brockmeier

Show HN: Notion Breadcrumb Navigator – Keyboard-driven page hierarchy navigation

Posted by brockmeier on Tuesday February 24, 2026 @07:04AM
from the show-hn dept.

https://github.com/felixbrock/notion-breadcrumbs

I built a small browser extension that adds a command palette to Notion for navigating through your page hierarchy. Press Ctrl+B to open an overlay showing parent pages, headings on the current page, and subpages. Arrow keys to navigate, type to filter, Enter to jump.It stays open across page switches so you can move through deeply nested pages without touching the mouse. Works in any Chromium...

( Read More... | no comments | 2 points | on HN )

Re:Show HN: VoxPaste – Fast voice-to-text CLI for dictating to Claude/... on Friday February 06, 2026 @06:33AM (#46911644)

Also, the new Mistral model is unbelievably fast:

https://simonwillison.net/2026/Feb/4/voxtral-2/

And the costs of usage are very low. For instance, with voxtral-mini-latest, you you can dictate for 5.5 hours and only have to pay $1:

https://mistral.ai/pricing#api

Re:Show HN: VoxPaste – Fast voice-to-text CLI for dictating to Claude/... on Friday February 06, 2026 @06:10AM (#46911464)

Just added openrouter support as well.

Show HN: VoxPaste – Fast voice-to-text CLI for dictating to Claude/Cursor

Posted by brockmeier on Thursday February 05, 2026 @01:15PM
from the show-hn dept.

https://github.com/felixbrock/voxpaste

Built this because typing long prompts to Claude Code got tedious. VoxPaste records audio and transcribes via your choice of provider—Mistral, Groq, OpenAI, or Deepgram—then copies directly to clipboard.Unlike single-provider tools, you can pick the fastest option for your needs. Mistral and Groq deliver fastest. Bind it to a hotkey and invoke from anywhere.Audio goes directly to your chosen...

( Read More... | 2 comments | on HN )

Data manipulation using natural language prompts

Posted by brockmeier on Tuesday June 10, 2025 @09:52AM
from the self-post dept.

I've got a dataset of ~100K input-output pairs that I want to use for fine-tuning Llama. Unfortunately it's not the cleanest dataset so I'm having to spend some time tidying it up. For example, I only want records in English, and I also only want to include records where the input has foul language (as that's what I need for my use-case). There's loads more checks like these that I want to run,...

( Read More... | 5 comments | 4 points | on HN )

Show HN: Grammarly for Prompts Built with Go, Htmx, Templ

Posted by brockmeier on Wednesday December 20, 2023 @01:59PM
from the show-hn dept.

https://lemonai.onrender.com/

Hey HN, I recently built a plan-validate-solve agent and struggled to write high-quality prompts so I decided to build a Grammarly for prompts. I used Go, HTMX, a-h/templ, Tailwind as well as the new OpenAI assistants - wanted to share a few learnings with you here:- The overall “weight” of the solution. Basically, no external dependencies needed. I haven’t even touched web frameworks like Gin...

( Read More... | no comments | 2 points | on HN )

Re:Show HN: Agentflow – Run Complex LLM Workflows from Simple JSON on Wednesday August 09, 2023 @08:32AM (#37061678)

This is really cool! I’m doing something similar with Lemon Agent (https://github.com/felixbrock/lemon-agent). What I find most powerful about defining workflows in a json file is that you can add additional fields to let the LLM know about specific execution requirements, like asking the user for permission before executing a specific workflow step. This allows for infinite configuration options. Curious to hear if you already experimented with something like this or if you are planning to include something similar?

Re:Show HN: Lemon Agent – Plan and Solve agent for workflow automation on Wednesday August 02, 2023 @04:32PM (#36976952)

I think Zapier's NLA solution goes in a similar direction and as far as I know, they are running their model on the server side to adjust workflow input and output of workflows to the unique needs of an LLM model. They are doing an amazing job there and I am also currently working on improving this (e.g. adjusting to a model's token limit).

Besides that, Lemon Agent focuses on providing an out-of-the-box agent that is great at solving tasks with workflow automation. If you want to use Zapier NLA you have to rely on generalistic agents like LangChain's ReAct Agent or the Plan and Execution Agent or you have to build your own agent. In any case, you have to twist the agent a lot to reach a certain degree of accuracy and reliability.

Show HN: Lemon Agent – Plan and Solve agent for workflow automation

Posted by brockmeier on Tuesday August 01, 2023 @06:17PM
from the show-hn dept.

https://github.com/felixbrock/lemon-agent

I built this Plan and Solve (PS) agent because I struggled to build stable sequential tasks with LangChain and GPT3.5 turbo. After many failed attempts with LangChain's PS agent, I decided to build my own.I built the agent in a way that it acts as a workflow automation co-pilot rather than trying to play AGI. For example, the user has to tell the Lemon Agent which task needs to be solved and...

( Read More... | 2 comments | on HN )

Re:Show HN: Lemon AI – open-source Zapier NLA to empower agents on Friday July 07, 2023 @10:35AM (#36632360)

Thanks a lot for sharing this, we really like gorilla! This is definitely on our roadmap.

Re:Show HN: Lemon AI – open-source Zapier NLA to empower agents on Wednesday July 05, 2023 @03:32PM (#36605877)

I think it’s best to view this separately. Langchain provides its own agent type (next to the commonly used ReAct agent) to interact with OpenAI functions. Lemon AI functions are standalone fallback mechanisms that will be used by the model in specific situations where near-deterministic model behavior is especially important, a bit similar to the functions offered by OpenAI just suitable for open source models. You can combine Lemon functions with any Langchain agent type. Hope this helps!

Re:Show HN: Lemon AI – open-source Zapier NLA to empower agents on Wednesday July 05, 2023 @11:01AM (#36601388)

Foundry is doing a nice job bringing functions in LLM apps to life. That's something I am also working on with Lemon AI functions. Besides that, to me it seems that it’s focused on read operations for web-based services. What I’m building is focused on allowing for read and write operations, both for internal tooling and web services to allow agents to take actions based on instructions. I’m essentially focussing on helping Langchain users to establish end-to-end workflow automation as quickly as possible. Going forward permission workflows will be covered as well so assistants can be team / user specific, something that I believe isn’t solved well by Zapier NLA right now.

Show HN: Lemon AI – open-source Zapier NLA to empower agents

Posted by brockmeier on Wednesday July 05, 2023 @10:29AM
from the show-hn dept.

https://github.com/felixbrock/lemonai-py-client

Hi HN, excited to share this open source Zapier NLA alternative I’ve been working on.A few weeks ago I found myself struggling to automate a relatively straightforward internal workflow using an open source LLM (update Hubspot based on Airtable entry and personal information coming from web sources, and send out a summary via Slack). There was no way to interact with these tools in a robust way...

( Read More... | 7 comments | 4 points | on HN )