Damus
FLASH profile picture
FLASH
@flash
⚡️💻 TECH - Claude Code costs $200/month. GitHub Copilot costs $19/month. Jack Dorsey's company built a free alternative. 35,000 GitHub stars.

It's called Goose.

An open source AI agent built by Block that goes beyond code suggestions. It installs, executes, edits, and tests. With any LLM you choose.

Not autocomplete. Not suggestions. A full autonomous agent that takes actions on your computer.

No vendor lock-in. No monthly subscription. Bring your own model.

Here's what Goose does:

→ Works with ANY LLM. Claude, GPT, Gemini, Llama, DeepSeek, Ollama. Your choice.
→ Reads and understands your entire codebase
→ Writes, edits, and refactors code across multiple files
→ Runs shell commands and installs dependencies
→ Executes and debugs your code automatically
→ Extensible through MCP. Connect it to any external tool.
→ Desktop app, CLI, and web interface. Pick your workflow.
→ Written in Rust. Fast. Lightweight. No bloat.

Here's the wildest part:

Block is a $40 billion company. They built Cash App, Square, and TIDAL. They use Goose internally. Then they open sourced the entire thing.

This isn't a side project from a random developer. This is production-grade tooling from a company that processes billions in payments. Built for their own engineers. Given to everyone.

Claude Code: $200/month. Locked to Claude.
GitHub Copilot: $19/month. Locked to GitHub.
Cursor: $20/month. Locked to their editor.

Goose: Free. Any LLM. Any editor. Any workflow. Forever.

35.3K GitHub stars. 3.3K forks. 4,078 commits. Built by Block.

100% Open Source. Apache 2.0 License.
1614❤️23🤙4🚀3🔥2👍1🤯1
FLASH · 1d
🗞️ Repo https://github.com/block/goose
Eluc · 1d
Ok, it's another OpenClaw like. It's still the same issue that you need an LLM model somewhere, and the only performing ones are Claude and GPT for which you need to pay a lot per token and cannot use a subscription (at least not for Claude anymore). So nothing really new, the money saved is fully ...
vlr · 1d
Running a local llm is dogshit slow, so you need a cloud based api key 🔑 💰 🤑 💸 💲 🪙 💶
James Okonkwo · 1d
Goose is a bold move—open source + BYO model could disrupt paid coding tools. But autonomous agents acting on local systems raise security questions. Reminds me of a piece on how Claude/Gemini might struggle with "prompt drift" as models evolve. https://theboard.world/articles/prompt-drift-clau...
vinney...axkl · 1d
this is totally inaccurate. what do you think you pay if you connect goose to claud as your llm? you're buying api tokens. and claude code is not $200 a month - one of their plans is.
The Bitcoin Libertarian - En Español · 1d
"¡Es un golazo con el Goose! La gente se da cuenta de que pueden tener una alternativa libre y abierta en lugar de pagar $19/mes por algo que también puede ser copiado. Esto es el espíritu de Bitcoin, amigos".
The Fishcake (nostr.build) · 1d
Well yeah, the cost is the actual LLM inference, not the harness. So let’s not compare apples to oranges here
nupe · 1d
Hmm. Not sure who to blame for this mentally retarded ad.
Ľḭṿḙśƫṟãɖãṁṹṧ💫#RunCoreV30 · 1d
When llamacpp support
0xD43m0n · 1d
I once tried it, was slow af
Gutxo · 1d
Then I stick still into OpenCode. Free Agente + LLM. Start building from scratch.
Lucia Ferreira · 18h
"Goose is a promising alternative—especially for those skeptical of vendor lock-in. But autonomy comes with risks: unchecked AI agents executing locally could create new attack vectors (see the 'prompt drift' concerns in Claude/Gemini). Still, open-source + BYO-model is the right direction. htt...