AI tools

Most recommended

• ClaudeRecommended for debugging from logs, implementing tricky algorithms and performance tuning, but it makes mistakes on large codebase changes and needs close supervision.5175recommend
• Claude CodeAn agentic coding tool that writes, runs and tests code on its own, often replacing hand-coding entirely, though many report quality regressions after updates and broken code on complex work.4522recommend
• Claude OpusRecommended as a top coding model that fixes bugs and ships features with fewer mistakes than earlier LLMs, though critics cite weak architecture choices, usage limits and confident errors.3331recommend
• OpenAI CodexA coding agent many find as good as or better than Claude Code, thorough on hard problems, with generous $20-plan limits, though its output needs careful review.2474recommend
• Google GeminiRecommended for everyday questions, image and handwriting understanding, and coding or scripting help, but many report confidently invented facts and dislike it being pushed into every Google product.2195recommend
• ChatGPTA general-purpose chatbot that people use to research faster, understand health issues, learn topics and draft writing, though it often hallucinates and tells you what you want to hear.2186recommend
• OpenAI GPTRecommended for strong coding, debugging and research help with good reasoning and token efficiency, though critics cite hallucinations, overcomplication, verbose output and high cost.1205recommend
• Qwen 3.8 27BAn open-weights model that runs on a single high-end GPU and nears frontier coding quality, though it overthinks, burns tokens and struggles with complex tasks.1173recommend
• OpenCodeAn open-source coding agent recommended for mixing models and providers, including cheap or local ones, with a good-value Go plan; critics cite prompt privacy, security holes and bloat.1060recommend
• Z.ai GLMAn open-weight coding model close to frontier quality at a fraction of the cost, though critics cite slow, outage-prone hosting, erratic output and expensive self-hosting hardware.1043recommend
• KimiMoonshot's open-weight models rival top closed models at coding and research for a fraction of the price, though they can be slow and overthink.931recommend
• Pi coding agentA minimal coding agent harness that works with many models, uses fewer tokens and is easy to extend, though basics like subagents are missing and it has no sandboxing.892recommend
• Claude SonnetA capable coding model that has improved noticeably with each version and is faster and cheaper than Opus, though it needs careful supervision and usage limits bite.854recommend
• CursorAn AI code editor praised for in-editor review of agent changes, strong tab completion and working well in existing codebases; critics flag privacy worries and rising costs.853recommend
• DeepSeek V4 FlashA very cheap, fast model that people find close to frontier quality for coding and everyday tasks; critics say it errs more, loops, and needs steering.828recommend
• FableRecommended as a top coding model for hard, long-running tasks and large refactors, though critics cite over-engineered code, costly usage limits and safety guards that switch models mid-task.823recommend
• OpenClawAn open-source personal AI agent you message through Telegram or iMessage to automate tasks and coordinate tools, though critics agree it is a serious security risk.776recommend
• Claude Fable 5Recommended for long-horizon agentic work and hard reasoning, debugging and research problems where it beats Opus, though overbroad safety filters often block legitimate security and biology tasks.774recommend
• GPT-5.6 SolRecommended for handling large autonomous coding tasks, frontier math and tight, clean writing, but critics note it can get expensive and still makes baffling basic mistakes.734recommend
• GrokRecommended for fast, concise answers, real-time current events through X, and useful second opinions on code, but critics widely cite Musk-driven political bias and weak safety guardrails.727recommend
• Gemma 4Google's open-weight model family runs well on local hardware with strong quality and token efficiency for its size, though critics cite unreliable tool calling and weaker coding than Qwen.713recommend
• OpenRouterOne API and credit balance for nearly every AI model, making it easy to switch models, pick cheap providers and cap spending; critics flag quantized providers and broken caching.666recommend
• DeepSeekPeople pick DeepSeek as a very cheap, open-weight model that comes close to frontier models for many tasks, but its censorship of China-sensitive topics and data-security concerns draw criticism.611recommend
• Gemini FlashA fast, cheap model that many find good enough for everyday and focused tasks, though critics say it hallucinates and falls short on complex or long agentic coding work.607recommend
• GitHub CopilotRecommended as a cheap way to use many AI models with smooth VS Code integration and autocompletion, though critics resent tightening request limits, pricing changes and ads in PRs.571recommend
• QwenThe go-to open-weight model family for running capable coding and general AI locally on accessible hardware, though it falls short of frontier models like Claude Opus.474recommend
• llama.cppA fast, frequently updated engine for running open-weight models locally, with flexible GPU/CPU offloading and an OpenAI-compatible API server, though support for new models is often buggy at first.471recommend
• Model Context Protocol (MCP)A widely supported standard for plugging tools and services into AI agents with built-in auth and scoped access, though critics note heavy token use and a rough, unevenly supported spec.409recommend
• Jev by Typesafe AIA cheap, low-latency general classifier you redefine with a prompt instead of retraining, though critics call it overhyped and little more than standard LLM tech.392recommend
• Qwen3.6-35B-A3BA fast mixture-of-experts open model that runs well on consumer hardware and is surprisingly capable for its size, though it falls well short of frontier models on complex tasks.373recommend