Blog
Insights on AI-powered development, autonomous coding agents, and the future of shipping software.
FeaturedProduct
End-to-end encrypted secrets: your keys, your devices
Trinity now ships end-to-end encrypted secrets: keys stay on your devices, our servers hold only ciphertext, and nobody — including us — can read your values.
Lorenzo Wynberg7 min read
Engineering7 min read
Stop waiting for a better model. Build a better system.
GPT-5.6 and Fable 5 shipped this month, then got throttled by the government. Stop betting your output on a better model — own the system around it.
Read more
Engineering14 min read
How Trinity builds accessible software by default
Most teams bolt accessibility on at the end. Trinity makes WCAG conformance a setting on the package that builds the code, enforced on every story that lands there. Here is how.
Read more
Product10 min read
Multiplayer AI coding: shared sessions, live handoff
Trinity makes every AI surface a shared, real-time conversation — and lets you pull a running agent session onto your own machine in under a second by tagging @agent.
Read more
Engineering7 min read
Run Dozens of AI Agents on One Machine — No Meltdown
Five AI agents per person, per project, each spawning sub-agents — and your machine survives. Inside run_queued, Trinity's throttle for parallel AI builds.
Read more
Product10 min read
A runtime you control: skills, commands, and hooks
Trinity gets a Runtime — one synced place to manage the skills, commands, and hooks your agents run with, and to create new ones just by describing them.
Read more
Product10 min read
Browse your code like an IDE, inside Trinity
Trinity's built-in code browser brings a commit history graph, per-commit diffs, and line-by-line blame into the app — review what your agents shipped without opening GitHub.
Read more
Engineering14 min read
Agent failure recovery: when a run gets stuck
Autonomous runs fail — merge conflicts, hung agents, runaway loops. Trinity treats failure as a first-class state: detect it, measure the blast radius, draft a fix.
Read more
Product5 min read
OpenAI Codex joins Trinity's growing engine family
OpenAI Codex joins Claude in Trinity's growing engine family — pick GPT-6 Astra or a GPT-5.6 model in Settings, powering every AI action, same framework.
Read more
Engineering10 min read
Why Trinity runs on Effect: typed errors, supervised agents
Trinity runs on Effect across its highest-leverage surfaces. Typed errors and supervised agents make the autonomous pipeline fail loudly, never silently.
Read more
Engineering10 min read
Parallel multi-host git: one process, every host
Trinity makes git pluralistic — every project runs against its own host, transport, credential, and identity, all in parallel. Here is how it works.
Read more
Engineering10 min read
Inside Trinity's release pipeline: from merge to tag
How Trinity turns merged stories into a shipped release — grading each repo version bump from real code, walking a staging chain, and tagging every repo on its own.
Read more
Company11 min read
Harness choice, not lock-in: Trinity is going multi-harness
Anthropic's June 15 programmatic-usage cap is a harness-layer change, not a model one. Here's why Trinity treats the harness as the real unit of portability — and how Claude Code, Codex CLI, and OpenCode all earn their place.
Read more
Engineering10 min read
How Solid + Vite + Hono cut Trinity's cold launch 37%
We rewrote Trinity's desktop from Next.js + React to Solid + Vite + Hono. Cold launch is 37% faster, the bundle is 33% smaller, idle memory is 19% lower.
Read more
Engineering11 min read
The Ralph Wiggum Loop, evolved
The bash loop proved AI agents can ship code — but it could not hold a living plan, let you steer it, or let a team build together. Here is how Trinity evolved the loop into a collaborative, plan-first release pipeline.
Read more