david1542

Thanks for sharing, I'll check it out!

I actually think there's a very big market for it tbh. A lot of teams building agents are struggling with this today, especially in legal, finance, pharma and government. It's also a much deeper problem than most people realize, even for tool builders, and it really requires working backwards from the experience an agent should have.

Vespper is our take on what that should look like.

Either way, it's exciting to see more people building in this space. Agents definitely need better ways to work with Office docs.

I think it's a valid point. A few reasons we went this way. - The teams we're building for don't want to touch DOCX at all. They just want to plug in their agents and move on, so we went for a smooth hosted experience instead of an open-source lib they'd have to set up and tune themselves. - We run a fine-tuned model under the hood, and it needs a GPU, so running it locally isn't really practical for most folks.

I agree privacy matters a lot. Because of that, we offer zero-data retention for teams, and there's also a self-hosted option if you want everything running in your own cloud.

Yep, a real run with DOCX skill would pay an extra tool call (e.g load_skill). We pre-loaded its context because we wanted to neutralize setup differences between tools and just focus on editing.

Good question. Vespper is meant to replace the python-docx work for your agent and simplify things. That said, it can definitely run alongside your agent (either as additional tools to your agent or as a subagent that uses our tools).

For example, you could keep python-docx for the easy stuff and fall back to a Vespper-based approach when your agent hits errors filling the document. However, the end goal is to completely free your agent from python-docx and low-level work, so it can just focus on what goes into the template.

EigenPal is great! I actually love their product.

Where I think it can break (and we show some of that in the benchmark post, though not on EigenPal specifically) is on tricky document edits, like multi-turn track changes, implicit style understanding (respecting surrounding styles without being told to), advanced list manipulation, etc. We also saw these problems get amplified on long-horizon, challenging document workloads.

Eventually we realized no product out there truly handles the wide variety of cases agents run into, so we set out to build one.

So to answer your question, it depends. If your documents are simple and you're happy with the results, stick with what works. But if you have tricky documents and find yourself chasing the N-th edge case, I think delegating that to something like our product makes sense.

Legit question :) so we've worked on a few ideas since we've been accepted to YC, one of them was the document editor for pharma.

After working on that for a while, we've decided to shift focus and work on the DOCX angle. We felt there's a big opportunity here since .docx is such a widely used format.

As to the feature complete point - I agree. We already cover the most common features today (paragraphs, lists, tables, tracked changes, header/footer) and we're working hard on implementing more. Our main focus right now is to be the most accurate, cheapest and fastest solution out there for common scenarios.

Btw we open sourced a Word add-in project that shows how to build a Word add-in with Vespper MCP: https://github.com/vespperhq/examples/tree/main/word-add-in

Btw we open sourced a Word add-in project that shows how to build a Word add-in with Vespper MCP: https://github.com/vespperhq/examples/tree/main/word-add-in

Looks great! What would you say are the main differentiators compared to SVGator?

Submitted, thanks!

Hey everyone, I worked on a fun weekend project.

I tried to build an OAuth layer that can extract memories from ChatGPT in a scoped way and offer those memories to 3rd party for personalization.

Would love to hear what you think!

Yeh I tend to agree. Real value comes from carefully curating the data and applying smart optimizations, which is something few companies focus on. But I also get the sense that a lot of energy ends up being spent elsewhere - on integration, infrastructure, lots of fragmented OS libraries, etc at the expense of iteration speed and relevance-focused experimentation.

If I understand correctly, the library doesn't index the codebase but just generates a good, formatted representation of the repo. I'm curious to hear what you think about more meaningful way to represent a codebase? There is a lot of tribal knowledge in the repo that can help the LLM.

Hey everyone :)

We had an interesting incident yesterday. I wrote a blog post about it, thought it'd be nice to share it here as well.

Looks awesome! Been using for over a year now and it's a great product :) The new improvements seems exciting.

I'm currently working on Merlinn, an open-source AI agent that helps on-call developers troubleshoot production incidents. https://github.com/merlinn-co/merlinn

Great game! I actually found myself doing an adventure for 10 minutes and it was fun! Few notes:

* As someone said, it'd be cool if you could render what I'm saying and add a loading indicator for the LLM. It'd improve the UX a bit.

* As someone mentioned, you can try to generate images to make the story more "real". This could be fun.

* You can also try to generate more realistic and drammatic sounds, and make the DM sound more theatrical. I'm not sure if that's easy but might be a big improvement. Bonus - maybe it'd be fun to choose a famous voice, like morgan freeman or anthony hopkins.

* It'd be cool if that could save my adventure. Right now, it is restarted everytime I leave the page.

Looks amazing! Definitely gonna have a look.

Definitely VS Code is my favourite. I’ve created so far 3 extensions. I really like the SDK and the way you can control every aspect of the IDE.

Definitely VS Code. I’ve created 3 extensions and I really like it.

Looks nice! How is it different from other well-known projects, like Ory and Logto?

I'm curious about incidental :) how are you going to compete with other, well established IM tools like rootly, incident.io, firehydrant.com?

You have plenty of options. some of them are open source https://signoz.io/ https://coroot.com/

Did you search tools that are cheaper than DD?

Looks good! Love the content

Hey there, thanks for your feedback. We're currently working on allowing people to work with different LLMs (private instances, different providers, etc). It'd probably be released next week :)

About privacy policy, so right now the main way to use the tool is to self-host the open source version. All of the data will stay in your environment. We plan on rolling out our Pro & Enterprise plans in the upcoming weeks/months and to create a more mature privacy policy. I hope that answer your question!

Regarding how it'd benefit support engineers - can you please elaborate a bit? Which areas do you think can be improved? Would love to hear your feedback.