Choose theme
AI Visuals
II-Agent
II-Agent is an agent framework for creating apps, researching questions, and working with documents through a self-hosted web interface.
Intelligent-Internet's current repository documents model-provider configuration, reusable skills, and connected-service workflows. 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
Agent framework with a web workspace
It combines task planning, document tools, research and creation workflows around configured language models.
Why it stands out
Research can become a website
The documented research workflow can produce a website with citations and embedded questions and answers, alongside app, slide and document creation.
Availability
Repository and setup guide
The core project is on GitHub. Its local setup runs a backend, frontend and supporting services; model-provider credentials are configured separately.
Why it matters
What makes it useful
A team preparing a research brief could use the documented research-to-website workflow to turn findings into a browsable page with citations and embedded Q&A. The source materials still need checking before the website is shared.
What to know
Where it fits
II-Agent supplies the agent and work interface. The selected provider supplies the model, while connected apps supply additional actions. Self-hosting the interface does not make requests to a hosted model stay on the local machine.
Notable points
What stands out
The same conversation can switch model providers, according to the repository. That separates a continuing work thread from one fixed model choice; provider credentials and supported configuration still determine what is available.
Before using
What to review
The development setup requires Docker, uv, Node.js and npm. The full Docker Compose path packages the stack separately.
The local development stack includes PostgreSQL, Redis and MinIO alongside the backend and frontend. It includes databases and file storage to maintain, not just a model process.
Configure model keys and any connected-account permissions for the workflow you intend to run.
Review generated code, research citations and documents before using or publishing them.
Reader fit
Who may find it relevant
Developers and teams who want to run or extend an agent workspace with document, research and creation tools.
People using a self-hosted setup need to manage its services and model accounts; it is more than installing model weights.
Editorial note
Why LifeHubber lists it
A generated research page is rarely the finished thing you want to share. II-Agent includes live editing for websites and slides, so its output can be revised within the same workspace. That makes it worth exploring for briefs that need to become a presentation or web page, where shaping the result is part of the work.
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
Set the boundaries before the agent acts.
App and document workflows can involve files, connected accounts and generated output. Continue with the access, approval and recovery choices around those actions.
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.
Genex Desktop
genex-games/genex-desktop
An early desktop workspace for making browser games with AI, combining game chat, playable previews, build history, assets, configurable model roles, local Blender tools, and static web export.
SkillOpt
microsoft/SkillOpt
A Microsoft project for improving reusable agent skills without changing target model weights, with a benchmark-driven optimizer and a separate SkillOpt-Sleep path for reviewing sessions, replaying recurring tasks after the live task, and validation-gating proposed changes.
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.
