Choose theme
AI Resources
Octop
Octop is a self-hosted AI assistant platform from TencentCloud for individuals, households, and small teams. It brings specialized assistants, document knowledge bases, messaging channels, and scheduled tasks into one deployment.
Each user can have several experts with their own workspaces and settings. You run the application and choose the model providers and connected services those experts use. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
An assistant platform you host
The web dashboard, command line, messaging integrations, and scheduled jobs run through one server process. The dashboard provides chat and administration for users and experts.
Why it stands out
Personal experts on a shared installation
Experts have separate workspaces, model-provider settings, channels, and schedules. Expert sharing and shared skill pools let other users reuse a setup; knowledge bases can also be shared within the deployment.
Availability
Source, desktop apps, and Docker
The repository declares MIT and provides installation instructions for macOS, Linux, and Windows. Desktop downloads and Docker deployment are available. AgentTeams, which coordinates several experts on a task, is marked Beta.
Why it matters
What makes it useful
A household or small team can set up specialists for recurring work rather than begin every request with the same instructions. The documented knowledge base retrieves material from uploaded documents, so an expert can draw on a collection of notes or reference files. Sharing a corpus gives colleagues a common document collection while keeping their expert setups separate.
What to know
Where it fits
Octop supplies the assistant application around the model. Its provider options include OpenAI-compatible APIs, DashScope, and Ollama, configured per expert. Messaging channels such as Telegram, Discord, and WeChat provide other ways to reach the same platform. OAuth connectors and MCP connections extend the tools it can use; those services have their own setup and access requirements.
Notable points
What stands out
Workspace files and the application database are separate storage choices. The database holds users, agents, channels, and schedules; an expert workspace carries files and memory. With the default SQLite setup, agent memory is file-based. The configuration documentation says PostgreSQL deployments default agent memory to the same database connection, with a separate schema for each agent, and there is no automatic SQLite-to-PostgreSQL memory migration. Moving the application database therefore needs a separate decision about existing memories.
Before using
What to review
Running from source needs Python 3.12 or newer; the documented installer provisions an isolated Python environment. The host also needs space for databases, workspaces, documents, and any local models or embedding caches.
Self-hosting describes where the application runs. A configured remote model or connected service may receive requests and material needed for the task; choosing Octop does not by itself make every workflow offline.
Browser automation, terminal commands, and remote-desktop control are available features. Review which tools and accounts an expert can access, along with the documented approval and command-guard settings, before connecting personal work.
Keep AgentTeams experimentation distinct from relying on a completed task: its documentation says stopping the coordinator does not cancel already queued or running member tasks.
Reader fit
Who may find it relevant
People comfortable maintaining a self-hosted service can explore a shared assistant installation with individual experts. Builders can inspect its Python backend, React dashboard, and programmatic APIs. Casual visitors can use the repository and desktop documentation to understand the setup, but someone still needs to configure models, storage, and any account connections.
Editorial note
Why LifeHubber lists it
We list Octop because it gives a household or small team a way to share useful assistant setups without requiring every person to assemble the whole platform. One person can maintain the host, while others use their own experts and reuse a shared knowledge base or specialist configuration. That combination is worth exploring when the practical obstacle is organizing AI help for several people, rather than finding another model to chat with.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Choose what your experts may act on.
For browser, terminal, and desktop tasks, the computer-control guide helps you define the files and accounts an assistant may reach and the actions that need your decision.
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.
OpenMuse
CopilotKit/OpenMuse
A CopilotKit personal-agent alpha with saved tasks, browser takeover, PDF workflows, and mobile/web interfaces, requiring separate conversation, model, and account-service configuration.
Mem0
mem0ai/mem0
A memory layer for AI agents and assistants, with library, self-hosted, platform, SDK, CLI, cookbook, evaluation, and integration paths for persistent context.
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.
