Explore AI Tools & Apps

SKI

SKI · Voice & Language · Coding

SKI is a free on-device voice assistant that puts a two-way spoken loop between you and your AI coding agent. Think of it as a voice assistant for AI coding agents: you speak the outcome you want, tools like Claude Code, Cursor, Codex, Gemini CLI, and OpenClaw do the work, and SKI reads the result back in a natural voice. Speech recognition and the voice itself run on your own machine, so audio and transcripts stay on your disk rather than in someone's cloud. It's voice coding turned into a conversation.

Denovo

Denovo · Coding · Business

Denovo is an AI cofounder platform that takes a one-line business idea and turns it into a running company. It writes the business plan, builds a website wired to Stripe for payments, and then runs ad campaigns and email outreach across multiple channels to bring in paying customers. The tool connects to more than 1,000 SaaS integrations, so the marketing and sales work happens inside the same place where the business gets built.

ClariLayer

ClariLayer · Coding

ClariLayer is a personal context layer for AI work, delivered over the Model Context Protocol (MCP). It works as AI context memory: it saves the facts, preferences, decisions, rules, and lessons you confirm, then hands them back to your AI client when a related task starts. Instead of re-explaining the same background every session, you build one authorized space that Claude Code, Cursor, Codex, or claude.ai can read from. It also seeds analytics context from SQL, dbt models, and notes, and checks saved definitions against real source evidence to surface mismatches as caveats.

MemoryCustodian

Zekun Wang (waittim) · Coding

MemoryCustodian is a free, open-source tool that gives coding agents durable project memory. It stores decisions, constraints, and rejected ideas as plain Markdown files inside your repo, then routes only the task-relevant pieces to the agent through a manifest. The result: less prompt stuffing and more consistent work across sessions, agents, and teammates. It's built for AI coding agent context management, not chat logs.

Prelint

Prelint · Coding

Prelint is an AI code review tool that checks each pull request against the specs and decisions your team already agreed on. Instead of hunting for bugs or style issues, it flags where code drifts from your pricing rules, architecture decisions, or compliance constraints before the change ships. It runs as a GitHub App, posts inline findings on the exact lines that triggered them, and keeps a searchable record of every product decision your code encodes.

G.I.A.ac

G.I.A.ac · Coding

G.I.A.ac is a prompt to app builder that turns a plain-language description into a working web app. You describe what you want, watch the actual files stream onto the screen as they're written, then push the result to your own GitHub and Vercel accounts with one click. It sits in the "vibe coding" camp. But unlike tools that hand you a sandbox demo and walk away, it ships something you own and can keep editing. That's the whole point: a no-code web app you actually control.

EasyCircuit

EasyCircuit · Coding · Productivity

EasyCircuit is an AI hardware prototyping tool that turns a plain-language idea into a working circuit. You describe what you want in chat, and it designs an editable schematic, explains every component choice, sources the parts into one made-to-order kit, and walks you from a breadboard test to a solder-ready perfboard layout. It's built for makers and first-time builders who don't want to read datasheets before they can build anything.

Prefactor

Prefactor · Coding

Prefactor is a runtime evaluation platform for AI agents. It's also agent performance monitoring with teeth. It records every step an agent takes as a trace, scores that step for quality, drift, and data risk, and then enforces an action when something crosses a line. Teams use it to hold a risky run for human approval, block an action outright, or keep watching with full visibility instead of finding out about the mistake from a customer email at 1am. Scoring is continuous. So is the enforcement.

Robynn AI

Robynn AI · Coding

Robynn AI is an agentic marketing platform that acts as an AI marketing tool for your site. It turns a website into a self-improving growth engine, and website optimization sits at the core of that work. You set a measurable goal on a page, Robynn audits it against your analytics, and it recommends evidence-backed fixes. Marketing automation runs the cycle. Nothing publishes until you approve it.

localskills.sh

localskills · Coding

localskills.sh is an agent skill registry and command-line tool for creating, versioning, and installing reusable agent skills and rules across your AI coding tools. Write a skill once, publish it to a shared library, and the agent skills CLI writes each tool's native format so the same instructions work in Cursor, Claude Code, Windsurf, and several others. Teams get access control, SSO, and audit logs on top of that library.

Openbase

Openbase · Coding

Openbase is a voice-first IDE and workspace built for developers who run AI coding agents. It turns scattered agent activity into one conversation. Start AI coding sessions by voice, route a task into the right workspace, approve sensitive commands, and review the resulting diff before anything lands. No more reconstructing what happened across chat threads and terminals. The whole session stays in one place.

Privent

Privent Technologies, Inc. · Coding

Privent is a runtime security layer built for n8n AI agents. It installs as a native workflow node and inspects the data your agent is about to send out, catching PII, PHI, and secrets before they reach an external LLM. Sensitive values get transformed into reversible tokens, risky runs get scored, and every decision lands in an audit log. Think of it as AI agent data control at the point where it matters. You can run it in Privent's cloud, in your own n8n engine, or fully on-prem.