opencode Reviews

OpenAI Reviews

opencode mentions (67)

• ZCode: Claude Code from the Makers of GLM

  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 / 1 day ago

• AI for Less Popular Programming Languages

  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 / 4 days ago

• How to Run Reliable Local LLM Agents on an RTX 3090: A Benchmark (5 Models, Priced in Watts)

  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 / 5 days ago

• The head chef model of AI collaboration

  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 / 14 days ago

• Testing GLM-5.2 on OpenCode: I'm impressed!

  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 / 15 days ago

OpenAI mentions (398)

• How to track LLM costs per customer in production

  Provider-side metadata. Both major providers expose per-user tagging. OpenAI accepts a user parameter on the Chat Completions and Responses APIs, and the OpenAI Usage API (launched December 2024) supports group_by=user_id for programmatic per-user cost breakdown. The Costs endpoint requires an admin key. Anthropic accepts metadata.user_id on every API request, capped at 256 characters and explicitly not for PII.... - Source: dev.to / about 1 month ago

• How I Run 3 Production AI SaaS on $5/Month of Hosting

  For solo founders who don't run their own gateway: use Claude direct for highest quality, OpenAI for proven reliability, or wire up multi-provider routing via something like Prism (or build your own — see Prism's architecture once it's published). - Source: dev.to / about 1 month ago

• Cursor Just Released Composer 2.5. Here's What Actually Changed for AI Coding Agents.

  Composer 2 originally gained attention because Cursor delivered strong coding performance at dramatically lower token costs than frontier proprietary models. Cursor positioned it as a cheaper alternative to systems from Anthropic and OpenAI. (Cursor). - Source: dev.to / about 1 month ago

• The Text Field is the New Dashboard

  The most extreme case arrived in April 2026. In 2024, OpenAI CEO Sam Altman predicted that a one-person billion-dollar company "would have been unimaginable without A.I., and now it will happen." He maintained a betting pool with fellow tech CEOs over when it would arrive. In April 2026, he emailed the New York Times claiming he won the bet and that he "would like to meet the guy.". - Source: dev.to / about 2 months ago

• What the F*ck Are We Even Measuring? The Definition Problem in AI Evals

  Everyone sees what they want in their benchmarks. OpenAI sees reasoning capability. Anthropic sees safety and helpfulness. Google sees multimodal understanding. The academic community sees generalization. Same numbers, completely different conclusions. - Source: dev.to / about 2 months ago