OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Tencentdb Agent Memory

TencentDB Agent Memory is a self-hosted hub and proxy that organizes conversations, documents and code into reusable memory assets for sharing across AI agents and frameworks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tencentdb Agent Memory — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when agent teams need to retain and reuse project context, workflows or knowledge across sessions and different supported clients.

Who it is for

  • Teams using multiple AI agents that want shared, reusable context.
  • Developers setting up a self-hosted memory service and connecting supported agent clients.

Documented uses

  • Extract Chat Memory and Skills from conversations and tasks.
  • Convert documents and code into an LLM-Wiki and Code-Graph.
  • Manage and share these assets across agents and frameworks.
  • Run a shared memory server and connect an agent through its Proxy.
Before you choose

Requirements & limits

The project is presented as a public repository with an MIT license badge. The documented setup runs locally and requires two sets of LLM parameters.

  • The documented setup launches memory-core, memory-hub and proxy together.
  • The README lists DeepSeek Harness, Claude Code, Codex, CodeBuddy, WorkBuddy, Hermes and OpenClaw as clients with installation guidance.
  • The repository says clients connect by pointing their base URL to the Proxy; see the installation guide for client-specific configuration.
  • MongoDB storage is experimental and off by default.
  • Vector search appears in repository topics, but the supplied project description does not detail its configuration or behavior.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Memory Hub and Proxy services

Start the documented three-service stack and open its local panel.

Before you start

  • A clone of the TencentDB-Agent-Memory repository
  • Node.js 22.16 or later, as indicated by the repository
  • Two sets of LLM parameters for the memory and proxy groups

Steps

  1. Clone the repository and change into deploy/global-images.

  2. Copy .env.example to .env and fill in the two LLM parameter sets.

  3. Run ./start-all.sh to launch memory-core, memory-hub and proxy.

  4. Open http://localhost:8125; use the configuration line printed by the script when configuring Claude.

Expected outcome

The three services are launched and the local panel is available; the script prints a Claude configuration line.

Guide limitations

  • The guide describes startup, not verification of successful operation or agent task execution.
  • MongoDB storage is experimental and off by default.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
TencentCloud/TencentDB-Agent-Memory · Official homepage title · retained in its source language
How we review sourcesSuggest a correction