AgentGPT VS aider

Their PR descriptions aren't much better https://github.com/reworkd/AgentGPT/pull/1372#issue-19887599...

AgentGPT was an early agent framework designed to create, configure, and deploy autonomous AI agents. It mostly relies on looping OpenAI's GPT models like GPT-3.5 and GPT-4. AgentGPT allows users to set a goal for the AI, which autonomously plans, executes, and refines strategies to achieve it. This platform allows for both web browser access and local operation via Docker, or server deployment.

There's a few tools out there like AgentGPT (https://github.com/reworkd/AgentGPT, although it's a more conversational interface), and (https://github.com/logspace-ai/langflow) and others. I think most developers definitely prefer a code-first interface though like a library but haven't found one that's great yet. We've used them in the past but didn't have the best experience so would love to hear if anyone has worked with a library they found really flexible.

17. AgentGPT

I saw a post earlier this week saying that they feel the outputs from ChatGPT have been declining, and a lot of people agreed. There are a good amount of quality AI chat alternatives out there besides ChatGPT and some even offer GPT-4 for free! Here's a list of alternative chatbots to try out (I've tried all of these not some bs list): Perplexity: "The first conversational search engine" (GPT-3.5 Free / GPT-4 Paid $20 a month) Bing: Microsoft's Chatbot with multimodal capabilities. (GPT-4 Free) Poe: Quora's AI app with multiple models (GPT-3.5 Free / GPT-4 free with 'limited access') AgentGPT: "Autonomous AI agent" Give one prompt and it will run continuously until finished. (GPT 3.5 Free / GPT-4 API access required) sign up for GPT-4 API waitlist here HuggingFace: Largest open source AI community find thousands of different open source projects (Free site) Ora: Access community LLM's or build your own (GPT-3.5 Free / GPT-4 Free) Direct link to free GPT-4 Inflection Pi: A personal AI chatbot (not meant for research purposes) (Free site) ... unsure what model I have seen conflicting information I believe it's GPT-3.5 Nat.dev: Use GPT-4 in playground and compare to other models (GPT-4 $5 credit fee) Merlin: Access GPT-4 chatbot in any browser (GPT-4 limited free plan / GPT-4 unlimited starting at $19 a month) These are all credible chatbots that have been running for months the majority do require email signups however. Hope this helps! **P.S.** If this was helpful and you want to keep ahead in the AI game, consider joining my free daily newsletter! Sent out every weekday at 9 a.m. sharp, it will keep you up-to-date on the ins and outs of generative AI technology, all over your morning cup of ☕️.

AgentGPT: "Autonomous AI agent" Give one prompt and it will run continuously until finished. (GPT 3.5 Free / GPT-4 API access required) sign up for GPT-4 API waitlist here

Very interesting approach. The folks at rift [0] worked on LSP as an integration point for AI coding. But I think they are focusing on other things now.

Do you think the LSP abstraction can support interactions beyond copilot style autocomplete? While that's a super helpful UX, it's also pretty narrow and limited.

My project aider [1] provides a pair-programming UX, which allows complex interactions like coordinating changes across many files. Could LSP servers support more general AI coding like this?

[0] https://github.com/morph-labs/rift

[1] https://github.com/paul-gauthier/aider

My open source tool aider [0] has long offered a "AI pair programming" workflow. Aider's UX is similar but not identical to Copilot Workspaces.

Aider is more of a collaborative chat, where you work with the LLM interactively asking for a sequence of changes to your git repo. The changes can be non-trivial, modifying a group of files in a coordinated way. So much more than just the original copilot "autocomplete".

Workspaces seems more agentic, a bit like Devin. You need to do a bunch of up-front work to (fully) specify the requirements. Then the agent goes off and (hopefully) builds what you want. You need to fully understand what you want to build up front, and you need the describe it unambiguously to the agent. Also, even with a perfect request, agents often go down wrong paths and waste a lot of time and token costs doing the wrong thing.

That's not how I code personally. My process is more iterative, where I explore the problem and solution spaces as I build.

The other difference between aider and Workspaces is that currently aider is a terminal CLI tool. Although I just released a basic browser UI [1] the other day, making it more approachable for folks who are not fully comfortable on the command line.

[0] https://github.com/paul-gauthier/aider

[1] https://aider.chat/2024/05/02/browser.html

Aider was developed by Paul Gaither and focuses on giving developers a pair programming experience directly from developers' terminals. This command-line tool edits code in real-time based on a user prompt in the command terminal. As of writing, it only supports OpenAI’s API but can write, edit, and refine code across multiple languages including Python, JavaScript, and HTML. Developers can use Aider for code generation, debugging, and understanding complex projects.

I built a similar thing in python using Playwright and Pandoc [0]. It's used by aider's `/web ` command that lets you paste a markdown version of any webpage into your AI coding chat. This helps if you want to include docs for an obscure or non-public package/api/etc with the LLM while coding.

I really value dependencies which are easy for all users to install, cross-platform. Playwright is nice because it has a simple way to install its dependencies on most platforms. And the `pypandoc` module provides a seamless install of pandoc across platforms.

The result turns most web pages into nice markdown without requiring users to solve some painful platform specific chromium dependency nightmare.

[0] https://github.com/paul-gauthier/aider/blob/main/aider/scrap...

Thanks for trying aider, and sorry to hear you had trouble getting the hang of it. It might be worth looking through some of the tips on the aider GitHub page [0].

In particular, this is one of the most important tips: Large changes are best performed as a sequence of thoughtful bite sized steps, where you plan out the approach and overall design. Walk GPT through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.

Not sure if this was a factor in your attempts? I'd be happy to help you if you'd like to open an GitHub issue [1] our jump into our discord [2].

[0] https://github.com/paul-gauthier/aider#tips

[1] https://github.com/paul-gauthier/aider/issues/new/choose

[2] https://discord.gg/Tv2uQnR88V

Have you tried something like Agentic’s Glide? (They announced it this week here on HN)

They use gpt, but they might be able to configure it so it uses Claude

Another tool to check out could be aider https://github.com/paul-gauthier/aider

Are you aware of the work on https://github.com/paul-gauthier/aider? What's your take on generating code diffs directly instead of code editing instructions?

He should add AI to his site!

Not really - the site is great as-is and there's nothing wrong with this approach. It looks like it works really well for Mr. 61.

But I'd imagine it'd be pretty helpful to write tools to help with maintaining the site which do leverage LLM models. Do a combination of search + AI to rewrite + reviewing the individual edits (e.g. through selective git adds).

I'm imagining a tool like https://github.com/paul-gauthier/aider (which I haven't tried yet, but it looks useful for this kind of effort).