Features Overview
OpenVibely is a web workbench for AI-assisted software work that gets more useful the more project work flows through it. The UI is the primary surface: it gives teams a place to configure models and agents, select a project, create work, monitor execution, review changes, automate recurring tasks, and let OpenVibely build durable project memory from completed work.
Product At A Glance
| Area | What Users Experience | Where To Learn More |
|---|---|---|
| Dashboard | A selected-project landing page with task counts, category entry points, and an empty state for first-time setup. | Dashboard |
| Projects | A workspace boundary that controls repository context, task lists, chat, schedules, workers, memory, and channels. | Projects |
| Chat | A project-aware conversation for exploration, attachments, Plan mode, and Orchestrate mode. Chat can centrally create, run, and coordinate multiple tasks or swarms from one window. | Chat, Runtime Capabilities |
| Tasks | A board for backlog, active, and completed work with run/cancel controls, streaming progress, threads, attachments, diffs, review, and multi-role swarm execution. | Tasks, Swarm Orchestration, Task Threads & Follow-Ups, Task Diffs & Review |
| Scheduling | Time-based automation for one-time, recurring, and system maintenance runs. | Schedule, Scheduled Task Runs |
| Alerts | Project-scoped failure, follow-up, and attention notices with unread state. | Alerts |
| Models | UI-managed access to Anthropic, OpenAI, Ollama, OpenAI-compatible providers, and Mixture of Models virtual configs with defaults, auth options, tool policy, and capacity controls. | Models, Mixture of Models, Model Selection & Tool Policy, Model Providers, Worker Capacity & Dispatch |
| Agents | Reusable AI worker profiles with prompts, skills, plugins, MCP servers, permissions, routing, and lifecycle hooks. | Agents, Lifecycle Hooks, Skill Curation |
| Memory | Memory Curator autonomously creates project memory from completed work, recalls relevant notes before future tasks, and consolidates memory over time. | Memory, Lifecycle Hooks |
| Configuration | Runtime, auth, integration, deployment, and environment controls for self-hosted operation. | Configuration, Environment Variables, Deployment Modes |
| Review workflows | Worktree-backed changes, task output, comments, merge decisions, cleanup, API-published pull requests, and authorized PR feedback. | Review Workflows, Git Worktrees & Merge Safety, GitHub |
| Channels | Slack, Telegram, Discord, Email, GitHub, webhook, and outbound-message entry points for creating, tracking, and reporting work outside the web UI. | Channels Overview, Outbound Messaging, Discord, Email, Webhook Triggers |
The Primary Workflow
| Step | What Happens In The UI |
|---|---|
| Configure | Add at least one model, optionally create agents, and set worker limits if needed. |
| Select a project | Use the sidebar project selector so every page knows which repository/workspace you are working in. |
| Start work | Use Chat when the work needs discussion, or Tasks when you already know the unit of work. |
| Monitor | Watch task status, streaming output, alerts, and board movement as workers execute. |
| Review | Inspect task threads, attachments, changed files, review comments, worktree state, and pull request options before shipping. |
| Automate | Use scheduled task runs, task chains, channel/webhook triggers, or structured workflows for repeatable work. |
What Makes It Different
- It is UI-first: the app is built around project selection, sidebar navigation, modals, task boards, calendars, chat, alerts, and review screens.
- It is chat-orchestrated: one project Chat page can plan work, create multiple parallel tasks, steer or queue follow-up prompts, and keep coordination centralized.
- It is project-first: tasks, chat, memory, schedules, workers, models, agents, and channels are scoped around the selected project.
- It is review-first: AI work becomes visible task state, event streams, logs, diffs, comments, and GitHub-ready changes.
- It keeps work continuous: task threads, follow-ups, queueing, and steering let users refine active work without losing context.
- It learns from completed work: Memory Curator creates, updates, and consolidates durable project context, while Skill Curator improves the right scoped skill library afterward.
- It is automation-ready: scheduled task runs, task chains, channel prompts, webhook triggers, and workflows are managed from the app instead of hidden in scripts.
- It is self-hosted: operators control configuration, authentication, model access, database, worker capacity, and channels.
Recommended Reading
| If You Want To... | Read This |
|---|---|
| Try it quickly | Installation, then Quickstart |
| Understand the main UI | Dashboard, Projects, Chat, Tasks, Schedule, and Alerts |
| Understand work mechanics | Task Threads & Follow-Ups, Task Chaining & Branch Lineage, Lifecycle Hooks, Worker Capacity & Dispatch, and Scheduled Task Runs |
| Configure AI behavior | Models, Model Selection & Tool Policy, Agents, Memory, Skill Curation, and Personalities |
| Review generated code | Task Diffs & Review, Review Workflows, Task Lifecycle, Git Worktrees & Merge Safety, and GitHub |
| Run for a team | Deployment Modes, Authentication, Configuration, Worker Capacity & Dispatch, and Channels Overview |