Humley
assistantsConversational AI for trusted answers
AI code tools assist with writing, testing, reviewing, and debugging software across a broad range of programming languages and environments. The 344 tools here include IDE integrations, web-based coding environments, specialized tools for data pipelines, and platforms for non-developers building internal apps.
Conversational AI for trusted answers
Build chatbots for voice and messaging
Chat with your data to find insights
Unified project management and CRM
AI testing for web and mobile apps
Reference codes for Midjourney style consistency
Free no-code RPA and desktop automation
No-code software for business processes
Infrastructure for turning expertise into branded AI products
Build and deploy mobile apps without coding
Creates artistic QR codes with AI technology
400+ pre-built integrations to automate routine tasks
Monitor AI coding agents and catch errors before production
Meeting scheduling
AI study platform with writing, math, and flashcards
Infrastructure for AI agents that run company workflows
Real-time coding feedback in Slack
Add AI chat to your website in minutes
Create an AI trading bot for crypto markets
Screen recording and video editing automation
AI products for healthcare and enterprise
Online betting platform with sports and casino games
Build professional AI apps and online businesses without coding
AI code analysis and vulnerability detection
The category is wide and includes tools that serve very different audiences. Experienced developers typically want tools that integrate into their existing editor and support their specific language stack well. Teams may prefer tools with collaboration features, shared context, and audit logging. Non-developers building internal tools are better served by visual or low-code platforms like Dynaboard AI. Bug-fixing tools like FixThisBug.de focus on a narrow but high-value task. Code review and quality tools like GitRoll and Relicx focus on testing and reliability rather than generation. When comparing tools, practical benchmarks on your own codebase outperform general capability claims. Also consider how the tool handles context: tools with larger context windows handle full-file and multi-file edits more reliably. Security considerations include whether your code leaves your environment and under what terms it may be used to train future models.