opencode
Claude Code
Cursor
Google Antigravity
Windsurf Editor
warp by spolu
GitHub Copilot
VS Code
nanochat
GPT4All
Jan.ai
Poe
AnythingLLM
Ollama App
fullmoon
Khoj
opencode nanochatNo features have been listed yet.
Based on our record, opencode should be more popular than nanochat. It has been mentiond 67 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 2 days ago
OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 5 days ago
I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% โ never edited a single file. - Source: dev.to / 6 days ago
Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 15 days ago
If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 16 days ago
Andrej Karpathy just released nanochat - "The best ChatGPT that $100 can buy." In 4 hours on an 8xH100 node, you get a working ChatGPT clone. Not a toy. An actual LLM that writes stories, answers questions, and attempts math problems. - Source: dev.to / 2 months ago
The best teacher in AI. Nanochat is the definitive entry point for understanding LLM training โ a full-stack pipeline in ~8,300 lines of clean PyTorch covering tokenization, pretraining, SFT, and reinforcement learning. Trains a 561M ChatGPT clone in ~4 hours for ~$100 (or ~$15 on spot instances). - Source: dev.to / 3 months ago
You're missing the point. Karpathy has other projects, e.g. : https://github.com/karpathy/nanochat You can train a model with GPT-2 level of capability for $20-$100. But, guess what, that's exactly what thousands of AI researchers have been doing for the past 5+ years. They've been training smallish models. And while these smallish models might be good for classification and whatnot, people strongly prefer big-ass... - Source: Hacker News / 4 months ago
This doesn't preclude that he might be working on other projects that aren't public yet (as part of his work at Eureka Labs). 1: https://github.com/karpathy/nanochat. - Source: Hacker News / 5 months ago
I used this just now on https://github.com/karpathy/nanochat and here is the output site built from the wiki markdown: https://comforting-alfajores-8752fe.netlify.app/readme. - Source: Hacker News / 6 months ago
Claude Code - Transform hours of debugging into seconds with a single command. Experience coding at thought-speed with Claude's AI that understands your entire codebaseโno more context switching, just breakthrough results.
GPT4All - A powerful assistant chatbot that you can run on your laptop
Cursor - The AI-first Code Editor. Build software faster in an editor designed for pair-programming with AI.
Jan.ai - Run LLMs like Mistral or Llama2 locally and offline on your computer, or connect to remote AI APIs like OpenAIโs GPT-4 or Groq.
Google Antigravity - Google Antigravity - Build the new way
Poe - Fast, helpful AI chat from Quora
