[HN Gopher] Goose: An open-source, extensible AI agent that goes...
       ___________________________________________________________________
        
       Goose: An open-source, extensible AI agent that goes beyond code
       suggestions
        
       Author : sansui12
       Score  : 233 points
       Date   : 2025-01-30 16:27 UTC (4 days ago)
        
 (HTM) web link (block.github.io)
 (TXT) w3m dump (block.github.io)
        
       | juunpp wrote:
       | It advertises that it runs locally and that it is "extensible"
       | but then requires you to set up a remote/external provider as the
       | first step of installation? That's a rather weird use of "local"
       | and "extensible". Do words mean anything anymore?
        
         | kylecazar wrote:
         | Yeah, they seem to be referring to the Goose agent/CLI that are
         | local. Not models themselves.
        
           | anonzzzies wrote:
           | You can run ollama, so no, not only Goose itself.
        
         | demarq wrote:
         | Did you not see Ollama?
        
         | tonygiorgio wrote:
         | Can't you just run ollama and provide it a localhost endpoint?
         | I dont think its within scope to reproduce the whole local LLM
         | stack when anyone wanting to do this today can easily use
         | existing better tools to solve that part of it.
        
         | raincole wrote:
         | You went as far as checking how it works (thus "requires you to
         | set up a remote/external provider as the first step").
         | 
         | But you didn't bother checking the very next section on side
         | bar, Supported LLM Providers, where ollama is listed.
         | 
         | The attention span issue today is amusing.
        
           | anonzzzies wrote:
           | > The attention span issue today is amusing.
           | 
           | I find it rather depressing. I know it's a more complex
           | thing, but it really feels irl like people have no time for
           | anything past a few seconds before moving onto the next
           | thing. Shows in the results of their work too often as well.
           | Some programming requires very long attention span and if you
           | don't have any, it's not going to be good.
        
             | EVa5I7bHFq9mnYK wrote:
             | But people really have no time. There is only one brain and
             | thousands of AI startups pitching something every day.
        
               | anonzzzies wrote:
               | Yeah, don't need to try any until everyone says 'you have
               | to'. Which happened with Aider and later Cline & Cursor.
        
             | unification_fan wrote:
             | But this is an elevator pitch. I didn't come here to be
             | marketed to, yet I am being marketed to.
             | 
             | So if you're going to market something to me at least do it
             | right. My attention span is low because I don't really give
             | a shit about this.
        
         | hiyer wrote:
         | You can use it with ollama too
        
       | XorNot wrote:
       | I don't know how useful this is, but my immediate reaction to the
       | animation on the front page was "that's literally worse then the
       | alternative".
       | 
       | Because the example given was "change the color of a component".
       | 
       | Now, it's obviously fairly impressive that a machine can go from
       | plain text to identifying a react component and editing it...but
       | the process to do so literally doesn't save me any time.
       | 
       | "Can you change the current colour of headercomponent.tsx to
       | <some color> and increase the size vertical to 15% of vh" is a
       | longer to type sentence then the time it would take to just open
       | the file and do that.
       | 
       | Moreover, the example is in a very "standard" format. What
       | happens if I'm not using styled components? What happens if that
       | color is set from a function? In fact none of the examples shown
       | seem gamechanging in anyway (i.e. the Confluence example is also
       | what a basic script could do, or a workflow, or anything else -
       | and is still essentially "two mouseclicks" rather then writing
       | out a longer English sentence and then I would guess, waiting
       | substantially more time for inferrence to run.
        
         | taneq wrote:
         | On the one hand, this isn't a great example for you because you
         | already knew how to do that. There's probably no good way to
         | automate trivial changes that you can make off the top of your
         | head, and have it be faster than just doing it yourself.
         | 
         | I've found LLMs most useful for doing things with unfamiliar
         | tooling, where you know what you want to achieve but not
         | exactly how to do it.
         | 
         | On the other hand, it's an okay test case because you can
         | easily verify the results.
        
         | pjm331 wrote:
         | Yeah the fact that just composing the first prompt would take
         | me longer than just doing the thing is my biggest blocker to
         | using any of these tools on a regular basis
        
           | ehnto wrote:
           | Which is also assuming it gets it right the first prompt, and
           | not 15 minutes of prompt hacking later, giving up and doing
           | it the old fashioned way anyway.
           | 
           | The risk of wasted time is higher than the proposed benefit,
           | for most of my current use cases. I don't do heaps of glue
           | code, it's mostly business logic, and one off fixes, so I
           | have not found LLMs to be useful day to day at work.
           | 
           | Where it has been useful is when I need to do a task with
           | tech I don't use often. I usually know exactly what I want to
           | do but don't have the myriad arcane details. A great example
           | would be needing to do a complex MongoDB query when I don't
           | normally use Mongo.
        
             | oxidant wrote:
             | Cursor + Sonnet has been great for scaffolding tests.
             | 
             | I'll stub out tests (just a name and `assert true`) and
             | have it fill them in. It usually gets them wrong, but I can
             | fix one and then have it update the rest to match.
             | 
             | Not perfect, but beats writing all the tests myself.
        
         | robertwt7 wrote:
         | I agree with the process not saving any of our time. however
         | aren't examples supposed to be simple?
         | 
         | Take it from Aider example: https://github.com/Aider-AI/aider
         | It asked to add a param and typing to a function. Would that
         | save us more time? I don't think so. but it's a good peek of
         | what it can do
         | 
         | just like any other hello world example i suppose
        
           | two_handfuls wrote:
           | Examples are supposed to be simple when they illustrate a
           | process we already know works.
           | 
           | With AI the challenge is that we need to convince the reader
           | that the tool will work. So that calls for a different kind
           | of example.
        
             | throwaway290 wrote:
             | If you don't know how implement it how can you be sure LLM
             | will do it correctly?
             | 
             | If the task is not simple then break it into simple tasks.
             | Then each of them is as easy as color change.
        
       | alexkehayias wrote:
       | So I gave goose a whirl and I actually really like the approach
       | they are taking, especially because I use emacs and not vscode. I
       | would recommend people try it out on an existing project--the
       | results are quite good for small, additive features and even ones
       | that are full stack.
       | 
       | Here's a short writeup of my notes from trying to use it
       | https://notes.alexkehayias.com/goose-coding-ai-agent/
        
         | terhechte wrote:
         | Which LLM did you use with Goose? That really affects the
         | quality of the outcome
        
           | alexkehayias wrote:
           | I'm using gpt-4o which I think is the default for the OpenAI
           | configuration.
           | 
           | Haven't tried other models yet but old like to see how
           | o3-mini performs once it's been added.
        
             | alexjhancock wrote:
             | Hi - Alex here from the Goose team. We do already support
             | o3-mini. If you're using the OpenAI provider you can enter
             | that model in the settings screen of the app. Let me know
             | if you have any trouble.
        
       | grimgrin wrote:
       | this is the page i'd link to
       | 
       | https://block.github.io/goose/docs/goose-architecture/
        
       | aantix wrote:
       | How does this compare to Cline or Cursor's Composer agent?
        
       | bckr wrote:
       | Today I decided that what I need is:
       | 
       | - prompt from command line directly to Claude
       | 
       | - suggestions dumped into a file under ./tmp/ (ignored by git)
       | 
       | - iterate on those files
       | 
       | - shuttle test results over to Claude
       | 
       | Getting those files merged with the source files is also
       | important, but I'm not confident in a better way than copy-
       | pasting at this point.
        
         | vessenes wrote:
         | Aider is fantastic. Worth a look.
        
           | bckr wrote:
           | I've been playing with it and I don't like it that much? I'm
           | not sure why. It feels a little buggy and like it's doing too
           | much.
        
             | yoyohello13 wrote:
             | You're being downvoted for some reason but I feel the same.
             | It's cool tech but I've found I often need to revert
             | changes. It's far too aggressive with tweaking files. Maybe
             | I can adjust in the settings, idk. Also, it's expensive as
             | hell to run with Claude sonnet. Cost me like $0.01 per
             | action on a small project, insane. At this point I still
             | prefer the chat interface.
        
               | extr wrote:
               | You can basically get the same experience as aider with
               | an MCP server like https://github.com/rusiaaman/wcgw.
               | It's not perfect - sometimes has trouble with exact
               | syntax of find/replace. But it's free to use up to your
               | regular Claude subscription usage limit. I actually use
               | it more than Cursor, because it's easier to flip back and
               | forth between architecting/editing.
        
               | yoyohello13 wrote:
               | Thanks! I'll take a look at this. It always kind of
               | annoyed me to pay for API credits on top of a
               | subscription, lol.
        
               | M4v3R wrote:
               | $0.01 per action that can potentially save you tens of
               | minutes to hours of work sounds like a pretty good deal
               | to me, if I compare this to my hourly wage.
        
               | sangnoir wrote:
               | > $0.01 per action that can potentially save you tens of
               | minutes to hours of work sounds like a pretty good deal
               | to me
               | 
               | Save _tens_ of hours in one commit?! No model is this
               | good yet[1] - especially not Aider with its recommended
               | models. I fully agree with parent - current SoTA models
               | require lots of handholding in the domains I care about,
               | and the AI chat /pairing setup works much better compared
               | to the AI creating entire commits/PRs before a human gets
               | to look at it.
               | 
               | 1. If they were, Zuckerberg would have already announced
               | another round of layoffs.
        
               | joshstrange wrote:
               | Ten hours in one commit? Nope, not yet, but it works
               | great to test out ideas and get unstuck when trying to
               | decide how to proceed. Instead of having to choose, just
               | do both or at least try 1 right away instead of bike-
               | shedding.
               | 
               | I often get hung up on UI, I can't make a decision on
               | what I think will look decent and so I just sort of lock
               | up. Aider lets me focus on the logic and then have the
               | LLM spit out the UI. Since I've given up on projects
               | before due to the UI aspect (lose interest because I
               | don't feel like I'm making progress, or get overwhelmed
               | by all the UI I'll need to write) this is a huge boon to
               | me.
               | 
               | I'm not incapable of writing UI, I'm just slower at it so
               | Aider is like having a wiz junior developer who can crank
               | out UI when I need it. I'm even fine to rewrite every
               | line of the UI by hand before "shipping", the LLM just
               | helps me not get stuck on what it should look like. It
               | lets me focus on the feature.
        
               | joshstrange wrote:
               | $0.01 per action? Yeah, and I've gotten up to 10 cents or
               | so I think in a "single" action but so what? The most
               | I've ever spent with it in one go has been like $5 for a
               | couple hours (maybe even 6-8) of on and off usage. That
               | $5 was completely worth it.
               | 
               | Also you can use local models if you want it to be
               | "free".
        
               | yoyohello13 wrote:
               | A running total of the "cost of my side project" doesn't
               | feel particularly good.
        
             | vessenes wrote:
             | Interesting. I occasionally feel that way with Claude as
             | the backend. Still the best backend that's reliable,
             | although o3-mini-high in architecture mode with Claude is
             | very good.
             | 
             | I find Claude wants to edit files that I don't like to be
             | edited often. Two ways I deal with that - first, you can
             | import 'read only' files, which is super helpful for
             | focusing. Second, you can use a chat mode first to talk
             | over plans, and when you're happy say "go".
             | 
             | I think the thing to do is try and use it at a fairly high
             | level, then drop down and critique. Essentially use it as a
             | team of impressive motivation and mid quality.
        
           | anonzzzies wrote:
           | There are many (ignored) requests, to, like cursor, copilot
           | and cline, automatically pick the files without having to
           | specify them. Not having that makes it much worse than those
           | others. I was a fan before the others but having to add your
           | files is not a thing anymore.
        
             | bckr wrote:
             | Hmm, I want to add my own files. This is because in my
             | workflow I often turn to the web UI in order to get a fresh
             | context.
             | 
             | I do like the idea of letting the model ask for source
             | code.
             | 
             | It's all about attention / context.
        
               | anonzzzies wrote:
               | But one does not exclude the other; some like one some
               | like the other. I am used to Cline now and it's pretty
               | good at picking the correct files, however, I get better
               | results out of aider once the files are in.
        
         | bckr wrote:
         | I've almost finished an interactive file selector inspired by
         | git add interactive, with the addition of a tree display.
         | 
         | I'm giving myself the option to output collated code to a file,
         | or copy it to clipboard, or just hold onto it for the next
         | prompt.
         | 
         | I know aider does this stuff, but because I'm automating my own
         | workflow, it's worth doing it myself.
        
         | lordswork wrote:
         | I'm building this for myself because I want it too. I recommend
         | you do the same, because it's been really fun to build and
         | teaches you a lot about what LLMs can and cannot do well.
         | 
         | I plan to share it on Github, but waiting for my employer's
         | internal review process to let me open source it as my own
         | project, since they can legally claim all IP developed by me
         | while employed there.
        
           | horsawlarway wrote:
           | I also built this for myself, and I really do suggest it as a
           | good project to get a grounded idea of what models can
           | handle.
           | 
           | Mainly - tool calling support just merged in llama.cpp
           | (https://github.com/ggerganov/llama.cpp/pull/9639) this week,
           | and it's been a fun exercise to put local LLMs through the
           | wringer to see how they do at handling it.
           | 
           | It's been a mixture of "surprisingly well" and "really
           | badly".
        
         | dbdoskey wrote:
         | You should try cline. I found it with Anthropic to be
         | invaluable.
        
       | esafak wrote:
       | Are people finding agent frameworks useful or they are
       | unnecessary dependencies like Langchain?
        
       | Keyframe wrote:
       | I don't know if anyone find this useful, but it seems rather
       | useless / not working? I tried with numerous online and local
       | llms for good measure. I installed that computerController
       | extension and tried couple of dozens different versions of open a
       | website (url) in a browser and save a screenshot. Most of the
       | time it wouldn't even open a website, and I never got a
       | screenshot. At best it did open a website once and saved a html
       | (even though I asked a screenshot); and that one was unique in a
       | bunch when it did something instead of complaining it can't find
       | AppleScript or whatever on a linux machine.. I qualified the ask
       | by telling it it's on linux. It managed to find which distro it
       | was on even. Really weird overall.
        
         | DrewHintz wrote:
         | I've had luck with a workflow similar to:
         | 
         | git clone a repo
         | 
         | Open goose with that directory
         | 
         | Instruct it to discover what the repo does
         | 
         | Ask it to make changes to the code, being detailed with my
         | instructions.
         | 
         | I haven't tried computerController, only Goose's main
         | functionality.
        
       | goldenManatee wrote:
       | Regarding the "Extensible," doesn't that completely moot its
       | whole point?
        
       | pzo wrote:
       | This looks very promising. I only played a little bit yesterday
       | but they really need to polish the UI. Comparing to desktop
       | version of chatgpt or perplexity they are in much lower league.
       | Some feedback for team:
       | 
       | 1) use better font and size
       | 
       | 2) allow to adjust shortcuts and have nice defaults with easy
       | change
       | 
       | 3) integrate with local whisper model so I can type with voice
       | triggered with global shortcut
       | 
       | 4) change background to blend with default system OS theme so we
       | don't have useless ugly top bar and ugly bottom bar
       | 
       | 5) shortcuts buttons to easily copy part of conversion or full
       | conversation, activate web search, star conversion so easy to
       | find in history etc.
       | 
       | They should get more inspiration from
       | raycast/perlexity/chatgpt/arcbrowser/warpai ui/cursor
        
       | po wrote:
       | Have many other projects put MPC servers
       | (https://modelcontextprotocol.io/introduction) to use since it
       | was announced? I haven't seen very many others using it yet.
        
         | paulgb wrote:
         | Cursor also just got support this week. Overall it's still
         | early (MCP only came out a couple of months ago) but seeing
         | multiple clients that allow it to be used with non-Anthropic
         | models, and getting good results, makes me bullish for MCP.
         | 
         | My colleague has working on an MCP server that runs Python code
         | in a sandbox (through https://forevervm.com, shameless plug).
         | I've been using Goose a lot since it was announced last week
         | for testing and it's rough in some spots but the results have
         | been good.
        
       | bArray wrote:
       | Running locally is such an important feature, running elsewhere
       | is an instant non-starter for me. I also want the LLM to be able
       | to read the code to build an in-context solution, but not be able
       | to make changes unless they are strictly accepted.
        
       | letniq wrote:
       | Is it the same as ollama?
        
       | 93po wrote:
       | I'm confused what this does that Cursor doesn't. The example it
       | shows on the front page is something Cursor can also easily do.
        
         | netfl0 wrote:
         | Open source licensing where the limit is on the ai-backend
         | right?
        
         | lordswork wrote:
         | The one that stands out most to me is that it doesn't bundle
         | the AI features with the editor. This is a standalone
         | application that runs on the side of your editor/tools of
         | choice.
        
       | betimsl wrote:
       | Does anyone know alternatives to this? GUI Frontend for various
       | AI providers? (incl. ollama, etc)
        
       | register wrote:
       | But... how does it work? The documentation is really confusing .
       | How to make it aware of code file and project structure?
        
         | DrewHintz wrote:
         | I tell it to discover that itself by asking leading questions:
         | "What does this repo do?" "How do you run its unit tests?"
         | "What does file foo do?"
        
       | yencabulator wrote:
       | This is amusing/worrying.
       | 
       | > Make sure to confirm all changes with me before applying.
       | 
       | https://block.github.io/goose/docs/guides/using-goosehints
       | 
       | So, we're supposed to rely on LLM not hallucinating that it is
       | allowed to do what it wants?
        
         | ramesh31 wrote:
         | >So, we're supposed to rely on LLM not hallucinating that it is
         | allowed to do what it wants?
         | 
         | Yes. Frontier models have been moving at light speed over the
         | last year. Hallucinations are almost completely solved,
         | particularly with Anthropic models.
         | 
         | It won't be long before statements like this sound the same as
         | "so you mean I have to trust that my client will always have a
         | stable internet connection to reach out to this remote server
         | for data?".
        
           | feznyng wrote:
           | This is missing the human language ambiguity problem. If you
           | don't perfectly specify your requirements and it
           | misinterprets what you're asking for that's going to be a
           | problem regardless of how smart it is. This is fine with code
           | editing since you've got version control and not so great
           | when running commands in your terminal that can't be as
           | trivially reverted.
           | 
           | Besides that, you can absolutely still trick top of the line
           | models: https://embracethered.com/blog/posts/2024/claude-
           | computer-us...
           | 
           | Hallucination might be getting better, gullibility less so.
        
       ___________________________________________________________________
       (page generated 2025-02-03 23:02 UTC)