TencentDB-Agent-Memory

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LL

What is TencentDB-Agent-Memory?

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.

Overview of TencentDB-Agent-Memory

What it is

TencentDB Agent Memory is a team-level memory hub for AI Agents. It transforms conversations, documents, and code into four reusable memory assets: Chat Memory, Skill, LLM-Wiki, and Code-Graph. These assets are governed, shared, and equipped across agents and frameworks. The project aims to reduce repetitive work by allowing agents to inherit accumulated experience rather than starting from scratch each session.

Key features

  • Automatically extracts Chat Memory and Skills from conversations and tasks; converts documents and code into Wiki and CodeGraph.
  • Memory assets are decoupled from agent frameworks, enabling portability and sharing across multiple agents and team members.
  • Supports cold-start by importing existing documents, codebases, and agent conversation sessions.
  • Chat Memory retains preferences, facts, decisions, and interaction history, with automatic per-agent memory creation.
  • Skill library allows extraction and management of reusable skills from conversations and tool calls, with versioning, resource files, and validation rules.
  • Wiki turns product docs, design specs, and ops runbooks into structured pages with a link graph; CodeGraph indexes code symbols, files, call relationships, and impact paths.
  • Team memory panel provides human-controlled management of ownership, versions, status, visibility, usage counts, and agent bindings, with role-based access control.

Use cases

  • Reducing repetitive work: project context explained once is reused across sessions.
  • Team experience accumulation: work produces assets that circulate through the team, and new members can load the team's save file on day one.
  • Cold-start for new agent teams: import existing documents, codebases, and past conversations to avoid learning from scratch.
  • Role-specific memory loadouts: different agents (e.g., Scout, Builder, Reviewer) receive only the memory assets they need.

Getting started

bash git clone https://github.com/TencentCloud/TencentDB-Agent-Memory.git cd TencentDB-Agent-Memory/deploy/global-images cp .env.example .env $EDITOR .env # Fill in two sets of LLM parameters (memory group + proxy group) ./start-all.sh # Launch everything with one command; when finished, it prints a one-liner you can paste directly into Claude Open the panel: http://localhost:8125. For complete installation documentation (standalone Memory Hub deployment, Proxy + Claude Code / CodeBuddy usage, stop and cleanup, port reference, etc.), see INSTALL.md.

License and pricing

The license is not stated (NOASSERTION). The project is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/tencentcloudtencentdb-agent-memory.svg)](https://yunodb.com/tools/tencentcloudtencentdb-agent-memory?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/tencentcloudtencentdb-agent-memory?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/tencentcloudtencentdb-agent-memory.svg" alt="Featured on YunoDB" height="20"></a>