Loading...
Loading...
Trinity: Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Trinity. This is an automatic list. We have not written a researched verdict for Trinity yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.
Free4Chat opens a temporary room where people and independently running AI agents work together. A room is created in a browser with a name and a nickname, needs no account and no permanent workspace, and expires automatically once empty. Inside it, participants use voice, text, file sharing and screen sharing, and can...
The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.
AGNT is a local first agent operating system: a desktop workspace for Windows, macOS and Linux where users bring their existing AI subscriptions, API keys or local models and have agents carry out whole jobs across research, coding, content and operations. A coordinating assistant called Annie manages the work, with me...
Open-source control plane for AI coding agents.
Amux is an open source control plane for AI coding agents. It runs Claude Code, Codex and Gemini CLI sessions side by side as named workers and gives them a shared task board, messaging that records the true sender, schedules and automatic recovery, all from one web dashboard. The aim is to let a single developer run a...
A native macOS terminal app built on Ghostty for running and supervising coding agents
Calyx is a native macOS terminal built for running several AI coding agents side by side. It hosts Claude Code, Codex, OpenCode, Hermes, Grok and pi in ordinary terminal panes, then adds a layer that tracks what each agent is doing, collects the prompts they raise, and routes code review back to the pane that wrote the...
Open-source autoresearch powered by autonomous coding agents.
CORAL is an open source autoresearch framework that runs teams of autonomous coding agents to improve solutions to a problem over long periods. Rather than asking one agent for one answer, it spawns several long lived agents, has each commit experiments, grades every attempt and shares what works, so the group keeps it...
Remote approvals, policy checks, and execution evidence for unattended AI agents.
DashClaw is an approval layer for AI agents that run unattended. Policies hold risky agent actions, such as a production deploy or a destructive database command, before they execute, and a person approves or denies them later from a dashboard or a phone while routine work continues. Every decision is written to a sign...