# TencentDB-Agent-Memory

> A shared memory server that lets AI agents reuse chats, skills, docs and code knowledge

- Repository: https://github.com/TencentCloud/TencentDB-Agent-Memory
- Category: Memory, RAG & data
- Stars: 29,819 · Forks: 2,891 · Language: TypeScript · License: not stated
- Experience: Some experience
- Page: https://ir.adyog.com/repos/tencentcloud/tencentdb-agent-memory/

Agents tend to start every session from scratch. You re-explain the project, they re-read the same documents, and a workflow that worked once gets rediscovered. This project is a memory hub that keeps that experience and hands it to the next agent.

It saves four kinds of assets. Chat Memory distils conversations in layers, from raw dialogue up to a persona. Skills are reusable procedures extracted from finished work. A Wiki turns documents into linked pages. A CodeGraph indexes symbols, call relationships and the impact of a change. A web panel lets people set who owns each asset, who can see it (private, team, restricted or agent) and which agent gets it.

The README contrasts it with plain chat history and standard RAG. Those find text. This also tracks versions, ownership and sharing, and lets you equip different agents with different assets. Agents connect by pointing their base URL at a proxy, so no plugin, hook or MCP server is needed. The README text provided was cut off, so details beyond this are not covered here.

## What it does

- **Four memory asset types**: Chat Memory, Skills, Wiki and CodeGraph are extracted from conversations, documents and code, then managed in one place.
- **Proxy-based integration**: Point an agent's base URL at the proxy. The README lists DeepSeek Harness, Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes and OpenClaw.
- **Cold-start import**: Import existing codebases, documents and past agent sessions so a new agent starts with that knowledge instead of learning it again.
- **Access control**: Assets are private by default. Sharing is explicit, with team, restricted (user, role or agent ACLs) and agent-targeted visibility.
- **Memory Hub panel**: A web panel to create teams and agents, review assets, bind them to agents and see versions, status and usage counts.

## What you could build

- Give Claude Code or Codex a code graph so it can check callers and impact before editing.
- Turn product docs and runbooks into a linked wiki that several agents can search.
- Extract a release checklist or review routine as a skill and assign it to one agent.
- Keep project decisions and user preferences across sessions so you don't repeat them.
- Set up a small team of role-based agents, each equipped with different memory assets.

## Who it's for

Developers who run coding or assistant agents regularly and want shared memory for them; you should be comfortable with Docker-style deployment, .env files and configuring LLM API keys.

## Get started

Clone the repo, copy .env.example to .env and fill in the two sets of LLM settings (memory group and proxy group). Run start-all.sh, then open the panel at http://localhost:8125 and follow INSTALL.md to connect your agent.

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

Tags: agent-memory, long-term-memory, knowledge-graph, multi-agent, typescript