TencentCloud /
TencentDB-Agent-Memory
A shared memory server that lets AI agents reuse chats, skills, docs and code knowledge
- 29.8k stars
- 2.2k stars since 3 Oct
- TypeScript
- Updated 2 days ago
- Some experience
- Memory, RAG & data
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.
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.gitcd TencentDB-Agent-Memory/deploy/global-images
cp .env.example .env./start-all.shCommands are copied from the project's README. Read it on GitHub for the full setup.
More in Memory, RAG & data
firecrawl
Web API that turns sites and search results into markdown or JSON for LLMs
markitdown
Python tool that turns PDFs, Office files, audio and more into Markdown for LLMs
graphify
Maps a codebase and its docs into a knowledge graph your AI assistant can query
claude-mem
Saves what your coding agent does and feeds the useful parts back into later sessions
vectorize-io/hindsight
Memory server that lets AI agents store, search and learn from past interactions
OpenViking
A context database that stores agent memory, docs and skills as browsable files
open-notebook
Self-hosted research notebook that chats with your documents using any AI provider
WeKnora
Self-hosted platform that turns documents into RAG search, an agent and a wiki
supermemory
Memory layer that lets AI assistants and apps remember users across conversations
gbrain
A shared memory for AI agents that stores sourced facts and answers with citations