Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Human brain is two separate organs, Stanford Medicine-led research finds(stanford.edu ↗)
    34comments
  2. If math is more than proof, we need to better celebrate the rest of it(terrytao.wordpress.com ↗)
    10comments
  3. GPT-6 Astra Solves a WWI German Radio Cipher(prinzai.com ↗)
    12comments
  4. San Francisco Onion Futures Company(onionfutures.com ↗)
    56comments
  5. Android 17 is the first since 3.x to add new APIs without releasing to the AOSP(grapheneos.social ↗)
    372comments
  6. Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step(github.com/awlevin ↗)
    26comments
  7. Science Is Open Software(jepedersen.dk ↗)
    29comments
  8. SDCC – Small Device C Compiler(sourceforge.net ↗)
    15comments
  9. Cloudflare Quick Tunnels(cloudflare.com ↗)
    275comments
  10. NASA-IBM Lunar Foundation open-Source Geospatial AI Model(usra.edu ↗)
    1comments
  11. Why building a Rust LSP is hard(rust-glancer.github.io ↗)
    26comments
  12. You can run Git on object storage if you re-make packfiles(tigrisdata.com ↗)
    6comments
  13. Saving another 100TB of RAM(cloudflare.com ↗)
    66comments
  14. How to Write with an LLM(sockpuppet.org ↗)
    317comments
  15. How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip(ieee.org ↗)
    78comments
  16. Ctenophores: Wonders of Biology(quantamagazine.org ↗)
    4comments
  17. Veronese's Dogs(publicdomainreview.org ↗)
    discuss
  18. The first new cat species discovered in 100 years(nationalgeographic.com ↗)
    96comments
  19. Goroutine Leak Profiles(go.dev ↗)
    2comments
  20. OpenJev(openjev.com ↗)
    257comments
  21. Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash(cactuscompute.com ↗)
    88comments
  22. Photon-Emission-Guided Laser Fault Injection Enables RP2350 Secure Debug(ledger.com ↗)
    66comments
  23. Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)(arxiv.org ↗)
    12comments
  24. The Farnese letter(simonklee.dk ↗)
    6comments
  25. Minimal Phone 2(minimalcompany.com ↗)
    215comments
  26. Stepfun Step 5 Preview (LLM): On AA Pareto frontier(artificialanalysis.ai ↗)
    1comments
  27. Xcode 27.1 Beta Release Notes(developer.apple.com ↗)
    98comments
  28. Cyclomatic Complexity in C#(ndepend.com ↗)
    18comments
  29. Inside ZCode: Silently uploading your Git history to the cloud(ferstar.org ↗)
    97comments
  30. Warez: The Infrastructure and Aesthetics of Piracy (2021)(archive.org ↗)
    53comments

Show HN: Gigacode – Use OpenCode's UI with Claude Code/Codex/Amp

27 pointsby 7mo agogithub.com
11 comments
Gigacode is an experimental, just-for-fun project that makes OpenCode's TUI + web + SDK work with Claude Code, Codex, and Amp.

It's not a fork of OpenCode. Instead, it implements the OpenCode protocol and just runs `opencode attach` to the server that converts API calls to the underlying agents.

We build this to scratch our itch of being able to rapidly switch between coding agents based on the task at hand. For example, we find that:

- Claude Code is the best executor & fast iterator - Codex (high) is the best for complex or long-running tasks - OpenCode for fine-tuned, do-exactly-as-I-say edits

I personally believe that harnesses matter almost as much as the models in 2026. OpenCode lets you swap out models already, but the CC & Codex harnesses + system prompts make a big difference in practice.

Under the hood, this is all powered by our Sandbox Agent SDK:

- Sandbox Agent SDK provides a universal HTTP API for controlling Claude Code, Codex, and Amp - Sandbox Agent SDK exposes an OpenCode-compatible endpoint so OpenCode can talk to any agent - OpenCode connects to Sandbox Agent SDK via attach

I want to emphasize: the Anomaly folks are doing awesome work with OpenCode agent + Zen + Black. I use OC regularly alongside CC & Codex depending on the task. Gigacode is only possible because OpenCode is insanely flexible, hackable, and well documented.

Give it a try:

$ curl -fsSL https://releases.rivet.dev/sandbox-agent/latest/gigacode-ins... | sh

Check out the project, architecture, and other install options:

https://github.com/rivet-dev/sandbox-agent/tree/main/gigacod...

7mo agoHN ↗

I personally believe that harnesses matter almost as much as the models in 2026.

Agreed. Great work

7mo agoHN ↗

Spontaneously I would like a protocol between agents and the clients and that's exactly what agentclientprotocol.com is. I wonder if you shuffle acp over https is it then similar to sandbox api used here?

7mo agoHN ↗

Yes. We want to support ACP. They have a spec for HTTP transport in the works, but there is nothing public on it. Trying to backchannel to the right folks.

7mo agoHN ↗

I feel like this was made for me. I really like the OpenCode UI.

Maybe this will finally create an ecosystem interchangeable LLM backends and UIs. I hope this will go beyond just coding agents.

7mo agoHN ↗

Been using it for a bit now, it's very convenient if I may say so myself. We're shipping a big stability update in a few minutes – would love feedback!

7mo agoHN ↗

Doubtful, AI cloud needs to lock in users. There's no world where they justify their values and say "the user can switch at any time"

7mo agoHN ↗

That's why I choose to distance myself from those vendors and products :)

The interesting stuff is happening in (free and) open source software.

7mo agoHN ↗

This looks neat. Thank you!

How does this relate to the recent changes of not being able to use a Claude Code Max subscription outside of Claude Code anymore? I assume technically this would work with Gigacode but would still be against their ToS?

7mo agoHN ↗

What's the benefit of using opencode ui vs vscode with agents?

7mo agoHN ↗

OpenCode supports:

- TUI (I prefer this for most programming)

- Web UI (negligible difference than VS Code)

- Mobile support (via web UI)

- TypeScript SDK to automate