What the person above is suggesting: * https://pi.dev/ * https://omp.sh/ Personally I also think that OpenCode is nice, their CLI version is enjoyable and their desktop/web version is mostly okay: * https://opencode.ai/. - Source: Hacker News / about 10 hours ago

I wired it into OpenCode, an open-source coding harness similar to Claude Code and Codex. I'm using an OpenCode Zen key and a Gemini key, and together, these give me access to multiple SOTA models for free, without touching a separate dashboard for each provider. - Source: dev.to / 10 days ago

I drove it from my coding-agent with a handful of commands. - Source: dev.to / 13 days ago

Https://pi.dev/docs/latest/providers#openai-codex is specific that it "Requires ChatGPT Plus or Pro subscription". https://opencode.ai are also both specific that it's for "Plus/Pro" subscriptions. Is there some link where you saw free tier Codex use in non-official apps is allowed by OpenAI? (I have used the free tier in the official Codex app, but as you said, labs can have different rules for official vs... - Source: Hacker News / 16 days 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 / about 1 month ago

You just need a few summaries occasionally. Standing up Ollama, a model, and an extraction pipeline to summarize five PDFs is overkill. If privacy isn't the constraint, a free web tool does it in seconds — ChatPDF and NotebookLM if you don't mind an account, or PDFSummarizer.net if you want no sign-up and formats like EPUB/PPTX handled for you. One caveat that matters specifically because this article is about... - Source: dev.to / 28 days ago

Last year I was heavily into Perplexity but for most of 2026 I've actually been using NotebookLM a lot more. Perplexity is still useful for just daily news, but when I want to research, when I want to summarise, when I want to learn... NotebookLM all the way. - Source: dev.to / 3 months ago

NotebookLM already sorted this on Google's side. You upload your sources, Gemini answers only from those sources, every answer comes with citations pointing to the exact passage. The catch was it's browser-only. No API. No way to wire it into your agent workflow. - Source: dev.to / 4 months ago

In Notebook LLM, add the information sources you use for studying and use different formats. It currently supports Latin American Spanish. - Source: dev.to / 4 months ago

Then there's NotebookLM. For me, this is the "holy grail" of studying. You feed it a few links, and it generates these incredibly fun, informative "Deep Dive" podcasts. I started listening to them on my daily commute, and honestly, I've never absorbed complex tech topics faster. - Source: dev.to / 4 months ago