Sakhanda Wire
NVDA $153.78 -1.51% MSFT $504.71 -2.56% GOOGL $279.10 -1.63% META $617.85 -1.37% AMZN $256.64 -0.43%
← Back to the news

Tencent Cloud open-sources team memory hub for AI coding agents

Tencent Cloud has released TencentDB Agent Memory v2.0 as an MIT-licensed, self-hosted memory hub for teams using AI agents. The stable 2.0.0 release was published on August 3, 2026. It converts conversations, documents and code into four governed asset types: Chat Memory, Skill, LLM-Wiki and Code-Graph. These assets carry ownership, versions, status and visibility settings, and can be equipped for specific agents.

Chat Memory records preferences, facts, decisions and interaction history. Skills capture reusable procedures, while the Wiki structures documents and CodeGraph indexes symbols, files, calls and impact paths. Conversations are distilled from L0 through L3 layers, with retrieval combining BM25, vector search and RRF under item, character and timeout limits.

The system supports private, team and restricted visibility, alongside access controls for users, teams and agents. New Chat Memory and Skills are private by default. A Memory Proxy supports Anthropic and OpenAI protocols, and integrations include OpenClaw, Hermes, Claude Code and CodeBuddy. Three Docker images support one-command deployment on linux/amd64 and linux/arm64. The project reports PersonaMem accuracy increasing from 48% to 76%, but describes this result as self-reported. Private-repository CodeGraph and automated routing are still being refined.

Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.

Originally published by MarkTechPost on

Read the original on MarkTechPost ↗

The reporting and the image belong to MarkTechPost and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news