Dify is a no-code/low-code platform for building agent workflows visually. It recently raised $30 million and is used by 280 enterprises across 1.4 million deployments. - Source: dev.to / 4 months ago

TL;DR: Pick LangGraph if you want maximum control over agent architecture. Go with CrewAI for structured role-based multi-agent pipelines. Choose AutoGen if you're in the Microsoft ecosystem and need research-grade flexibility. Try Dify if you want to build AI apps visually without writing orchestration code. And if you need production agents connected to 1,000+ tools with scheduling and memory built in, Nebula... - Source: dev.to / 4 months ago

Compared to multi-model platforms like Dify or n8n, this limitation feels rather restrictive. Or rather, if you're used to it, wouldn't ◎◎ be perfectly adequate? - Source: dev.to / 9 months ago

In the rapidly evolving landscape of artificial intelligence, the synergy between platforms and models is paramount for developing robust AI applications. Dify, an open-source LLM (Large Language Model) application development platform, offers seamless integration capabilities with CometAPI's powerful models. This article delves into the features of Dify, elucidates the integration process with CometAPI, and... - Source: dev.to / over 1 year ago

Africa’s tech ecosystem is ready to lead in AI and Web3, and Dify is the perfect tool to make that happen. As a Developer Advocate, I’m committed to empowering African developers to innovate, collaborate, and solve local challenges with these technologies. If you’re an African developer, join the Dify Africa Community, try out the platform, and let’s build the future together. What AI and Web3 solutions would you... - Source: dev.to / over 1 year ago

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 / 3 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 / 6 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 7 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