Complete Feature Reference

Features & Architecture

Every capability of the Hive platform, how the pieces fit together, and training videos to get you started.

Capabilities

22 Features, One Platform

Everything you need to build, deploy, and monitor multi-agent AI workflows.

A

Setup & Infrastructure

1

Infrastructure Management

Infrastructure page · Default landing page

Manages the Docker infrastructure that powers the platform. Pull/remove images, deploy/stop core services, view real-time container logs, and control the MCP DevServer.

2

Local LLM Management

Local LLM page

Run LLMs locally without cloud API keys. Pull the Ollama container, browse models from the Ollama library or HuggingFace, detect GPU, and chat with local models directly.

3

Key Store

Key Store page

Securely store API keys for LLM providers and tool services. Encrypted at rest using platform credential stores (DPAPI on Windows, AES-256-GCM on Linux/Mac). Auto-migration encrypts existing plaintext keys on first boot.

B

Agent & Skill Building

4

Agent Studio

Agent Studio page

Create and manage reusable agent templates. Each agent has a name, description, system prompt, and LLM provider configuration. Templates become live agents when added to a workflow and deployed.

5

Skill Hub

Skill Hub page

Create reusable prompt skills (templates with categories) that attach to agents. Building blocks for agent behavior — "Summarize Text," "Extract Entities," "Draft Email."

C

Tools & Marketplace

6

Tool Hub

Tool Hub page

Browse and configure installed plugin tools and MCP (Model Context Protocol) servers available to agents. View tool descriptions and parameter requirements.

7

Marketplace

Marketplace page

Browse and download tool packages from a GitHub-hosted NuGet feed. One-click install adds tools to the platform.

8

Packages

Packages page

View and manage downloaded tool packages. Each package contains tool functions that agents can use. Configure package-specific parameters.

PackageDescription
Agents.Tools.FileIOFile read/write/list/delete with sandboxed workspace
Agents.Tools.CodeExecShell, .NET, and Git CLI command execution
Agents.Tools.GitFull git operations (21 tools: clone, commit, push, merge, etc.)
Agents.Tools.GitHubGitHub API via Octokit (repos, issues, PRs, releases, branches)
Agents.Tools.WebSearchWeb search via SerpAPI + URL fetch
Agents.Tools.EvalsLLM-as-judge scoring + Ollama embedding similarity
Agents.Tools.AdzunaJob search via Adzuna API (12+ countries)
Agents.Tools.JSearchJob search via RapidAPI (Indeed, LinkedIn, Glassdoor, ZipRecruiter)
Agents.Tools.TheMuseJob search via The Muse (free, no API key)
Agents.Tools.EmailGeneric email send (SMTP) and read (IMAP)
Agents.Tools.GmailReceiveRead Gmail via IMAP with Google OAuth2
Agents.Tools.GmailSendSend Gmail with Google OAuth2
Agents.Tools.ImapEmailIMAP email client
Agents.Tools.SmtpEmailSMTP email client
D

Workflow Design & Deployment

9

Workflow Designer

Workflow Designer page

The core visual canvas for building AI workflows. Drag agents onto a canvas, connect them with edges defining communication paths, configure per-agent settings, and deploy as Docker containers. Supports Scheduler, Input Gateway, Output Gateway, and A2A Proxy nodes.

10

Workflow Chat

Chat Panel (right sidebar in Workflow Designer)

Send messages to deployed workflows in real-time. Supports @AgentName routing, per-message quality scores (auto-eval badges), cost tracking, token usage, and session management.

11

Scheduler (Cron Triggers)

Scheduler node in Workflow Designer

Add time-based triggers to workflows. Fires on a cron schedule, sends a configured message to a connected agent. Trigger history recorded per workflow.

E

Per-Agent Quality & Safety

12

Output Parsers (Structured Output)

Agent Detail Panel > Response Format

Enforce structured output formats. Three parser types: JSON Schema, Regex Extract, and Markdown Sections. Auto-retries with error feedback if format doesn't match. Format instructions auto-injected into the agent's system prompt.

13

PII Filtering

Agent Detail Panel > PII Filtering

Detect and redact personally identifiable information from agent responses. Configurable per workflow node — choose which PII categories to filter.

14

Auto Evaluation (Quality Scoring)

Agent Detail Panel > Auto Evaluation

Three-tier quality evaluation. Tier 1: static checks. Tier 2: reference metrics (BLEU, ROUGE, BERTScore). Tier 3: LLM-as-judge. Three modes: Monitor, Gate, Self-Correct. Custom rubrics, eval reports with per-metric badges.

15

Response Ranking

Agent Detail Panel > Ranking

When an agent returns a list of results, automatically rank and score each item. Four criteria: keyword boost, recency decay, semantic relevance, LLM-as-judge. Returns top-K ranked results.

16

Tool Configuration

Agent Detail Panel > Tools

Assign specific tools to each agent node and configure their parameters. API keys pulled from Key Store, workspace paths auto-resolved.

17

Custom Agent Images

Agent Detail Panel > Custom Image

Use any Docker image instead of the built-in agent image. Custom images must expose A2A protocol endpoints. Supports Python, Java, Go, Rust agents. Key declarations pass secrets and config.

F

External Access

18

Input Gateway

Input Gateway node in Workflow Designer

Expose a workflow as an external API endpoint. Supports API key and OIDC/JWT auth, input guardrails via Guardian, configurable port for stable URLs, and Cloudflare Tunnel support for public access.

19

Output Gateway (A2A Proxy)

Output Gateway node in Workflow Designer

A forward proxy that transparently forwards requests to a remote Hive instance. Other agents call it like a regular peer — they don't know they're talking to a proxy. Guardian safety checks run on every outbound message.

G

Audit & Monitoring

20

Audit & Cost Tracking

Chat messages + Eval Reports panel

Every LLM interaction logged with token counts, cost, and quality scores. Cost calculated at insertion time using provider pricing. Streams to Dashboard via SSE. Ollama interactions tracked at $0.

H

AI-Driven Building

21

MCP DevServer

Infrastructure page (start/stop) or CLI

An MCP server exposing 51 tools for building workflows entirely through AI conversation. Any MCP-compatible client (Claude Desktop, Cursor, Windsurf) can create agents, skills, workflows, configure nodes, and deploy via natural language.

I

Deployment Modes

22

Desktop Mode (Electron)

Installed application (Windows / macOS)

Single-click desktop installer. On launch: splash screen, Docker auto-detection, image pull, infrastructure deploy, Dashboard opens. Auto-updates via GitHub Releases.

23

Server Mode (Headless)

CLI or Docker container

Headless web server on port 8001. No Electron — access via any browser. For remote/team access or Docker deployment. Same codebase, same capabilities.

Learn

Training Videos

Short, narrated walkthroughs of every feature. Watch them in order or jump to what you need.

Open Training Player
00
Introduction
01
Infrastructure
02
Local LLM
03
Key Store
04
Agent Studio
05
Skill Hub
06
Tool Hub
07
Marketplace
08
Packages
09
Workflow Designer
10
Workflow Chat
11
Scheduler
12
Output Parsers
13
PII Filtering
14
Auto Eval
15
Response Ranking
16
Tool Config
17
Custom Images
18
Input Gateway
19
Output Gateway
20
MCP DevServer
21
Deployment Modes
99
Wrap-Up
Get in Touch

Ready to Build Your Agent Team?

Looking for early access, licensing, or a demo? Drop a line.

Get in touch