentDB Agent Memory work with Hermes Agent?

Yes. The README lists Hermes among the agents that can share the memory server by pointing their base URL at the proxy. No plugin, hook or MCP server is needed, and INSTALL.md has the exact steps for each client.

How do I install TencentDB Agent Memory?

Clone the repository, go to deploy/global-images, copy .env.example to .env, fill in the two sets of LLM parameters and run ./start-all.sh. It starts memory-core, memory-hub and the proxy, and the panel opens at http://localhost:8125.