Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. San Francisco Onion Futures Company(onionfutures.com ↗)
    41comments
  2. Android 17 is the first since 3.x to add new APIs without releasing to the AOSP(grapheneos.social ↗)
    359comments
  3. Human brain is two separate organs, Stanford Medicine-led research finds(stanford.edu ↗)
    2comments
  4. Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step(github.com/awlevin ↗)
    10comments
  5. SDCC – Small Device C Compiler(sourceforge.net ↗)
    13comments
  6. Science Is Open Software(jepedersen.dk ↗)
    24comments
  7. Cloudflare Quick Tunnels(cloudflare.com ↗)
    272comments
  8. How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip(ieee.org ↗)
    74comments
  9. NASA-IBM Lunar Foundation open-Source Geospatial AI Model(usra.edu ↗)
    discuss
  10. Why building a Rust LSP is hard(rust-glancer.github.io ↗)
    18comments
  11. Saving another 100TB of RAM(cloudflare.com ↗)
    59comments
  12. How to Write with an LLM(sockpuppet.org ↗)
    311comments
  13. Goroutine Leak Profiles(go.dev ↗)
    2comments
  14. You can run Git on object storage if you re-make packfiles(tigrisdata.com ↗)
    3comments
  15. The first new cat species discovered in 100 years(nationalgeographic.com ↗)
    89comments
  16. Xcode 27.1 Beta Release Notes(developer.apple.com ↗)
    87comments
  17. Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash(cactuscompute.com ↗)
    83comments
  18. OpenJev(openjev.com ↗)
    256comments
  19. Photon-Emission-Guided Laser Fault Injection Enables RP2350 Secure Debug(ledger.com ↗)
    64comments
  20. The Farnese letter(simonklee.dk ↗)
    6comments
  21. Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)(arxiv.org ↗)
    12comments
  22. Minimal Phone 2(minimalcompany.com ↗)
    207comments
  23. Cyclomatic Complexity in C#(ndepend.com ↗)
    17comments
  24. Claude Code now reads AGENTS.md if there is no Claude.md(claude.com ↗)
    217comments
  25. Inside ZCode: Silently uploading your Git history to the cloud(ferstar.org ↗)
    97comments
  26. LispBM is a concurrent Lisp for microcontrollers with message passing(lispbm.com ↗)
    3comments
  27. Warez: The Infrastructure and Aesthetics of Piracy (2021)(archive.org ↗)
    44comments
  28. Alibaba open-sources AI model that can detect cancer and nearly 150 conditions(scmp.com ↗)
    11comments
  29. How SpaceX streamlined the Raptor engine(construction-physics.com ↗)
    68comments
  30. The Implications of Linguistic Illegibility for LLM Security(arxiv.org ↗)
    26comments

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