Skip to content

trinity

A coordination-first AI employee OS tuned for watched threads, TODO-first heartbeat execution, file-backed memory, and evidence-driven delivery.

FieldValue
StatusDraft
Versionv0.1.0
Familymanager-heavy
Spec>=1.0.0 <2.0.0
PersonaCoordinator-first
HeartbeatProactive

Description

Trinity is designed for AI agents that must act like accountable operators, not passive chatbots. It emphasizes watched DM/thread environments where every action needs a short receipt, strict follow-up discipline, and evidence-driven delivery.

Use Cases

  • Owner-facing AI employee workspaces
  • Slack / IM-heavy execution loops
  • Multi-agent coordination with strict follow-up discipline
  • Environments where every outbound message requires post-send verification

Skills

Required (included_skills)

SkillDescription
agent-managerEmployee agent lifecycle management
use-fractalbotOutbound messaging via fractalbot CLI
turbo-frequencyHigh-frequency execution mode

Workspace Files

After installation, your workspace will contain:

Core OS files

FilePurpose
SYSTEM.mdKernel contract
SOUL.mdOperating principles
AGENTS.mdSession bootstrap and rules
USER.mdOperator profile
HEARTBEAT.mdTODO-first execution surface
OKR.mdActive OKR control plane
TODO.mdTemporary work tracker
MEMORY.mdLong-term memory
TOOLS.mdEnvironment notes

Memory system

PathPurpose
memory/index.mdTopic navigation
memory/watched-dm-receipts.mdWatched thread receipts

OKR system

PathPurpose
okrs/Candidate.mdNon-active OKR parking lot

Key Principles

  • Result-oriented, not step-oriented: Focus on outcomes, not process
  • Post-send verification: Not just "sent" but "delivered correctly"
  • Watched DM/thread discipline: Every action change produces a short receipt
  • TODO-first heartbeat: Urgent work before OKR progression
  • Evidence-driven delivery: Prove completion with artifacts

Version History

VersionDateHighlights
v0.1.02026-04-12Initial draft — AI employee OS with watched thread discipline

View full release notes on GitHub

Install

See the Installation Guide for step-by-step instructions.

Released under the MIT License.