GitHub
Concept

Key Concepts

Core concepts and terminology in ProxifAI

Understanding these core concepts will help you get the most out of ProxifAI.

Organizations

An organization is the top-level unit. It represents your team or company. Each organization has its own members, projects, repositories, billing, and settings. Members can belong to multiple organizations.

Teams

Teams group members within an organization. Projects, sprints, and views can be scoped to a team, so each team sees only the work relevant to them.

Projects

Projects group related work together. A project tracks issues, links to repositories, and shows progress metrics. Projects have a status (backlog, planned, in_progress, paused, completed, cancelled) and an independent health (on_track, at_risk, off_track, no_updates). They can be organized into roadmaps and initiatives.

Issues

Issues are the fundamental unit of work. They have:

  • Status — backlog, todo, in progress, in review, done, cancelled
  • Priority — urgent, high, medium, low, none
  • Assignees — one or more team members
  • Labels — for categorization and filtering
  • Time entries — for tracking effort
  • Comments — threaded discussion

Issues connect to branches and pull requests, creating full traceability from planning to code.

Repositories

ProxifAI includes a native Git forge. You host repositories directly on the platform — no external Git provider required. Repositories support branches, tags, releases, deploy keys, and branch protection rules.

Pull Requests

Pull requests enable code review within the platform. They include diff viewing, inline comments, approval workflows, CI/CD check integration, and merge conflict detection.

Sprints

Sprints are time-boxed iterations for organizing work. Create sprints, assign issues, and track progress — all scoped to a team.

Workflows

Workflows are automated sequences that can be triggered by events, schedules, or manually. They support conditional logic, loops, and human-in-the-loop approvals. Workflows can assign tasks to AI agents that execute in isolated containers.

Agents

AI Agents run in fully isolated containers (Docker or Kubernetes). They can:

  • Clone repositories and install dependencies
  • Write code, run tests, and open pull requests
  • Triage issues and suggest priorities
  • Answer questions about your entire codebase

Agents access only what their owner can access — no privilege escalation.

Knowledge Base

The Knowledge Base indexes your code, documents, and project data for AI-powered search. Use the chat interface with @ mentions to reference any issue, PR, document, or file across your organization.

The AI chat supports four modes: Ask (read-only Q&A), Plan (analysis with full forge access), Code (live development inside a container with shell + file + git tools), and Build (same toolset as Code, framed as a feature-shipping session). See Chat Modes for the full breakdown.

Pipelines

Pipelines are YAML-defined CI/CD workflows that run on push, PR, or manual trigger. They support secrets, environment variables, approval gates, and artifact generation.

Inbox

The Inbox is a unified notification center with real-time updates. Notifications include inline actions — approve a pipeline, merge a PR, or respond to a workflow approval without leaving the inbox.