LifeHubber.
Resources
AI Resources
TencentDB Agent Memory
TencentDB Agent Memory is a self-hosted memory hub that turns conversations, completed work, documents, and code into reusable assets for AI agent teams.
The project organizes those assets as Chat Memory, Skills, Wiki pages, and CodeGraph indexes. A web panel controls ownership, versions, visibility, and which assets each agent can use, while a proxy and SDKs connect the memory layer to supported agent environments.
What it is
A shared memory hub for agent teams
The project stores more than conversation recall. It can turn prior sessions into layered memories and skills, documents into linked wiki pages, and repositories into code relationship graphs.
Why it stands out
Memory assets with human controls
Owners can keep assets private, share them with a team, restrict them to named users or roles, or equip a specific agent. Versions, status, ownership, and bindings remain visible in one panel.
Availability
Public repository and Docker deployment
The official installation path runs Memory Core, the Hub, and a model proxy as a Docker stack. The project also publishes TypeScript and Python SDK paths and documents several agent integrations.
Why it matters
What makes it useful
A useful result from one agent session can otherwise disappear into a chat log. TencentDB Agent Memory gives teams separate places for facts, repeatable procedures, document knowledge, and code relationships, then lets them decide which agent should receive each one.
What to know
Where it fits
It fits teams and practical builders who want a self-hosted memory control panel around several agents. It is a larger system than a simple memory library: the recommended setup includes a memory service, knowledge service, web panel, model proxy, persistent storage, and external model configuration.
Notable points
What stands out
The project says it currently supports OpenClaw, Hermes, Claude Code, CodeBuddy, and SDK integration. Wiki and CodeGraph processing is asynchronous, private-repository support is still being refined, and fully automatic memory routing remains under development.
Before using
What to review
Which conversations, documents, repositories, skills, and user details should enter the memory system, and who should be able to read or share each asset.
Whether the model proxy is acceptable for the intended workflow, since it injects selected memory into prompts and forwards requests to the configured upstream model provider.
How Docker volumes, administrator and user keys, model API credentials, backups, retention, deletion, and service ports will be protected.
Whether a fast-moving 2.0 stack and its current agent integrations are stable enough for the intended production use.
Check the original listing's documentation for current requirements, limitations, licensing and any relevant privacy or security considerations.
Reader fit
Who may find it relevant
Teams that want memories and reusable skills to move between several agents without sharing every asset with everyone.
Builders comparing conversation memory with document knowledge, code graphs, access controls, and agent-specific context in one stack.
Less relevant for someone who only wants a lightweight personal memory library or a no-setup consumer assistant.
Editorial note
Why LifeHubber lists it
LifeHubber lists TencentDB Agent Memory because it combines four different kinds of reusable agent knowledge with visible ownership and access controls. That helps readers decide whether they need simple personal recall or a team hub that can also carry procedures, documents, and code context between agents.
Source links
Source materials
Reader note
About our listings
LifeHubber’s listings help you explore what’s available in AI and are not endorsements. We don’t independently verify every detail or guarantee that each listing is accurate, safe, actively maintained, or right for your needs.
What to explore next
Compare what an agent memory system should keep.
TencentDB Agent Memory combines personal recall with shared skills, documents, and code context. These next paths help compare a wider memory field and two narrower approaches.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
shadcn/ui
shadcn-ui/ui
Editable React interface components with a registry and CLI for adding source files, previews for proposed changes, and optional MCP search across configured registries.
Dash
agno-agi/dash
An Agno public data-agent template for asking questions over company data, with read-only SQL analysis, agent-created views in a separate schema, six context layers, a learning loop, AgentOS, Slack, Docker, Railway, and eval paths.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
MORE ON LIFEHUBBER
Use AI on your own terms.
Explore more AI projects, stories, guides, tools and community insights across LifeHubber.
