Tencent Cloud Open-Sources TencentDB Agent Memory v2.0: A Team-Level Memory Hub for AI Coding Agents
Tencent Cloud has open-sourced TencentDB Agent Memory v2.0, a team-level memory hub for AI agents. The idea is super simple: if project context was already explained once, a new session should not need it repeated. The system turns conversations, documents and code into four reusable memory assets — Chat Memory, Skill, LLM-Wiki and Code-Graph — that are versioned, permissioned and equipped to specific agents. Single-agent memory is not new. What is new here is the governance layer, which lets a teammates agent read what your agent learned, without leaking anything you marked private. The stable release is published on August 3, 2026. Is it deployable? Yes, it is deployable. TencentDB Agent Memory is MIT-licensed and self-hosted. Three Docker images published to Docker Hub start with one...
Tencent Cloud has open-sourced TencentDB Agent Memory v2.0, a team-level memory hub for AI agents. The idea is super simple: if project context was already explained once, a new session should not need it repeated. The system turns conversations, documents and code into four reusable memory assets — Chat Memory, Skill, LLM-Wiki and Code-Graph — that are versioned, permissioned and equipped to specific agents. Single-agent memory is not new. What is new here is the governance layer, which lets a teammates agent read what your agent learned, without leaking anything you marked private. The stable release is published on August 3, 2026. Is it deployable? Yes, it is deployable. TencentDB Agent Memory is MIT-licensed and self-hosted. Three Docker images published to Docker Hub start with one command, and multi-arch builds cover and . Which companies: Solo builders and small engineering teams get the most value now. The project explicitly targets the one-person company. Mid-size orgs with a platform or DevEx function can run it as shared infrastructure. Large regulated enterprises should pilot rather than standardize, because private-repo CodeGraph and automated memory routing are still being refined. Industries: Software and developer tooling, SaaS, fintech, consulting and agencies, plus any regulated team that needs memory to stay inside its own network. Applications: Onboarding a new agent to an existing codebase, impact analysis before refactoring, release checklists, incident runbooks, code review standards, and turning product docs into agent-readable pages. Four memory assets The system converts work into four asset types: Chat Memory retains preferences, facts, decisions and interaction history. Skill distills reusable procedures from completed tasks, carrying versions, resource files, trigger boundaries, execution steps and validation rules. Wiki turns documents into structured pages with a link graph, an approach informed by Andrej Karpathys LLM-maintained knowl