BuildTube Preview About
Back to the feed

TencentDB-Agent-Memory: Share reusable memory across agents

Added · Updated

Made by Tencent Cloud

View profile on GitHub (opens in a new tab)

Share conversation memories, skills, documents, and code maps with AI agents.

For teams using the supported agents; Team Memory is marked beta.

What it does

TencentDB Agent Memory is a shared memory hub for AI agents. It organizes conversation memory, reusable skills, a wiki made from documents, and a code graph. The source describes importing documents, code, and agent sessions; creating memory assets; and managing ownership, versions, visibility, status, and bindings to individual agents. A Memory Core, Hub, and proxy connect supported agents to the shared assets. The project lists integrations for Claude Code, Codex, DeepSeek Harness, CodeBuddy, WorkBuddy, Hermes, and OpenClaw. Its documentation calls Team Memory beta.

How to use it

Start the documented Memory Core, Hub, and proxy services, fill in the memory and proxy LLM settings, then import documents or code and bind selected memory assets to a supported agent.

Common use cases

  • Import team documents and receive wiki pages the agents can consult.
  • Extract a reusable skill from an agent conversation and make it available to a selected agent.
  • Bind different memory assets to different agents and review their visibility and status in the hub.

Can I use this?

Runs three services · LLM setup needed

Requirements The source's quick start launches Memory Core, Memory Hub, and a proxy, then asks for two groups of LLM settings: one for memory and one for the proxy. The documented setup guide gives the exact deployment steps.

Caveat Team Memory is labeled beta. The source says automated memory routing is still under iteration and the hub currently supports manual asset binding.

Worth knowing The source labels Team Memory beta and says automated memory routing is still being developed; asset binding is manual. The repository license file states MIT.

Why it's here

Not trending this week

Last seen on the GitHub trending list on 21 October 2026. It stays on BuildTube so you can still find it.

  • 30,639 people have starred it on GitHub.

Numbers checked on 8 November 2026; not refreshed since.

Behind it

View setup guide

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is TencentDB-Agent-Memory?
TencentDB Agent Memory is a shared memory hub for AI agents.
What can I use TencentDB-Agent-Memory for?
Import team documents and receive wiki pages the agents can consult; Extract a reusable skill from an agent conversation and make it available to a selected agent; Bind different memory assets to different agents and review their visibility and status in the hub
Can I run TencentDB-Agent-Memory on my computer?
It runs on your own computer or server after a local setup.
What do I need to use TencentDB-Agent-Memory?
Run the Memory Core, Hub, and proxy, and configure LLM settings for both the memory and proxy groups; then connect a supported agent.
What license does TencentDB-Agent-Memory use?
The repository license file states MIT.

More from this week

Related projects

Explore by topic

Post this

A ready-made picture of this card for X, LinkedIn or a group chat. Link to this page alongside it.

Share image for TencentDB-Agent-MemoryDownload share image

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

Featured on BuildTube

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/gh-tencentcloud-tencentdb-agent-memory.svg)](https://buildtube.app/p/gh-tencentcloud-tencentdb-agent-memory/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/gh-tencentcloud-tencentdb-agent-memory/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="TencentDB-Agent-Memory on BuildTube"></iframe>

Back to the feed