Now available for macOS & Linux

Plan. Delegate. Ship.

The AI-native IDE.

Trinity Dashboard — project overview with story progress, phase tracking, and execution status
Built with Tauri 2
Powered by Claude, DeepSeek, Kimi & Ollama
macOS · Linux

The first agent-native IDE.

Trinity doesn't add AI to your editor. It's an entirely different kind of IDE — one where AI agents plan, build, review, and learn across your entire project.

The plan lives here

PRDs, stories, dependencies, and phase structure — not tickets scattered across another tool.

Agents do the work

A 4-agent pipeline executes stories in parallel, each in its own isolated git worktree.

Everything is connected

Plan → code → review → knowledge. Every agent knows the plan. Every review knows the intent.

Memory compounds

Every decision, merge, and lesson feeds the next one. Nothing starts from zero.

How It Works

Other tools help you write code. Trinity ships entire features.

Step 1

Describe

Chat with Trinity about what you want to build. A 9-step wizard understands your project deeply — or import an existing codebase for AI analysis.

New PRD → "Build a SaaS billing
system with Stripe, usage
tracking, and team subs"

✓ Analyzing requirements...
✓ 4 phases, 8 epics, 24 stories
Step 2

Plan

A 4-phase AI pipeline breaks your idea into structured stories with dependency graphs: Architect → Story Writer → Dependency Mapper → Calibrator.

Phase 1: Core Infrastructure
  Epic 1.1: Auth System
    → Story 1.1.1: User model
    → Story 1.1.2: JWT auth
  Epic 1.2: Billing
    → Story 1.2.1: Stripe setup
    ↳ depends on 1.1.2
Step 3

Execute

Up to 5 workers execute stories in parallel through a 4-agent pipeline: Analyst → Implementer → Auditor → Documenter. Each in its own git worktree.

Workers: 3/5 active

[W1] Story 1.1.2 → Auditor ●
[W2] Story 1.2.1 → Impl    ●
[W3] Story 1.1.3 → Analyst ●
[W4] idle
[W5] idle
Step 4

Ship

PRs are created automatically with full documentation. Checkpoint releases with semver tagging. Optional auto-merge. Every merge, release, and agent decision is permanently recorded — building compound project history that survives any session.

PRs ready for review:
  #42 feat(auth): JWT auth  ✓
  #43 feat(billing): Stripe ✓

Release v0.2.0 tagged
  3 stories shipped
  0 issues found

A truly integrated development environment

Three things Trinity does that nothing else does.

Architect — Plans, in plain English

Architect is how all planning happens in Trinity. Describe what you want to build and it drafts a full PRD — phases, epics, stories, dependency graph. Describe a change — "add user profiles," "split this monolith," "drop the quarterly reports epic" — and it reshapes the work atomically, respecting whatever is already running. Plans stop being static documents and start being living objects you talk to.

Audit + Align — Two ways things get caught

Audit scans your codebase from multiple perspectives for architecture, security, performance, and pattern issues. Align scans your plan for drift, scope gaps, and inconsistency. Both surface findings as fix stories that flow through Architect — so diagnostics don't live in a report nobody reads, they get shipped.

Compound memory — Every run makes the next one smarter

Gotchas caught in one story become guardrails for the next. Vault knowledge accumulates across releases. Audit history compounds. Your codebase gets smarter as you build — because Trinity remembers everything the last run learned, and the agents actually consult it during planning.

Three Pipelines, One System

Stories, checkpoints, and releases each run through their own specialized multi-agent pipeline — every agent has a specific job, creating review loops that catch what single-shot generation misses.

Phase 1

Analyst

  • Read story requirements
  • Analyze codebase context
  • Create implementation plan
  • Identify risks & dependencies
Phase 2

Implementer

  • Execute the implementation plan
  • Write code across files
  • Run tests & fix failures
  • Handle Docker services
Phase 3

Auditor

  • Full code review
  • Check against requirements
  • Generate fix stories if needed
  • Verify quality standards
Phase 4

Documenter

  • Update documentation
  • Write PR description
  • Record learnings to vault
  • Capture patterns & gotchas
Story in→ AnalystImplementerAuditorDocumenterPR shipped
Personalize

Three themes. Light and dark.

Plain, Cyber, and Trinity — each in a light and a dark variant. Designed for developers who want their tools to look as good as they work.

Trinity Light theme

Light

Clean and minimal

Trinity Dark theme

Dark

Easy on the eyes

Trinity Cyber Light theme

Cyber Light

Vibrant and expressive

Trinity Cyber Dark theme

Cyber Dark

Neon developer aesthetic

Trinity Trinity Light theme

Trinity Light

Signature green on white

Trinity Trinity Dark theme

Trinity Dark

Signature green on black

Live from our private repo

We ship. A lot.

Trinity is in beta — but we're building at full speed. These numbers are pulled straight from our GitHub repo, updated daily.

4K
Commits
465K
Lines of Code
116
Days Building
34
Commits / Day

Simple, transparent pricing

One plan. Everything included. No tiers to compare.

15-day free trial · No credit card required

Pro

Everything you need to ship with Trinity

$10/seat/month
  • Cloud sync via Turso
  • Unlimited projects
  • 5 GB managed cloud storage
  • Team collaboration
  • Full feature set
  • Metrics & reports
  • PDF reports
  • All AI providers
  • Parallel execution
  • Priority support
Start free trial

15 days free, then $10/mo. Cancel anytime.

One subscription per person. Team owners can pay for members' seats.
Bring your own AI API keys — Trinity doesn't charge for AI usage.
Team projects draw from the team owner's 5 GB pool. Need more? Add 10 GB packs for $5/mo, or switch to BYO S3 (no limit, free).

Frequently asked questions

Everything you need to know about Trinity

Ready to see what an IDE can really do?

Download Trinity and ship your first feature tonight.

Available for macOS and Linux