Choose theme
AI Resources
OpenDots
OpenDots is a CopilotKit template for building a workspace with persistent specialist agents called Dots. It brings their conversations together with editable documents and optional computers for browser, file, and terminal work.
You run the application and connect its services. The project is in early development, with separate setup for conversations, computer tools, Slack, and voice. 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
A starting workspace for specialist agents
Create Dots with their own roles, instructions, and permitted tools. Spaces hold documents that those specialists can read and revise when granted access.
Why it stands out
Documents alongside ongoing conversations
A saved page can have a separate conversation for each specialist. You can return to the document and ask the chosen Dot to continue working with its saved contents.
Availability
Source template with services to connect
The repository declares MIT and documents a Node.js 24 setup and Docker deployment. Manual page editing works before conversation credentials are configured.
Why it matters
What makes it useful
A research Dot can gather material for a brief, then a writing Dot with access to the same Space can revise the document. The page library keeps the resulting work available for later editing rather than leaving it only in chat.
What to know
Where it fits
The app uses CopilotKit and AG-UI for agent interaction, TanStack AI for model streaming and tools, and Intelligence for conversation persistence. You configure the model endpoint and credentials; Slack uses a managed Channels SDK connection, and calls need a separate speech provider.
Notable points
What stands out
A Dot computer uses separate OpenBot services. Its browser profile and workspace files persist across stop/start, while the interface exposes human takeover and per-Dot browser, file, and shell permissions. These computer services are an additional deployment step.
Before using
What to review
The setup guide separates storage: SQLite holds pages and workspace metadata, while the configured Intelligence project holds conversation history. Copying the local database alone does not back up that history.
The README distinguishes local tests and demonstrations from connected-service verification. Live Slack, spoken compute delegation, and cloud Learning schedules and skill delivery still need verification.
Shared page editing, invitations, file uploads, and interactive page embeds are absent. Multiple Dots do not yet provide group conversations or automatic delegation.
Reader fit
Who may find it relevant
Developers prototyping a personal agent workspace can start from an existing document editor and specialist interface. Running the server and configuring its service connections requires more setup than opening a hosted chatbot.
Editorial note
Why LifeHubber lists it
The draft-to-document flow gives a builder a concrete approval step to adapt: a Dot presents its proposed page in chat, waits for Approve & save or Decline, and saves an approved draft into a Space it can access. This is a starting pattern for reviewing an agent-written brief before it becomes a saved working document.
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
Build beyond the workspace template.
If your next task is adapting the agent interface, CopilotKit covers the framework underneath OpenDots: chat, shared state, tool displays, and human-input points.
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.
OpenSEO
every-app/open-seo
An SEO workspace with keyword, ranking, backlink, and site research tools, an MCP connection for AI agents, reusable research skills, and hosted or self-hosted access.
Open Multi-Agent
open-multi-agent/open-multi-agent
A TypeScript-native framework for coordinating multi-agent work from a goal into a task DAG, with auto task decomposition, parallel execution, plan preview and replay, human approval hooks, MCP tools, provider routing, observability, and sandboxed filesystem defaults.
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.
