Mini tools
▼ Latest
Intellij
Free mode
100% free
Freemium
Free Trial
Verified tools
-
Since the first release, Verdent has changed quite a bit. It started as a simple AI coding assistant. Now it feels much closer to a full workflow, something you can actually build with, not just generate code from. We've added multi-model planning, so you don’t have to rely on a single model's opinion anymore. You can see better plans upfront, before anything gets written. We also introduced built-in code review across models, which helps catch real issues earlier instead of discovering them halfway through. On top of that, Verdent now suggests what to do next as you go, and lets you reuse workflows through Skills, so you're not starting from scratch every time. A lot of smaller things improved too: better structure, and support for more models. Overall, it's less about "help me write code," and more about "help me get to a solid result."
-
lucas zhang🙏 5 karmaMay 28, 2024@IntellectiaReally cool product! I use it every day to do stock research.
Other tools
-
A spotlight-ish and unique design styled app for Mac with support for local LLMs and the major flagship LLM models via API key like OpenAi, Anthropic, xAi, Groq, Google, perplexity and last but not least Deepseek. The UI blends perfectly with the MacOS UI. Has support for keyboard shortcuts. It has Some design decisions adding a touch of uniqueness. You can contextually talk with it, like, with files, audio, and document texts. So far so good.
-
The tool's quality has dropped significantly over the past three months. The AI is taking three times longer to solve problems and is still making many mistakes. Accuracy has decreased by at least 60%. I had to manually fix everything and stop using the prompt. Unfortunately, it used to work very well for me, but now it no longer does.
- Sponsor
Rocket - Think it. Type it. Launch it. -
Cursor — v2Much stronger coding performance, with big benchmark gains over Composer 1.5 across CursorBench, Terminal-Bench 2.0, and SWE-bench Multilingual. Better long-horizon task solving, aimed at coding jobs that require hundreds of actions instead of shorter edit loops. Stronger base model training from Cursor’s first continued pretraining run, giving reinforcement learning a better foundation than before. Better price-to-intelligence balance, positioned as a much stronger model without giving up cost efficiency. Adds a faster same-intelligence variant and makes fast mode the default option.
-
Very helpful tool in my design process and coming up with new features!
-
Post
