Skip to main content
Trinity
Polyform Noncommercial— Free for personal & research use

Autonomous Agent Orchestration & Infrastructure

Deploy, orchestrate, and govern fleets of autonomous AI agents — with real-time observability, fleet-wide scheduling, agent-to-agent delegation, and complete audit trails. On your own infrastructure.

Four Pillars of Deep Agency

Trinity implements the foundational capabilities that transform simple chatbots into fleets of autonomous AI agents.

Hierarchical Delegation

Agent-to-agent communication with fine-grained permission controls. Agents decompose goals into parallel tasks and delegate to specialized sub-agents.

Persistent Memory

File-based and database-backed memory across sessions. Agents maintain context via GitHub sync, shared folders, and custom dashboards.

Extreme Context Engineering

Composable skills and playbooks define agent capabilities. Each agent receives precisely engineered context for its specific role via the skill system.

Autonomous Operations

Cron-based scheduling with Redis distributed locks, multi-layer health checks, runaway prevention, and live execution streaming.

Up and Running in Minutes

Three steps from zero to your first autonomous agent.

01

One-Line Install

curl -fsSL https://raw.githubusercontent.com/abilityai/trinity/main/install.sh | bash
02

Create an Agent

# Via the Web UI at http://localhost
# Or via API:
curl -X POST http://localhost:8000/api/agents \
  -H "Content-Type: application/json" \
  -d '{"name": "my-agent"}'
03

Connect & Orchestrate

# Connect via MCP
claude mcp add trinity http://localhost:8080/mcp

# Chat with your agent
curl -X POST http://localhost:8000/api/agents/my-agent/chat \
  -d '{"message": "Hello, agent!"}'

Built for Production

Everything you need to deploy and manage autonomous AI agents at scale.

Isolated Containers

Each agent runs in its own Docker container with dedicated resources, multi-runtime support (Claude Code or Gemini CLI), and model selection per task.

Fleet Observability

Graph view topology, Gantt-style execution timeline, host telemetry, fleet health monitoring, and OpenTelemetry metrics export.

MCP Integration

62+ tools exposed via the Model Context Protocol. Connect Claude Code, Cursor, or any MCP client for external orchestration.

Agent-to-Agent Delegation

Hierarchical delegation with fine-grained permissions, parallel task execution, and shared folders via Docker volumes.

Credential Security

Direct file injection with encrypted git storage, centralized subscription management, and OAuth2 flows for external services.

Operations Dashboard

Real-time monitoring, cron scheduling, live execution streaming, public agent links, mobile PWA admin, and cost tracking per agent.