All directories
AgentEngineeringOperations

TencentDB Agent Memory

TencentCloud/TencentDB-Agent-Memory

Team-level memory hub for AI agents — turn chats, docs, and code into shared Chat Memory, Skills, Wiki, and Code-Graph assets.

00

GitHub repository

https://github.com/TencentCloud/TencentDB-Agent-Memory
01

Overview

Instead of each agent forgetting everything (or hoarding private notes), this project stores reusable team memory: conversations, skills, a wiki, and a code graph that multiple agents can share. Repo (copy/paste): https://github.com/TencentCloud/TencentDB-Agent-Memory

SaaSOther

Work with LimeDock

Using this skill? LimeDock can wire it into a durable automation you own.

Agents are a starting point. LimeDock turns the workflow into production automation your SaaS team owns — not another prompt library.

We sell owned automations for SaaS teams — live workflows that plug into Slack, CRM, and your internal platform — not just a skill list.

02

Link

https://github.com/TencentCloud/TencentDB-Agent-Memory
03

Installation guide

Not installed into LimeDock.

1. Copy: https://github.com/TencentCloud/TencentDB-Agent-Memory 2. Follow the README install (Node package / gateway notes). 3. Connect the agents you already use so they read/write the shared memory store. 4. Decide what is team-shared vs private.

04

How to use it

**Simple example** Two agents keep re-learning your API quirks every Monday.

1. Install the memory hub for your team. 2. After a hard debugging session, save the lesson as Chat Memory / Skill. 3. Next week a different agent pulls the same skill instead of rediscovering it. 4. Humans innovate; agents stop amnesia.

05

Example prompts

  • What four memory asset types does TencentDB Agent Memory create?
  • Design a rule: which conversations become team Skills vs stay private.
  • How would we plug our support bot and coding agent into one memory hub?
06

Use cases and examples

  • Shared memory across multiple coding agents
  • Turning tribal Slack knowledge into reusable skills
  • Code-graph context for larger repos
07

Prerequisites

  • Node / gateway requirements from the README
  • Agreement on shared vs private memory
  • Agents that can call the memory APIs / gateway
08

Tips

  • Memory without governance becomes a junk drawer — set owners.
  • Start with one squad before company-wide memory.