# tencentcloud/tencentdb-agent-memory

> tencentdb-agent-memory is a team-level memory hub for AI Agents, meant to stop project context, documents, code and working methods from being re-explained in every new session. It turns agent conversations, docs and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki and Code-Graph. These assets can be governed, shared and equipped across agents and frameworks. The project is written mainly in TypeScript.

Source: https://github.com/tencentcloud/tencentdb-agent-memory
Indexed: commit 42d4cde on 2026-11-10 by Repowise. Facts come from the source and git history, not from the maintainer.

## Facts

- Language: TypeScript
- Stars: 30,956 at index time
- Code health: 6.8/10, Fair
- Last commit: 2026-11-09
- Contributors: 37

## Install

From the README: https://github.com/tencentcloud/tencentdb-agent-memory#installation

Clone the tencentdb-agent-memory repository.
    git clone https://github.com/tencentcloud/tencentdb-agent-memory.git

Change into the deployment directory of the repository.
    cd TencentDB-Agent-Memory/deploy/global-images

Create the environment file from the example and fill in the two sets of LLM parameters in it.
    cp .env.example .env

## How it works

Agent conversations, tool calls, documents and code enter the system through the MemoryProxy and MemoryCore parts. MemoryProxy handles session initialization, session recovery and per-request metadata, so requests reach the right agent and task context. MemoryCore/index.ts is the entry point for the MemoryCore pipeline, which builds and persists memory artifacts, and MemoryKnowledge exposes HTTP routes and wiki and code-graph services that index those artifacts. The MemoryPanel web UI shows the resulting chat memory, skills, and wiki and code-graph pages to people who manage teams and assets. The deploy/global-images directory contains the start-all.sh script that launches the memory, hub and proxy services together.

- MemoryCore/bin/export-tencent-vdb.mjs: entry point
- MemoryCore/bin/migrate-sqlite-to-tcvdb.mjs: entry point
- MemoryCore/bin/read-local-memory.mjs: entry point
- MemoryCore/index.ts: entry point
- MemoryCore/pi-plugin/index.ts: entry point
Modules: MemoryCore, MemoryProxy, MemoryPanel, MemoryKnowledge, sdk, deploy, agents, adapters. 1,203 files, 196,543 lines, 12,056 symbols.

## Code health

- Score: 6.8/10 (Fair)
- Rank: #164 of 4,000+ indexed repos
- Hotspots: MemoryProxy/src/pipeline/runners/openai-chat.ts, MemoryProxy/src/pipeline/runners/anthropic.ts, MemoryProxy/src/session/codebuddy/init.ts, MemoryPanel/web/src/pages/ChatMemoryPage/components/BlockDetail.tsx, MemoryProxy/src/pipeline/runners/workbuddy.ts
- Lowest file: MemoryProxy/src/session/store.ts
- Dead code: 93 findings

## Maintenance

- Last commit 2026-11-09, first commit 2026-07-22, 75 commits
- 37 contributors, bus factor 1

## Security

- Security findings are shown to signed-in users at https://repowise.dev/repo/tencentcloud/tencentdb-agent-memory/security

## More

- Page: https://repowise.dev/repo/tencentcloud/tencentdb-agent-memory
- Ask this codebase: https://repowise.dev/repo/tencentcloud/tencentdb-agent-memory/chat
- Docs: https://repowise.dev/repo/tencentcloud/tencentdb-agent-memory/docs
- MCP (signs in with Repowise on first use):
    claude mcp add --transport http repowise https://api.repowise.dev/mcp/tencentcloud/tencentdb-agent-memory
