Trinity
Self-hosted AI agent platform to run agents in production on your infrastructure
Visit ability.ai ↗What is Trinity?
Trinity is an open-source, self-hosted runtime for deploying AI agents in production. Built by Ability.ai, it runs Claude Code, Codex, and Gemini CLI agents within your own perimeter, keeping models, keys, memory, and audit trails private. Each agent runs in an isolated container with git-versioned state, multi-agent orchestration, and governance controls.
The platform is designed for teams building proprietary autonomous systems who need full control over their infrastructure and data. Trinity offers agent-to-agent delegation, a knowledge graph core called Cornelius, real-time observability, fleet-wide scheduling, and an append-only audit trail. The entire platform is exposed as an MCP server with 90+ tools, allowing control via Claude, ChatGPT, or Cursor in plain language.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Trinity automatically. Evidence: GitHub Abilityai/trinity; repo has .claude, AGENTS.md, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces
Manage teams of AI agents to run your business from one dashboard
Persistent memory for AI agents across Claude Code, Cursor, and MCP clients