AI Agents Overview
VORTΞXHQ ships with a fleet of specialised AI agents that can drive every module — API, SSH, SQL, FTP, Email, Studio — and a Global Orchestrator that chains them together.
Why Agents?
Most AI assistants are chat boxes. VORTΞXHQ agents are real autonomous workers: they pick tools, execute multi-step plans, verify the results, recover from errors, and report back with full evidence. Every agent runs through a hardened reasoning loop with permission gating, tool whitelists, memory, and cancellation support.
Agent Catalogue
| Agent | Where it lives | What it does best |
|---|---|---|
| Global Orchestrator | Footer · AI Command Center | Cross-module workflows: design → build → test → deploy. Routes to specialists. |
| API Agent | API Client → API Agent drawer | Send requests, sync git endpoints, generate docs, debug responses. |
| SSH Agent | SSH Terminal → SSH Agent drawer | Run remote commands, deploy code, tail logs, manage snippets. |
| SQL Agent | SQL Client → SQL Agent drawer | Generate queries, analyse schema, fix migrations, import/export data. |
| FTP Agent | FTP/SFTP → FTP Agent drawer | Navigate workspaces, edit remote files, deploy assets safely. |
| Email Agent | Email → Email Agent drawer | Triage inbox, summarise messages, audit HTML, cleanup test mail. |
| Studio Agent | Studio → Workspace | Senior full-stack developer that scaffolds projects and ships features end-to-end. |
| Project Architect | Specialist · invoked by Global | Requirements, data models, API specs, risk analysis. |
| Developer | Specialist · invoked by Global | Code generation, migrations, security review, git ops. |
| QA Tester | Specialist · invoked by Global | Test creation, coverage, performance, security testing. |
| DevOps / Debug | Specialist · invoked by Global | Deployments, CI/CD, log diagnosis, root-cause hunting. |
The Real-Agent Contract
Every agent in VORTΞXHQ follows the same six-step contract — never a single tool call:
- PLAN — think through every step before touching anything.
- EXECUTE — call tools sequentially, each building on the last.
- VERIFY — read back results before continuing.
- FIX — diagnose failures and try alternatives.
- NARRATE — keep the chat panel updated between steps.
- SUMMARIZE — finish with Changed Files, Test Results, Deploy Result, Verification Checks.
Provider Agnostic
Agents work with all 7 supported providers (Vortex, OpenAI, Anthropic, DeepSeek, Groq, Ollama, Custom OpenAI-compatible). Switch provider at any time — the agent keeps its tools, memory, and active chat.