Explore AI Tools & Apps

Toone

Toone · Coding · Productivity

Toone is a native macOS workspace built for projects that run on AI agents. It keeps your agents, the repeatable routines they run, and the tools and knowledge they share in one place, so a workflow you describe once becomes something you can launch again and again. Built on Claude Code and Codex, it works alongside your own OpenAI or Anthropic subscription rather than selling a separate model plan. It's aimed at people who want to automate real work with AI agent workflows without wiring up scripts by hand. Access is invitation-only for now.

Pushary

RalphNex OÜ · Coding · Productivity

Pushary is a human-in-the-loop control panel for AI agents that routes approval requests to a real person before an agent does something risky. Instead of leaving Claude Code, Codex, Cursor, or any MCP agent to run unattended, you set per-tool rules once and the question lands on your phone, your Mac's notch, Slack, or the web app. You tap approve, deny, or type an answer, and the agent keeps working from where it paused. It's built for developers and small teams who want agent automation without giving up the final say. The service is operated by RalphNex OÜ and was created by Aadil Ghani.

AgentGit

Einsia AI · Coding · Productivity

AgentGit is an open-source AI agent session manager that saves your sessions as Git repositories, so the full process behind a task survives after the chat window closes. It stores the instructions, reasoning, tool calls, and decisions from agents like Claude Code, Codex, and OpenCode in a version-controlled session. Then it lets you share a read-only link, or hand the whole thing to another agent that continues from where you stopped. Ever lost hours of work because a teammate switched tools or finished for the day? AgentGit is built for exactly that moment.

QAgent

QAgent Inc. · Coding · Business

QAgent is an automated quality assurance platform for AI agents. You point it at your agent's endpoint, define the ground truth it should follow, and it runs test suites that score answer quality, hallucination rate, policy adherence and multi-turn memory on every release. It works as an LLM evaluation tool that anyone can run in minutes. It's built for solo developers and small teams who ship agents without a dedicated QA department.

ComputeArena

Base Compute Pty. Ltd. · Coding · Other

ComputeArena is a community benchmark platform for local AI. It collects AI throughput benchmarks from real machines, then ranks models by how fast they prefill prompts and decode tokens on specific chips. You install a CLI on macOS or Linux, run a model offline, and submit the signed report when you're ready to share it. The result is a benchmark leaderboard built from hardware people actually own, not a single lab's test bench.

Die With Me

Die With Me · Coding · Productivity

Die With Me is a free Mac menu bar app that turns your AI coding limits into a little social space. Think of it as an AI usage tracker with a heartbeat. It watches how much Claude Code and Codex usage you have left, shows your friends' remaining energy next to your own, and opens a chatroom once you drop to 20% or less. You build, you run out, you hang out with other exhausted humans, then you go back to making things.

NovaSynth by Noveum

Noveum · Voice & Language · Coding

NovaSynth by Noveum is a pre-production testing platform for AI voice and chat agents. It sends synthetic users at your agent over real SIP calls, LiveKit audio, and chat, complete with personas, interruptions, accents, and adversarial intent. The point is simple: find the failures in rehearsal, before a real caller finds them in production. Every run is captured as a full trace and scored against 30+ voice AI metrics. Agent simulation here means real telephony, not mocked transcripts.

Modaal

Modaal · Coding

Modaal is an AI mobile app builder that turns a plain-language description into native Swift and Kotlin apps for iOS and Android, from a single project. It's built for AI app development that ends in real code, not a web view in a native shell. It writes Swift and Kotlin that talk to the phone directly. It also orchestrates the coding agent you already pay for. Claude Code, Codex, Cursor and about ten other agents feed into a build-and-fix loop, so a prototype can reach the App Store and Google Play.

Bitrise

Bitrise Ltd. · Coding

Bitrise is a mobile DevOps platform for building, testing, and shipping iOS and Android apps without babysitting your own build machines. It runs continuous integration for mobile apps and continuous delivery (CI/CD) on managed macOS and Linux infrastructure, so a push to your repo triggers a build, your tests run, and a signed release goes out to testers or the store. It's built for mobile teams that want Apple silicon and fresh Xcode without maintaining the servers themselves. Fair warning: the free tier is small, and paid tiers climb fast.

AppwriteWhat Appwrite did right

Appwrite · Coding

Appwrite is an open-source backend platform that packs the core services of an app into one place. Auth, databases, storage, serverless functions, messaging, realtime, and hosting all ship together. Teams spend their time on the product, not on wiring up a dozen separate services. It works as backend as a service, and you can run it as a managed cloud service or keep it as a self-hosted backend on your own servers, depending on how much control you want over where your data lives.

Weave Engineering Intelligence

Weave · Coding · Productivity

Weave Engineering Intelligence is an engineering analytics platform that measures how AI changes the way your team builds software. It combines LLM-driven analysis with DORA, SPACE, and survey data to score token spend, code quality, and output engineer by engineer. Teams use it to see where AI money actually pays off, route prompts to cheaper models, and ask plain-language questions about their engineering org. The goal is simple. Know where every AI dollar goes.

Buddy Works

Buddy (Buddy Works) · Coding · Productivity · Business

Buddy Works is a DevOps and platform engineering suite that automates the path from a git push to a live deployment. Teams use it as a continuous deployment tool: run builds and tests in containers, preview every pull request on its own environment, and ship to thousands of targets without touching server configs. The selling point is breadth: one tool covers CI/CD pipelines, environments, tunnels, domains and a dev cloud, so you don't have to stitch five services together.