The best Hacker News stories from Show from the past day

from

All Show

from the past*

day week month

with these search terms:

Create follow Go back

Latest posts:

Show HN: Audiocube – A 3D DAW for Spatial Audio

I’ve recently released my solo project Audiocube<p>I wanted to make a 3D DAW, where spatial audio, physics, and virtual acoustics are all directly integrated into the engine.<p>This makes it easy to create music in 3D, and experiment with new techniques which aren’t possible in traditional DAWs and plugins.<p>I’d love to get any feedback on this software (Mac/Windows) to make it better.<p>You can download it for free through the website.<p>Thanks, Noah

Show HN: Audiocube – A 3D DAW for Spatial Audio

I’ve recently released my solo project Audiocube<p>I wanted to make a 3D DAW, where spatial audio, physics, and virtual acoustics are all directly integrated into the engine.<p>This makes it easy to create music in 3D, and experiment with new techniques which aren’t possible in traditional DAWs and plugins.<p>I’d love to get any feedback on this software (Mac/Windows) to make it better.<p>You can download it for free through the website.<p>Thanks, Noah

Show HN: Audiocube – A 3D DAW for Spatial Audio

I’ve recently released my solo project Audiocube<p>I wanted to make a 3D DAW, where spatial audio, physics, and virtual acoustics are all directly integrated into the engine.<p>This makes it easy to create music in 3D, and experiment with new techniques which aren’t possible in traditional DAWs and plugins.<p>I’d love to get any feedback on this software (Mac/Windows) to make it better.<p>You can download it for free through the website.<p>Thanks, Noah

Show HN: Mcp-Agent – Build effective agents with Model Context Protocol

Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](<a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a>) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions.<p>For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and prompts.<p>mcp-agent provides a higher level interface to build apps with MCP. It handles the connection management of MCP servers so you don’t have to. It also implements the Building Effective Agents patterns: - Augmented LLM (an LLM with access to one or more MCP servers) - Router, Orchestrator-Worker, Evaluator-Optimizer, and more - Swarm<p>The key design principles are composability and reusability – every pattern is an AugmentedLLM itself, so you can chain them into more complex workflows.<p>Some background: I worked on LSP [5] and language servers at Microsoft, and saw firsthand how standards and protocols can revolutionize developer workflows. Before LSP every IDE had its own esoteric ways of providing language services. LSP changed all that, and arguably made every language server better, since they can focus on improving a single implementation for all clients.<p>I think AI development is in a similar pre-LSP space right now. There are tons of frameworks [6], every model provider has its own way of handling messages, tool calls, streaming, etc. I really think we need a protocol to standardize these patterns.<p>Pretty soon every service is going to expose an MCP interface, and mcp-agent is about letting developers orchestrate these services into applications (i.e. build “MCP apps”). This can cover any use of an AI model that needs to interact with the world around it: - RAG pipelines and Q&A chatbots - Process automation via AI workflows/async tasks - Multi-agent orchestration, with human in the loop<p>The repo contains examples [7] to build RAG agents, streamlit apps and more. There’s a lot left to build, like streaming support, server auth and tighter integration with MCP clients.<p>But I wanted to share early in the hopes that you can guide me: - If you find this useful, please let me know. If it’s useful to you, I will dedicate all my time to improving it. - I really welcome contributions. If you want to collaborate, please reach out on github to help take this forward.<p>I want to help standardize AI development, so developers a few years from now can look back with horror at the pre-MCP days.<p>[1] - <a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a><p>[2] - <a href="https://modelcontextprotocol.io/introduction" rel="nofollow">https://modelcontextprotocol.io/introduction</a><p>[3] - <a href="https://www.anthropic.com/research/building-effective-agents" rel="nofollow">https://www.anthropic.com/research/building-effective-agents</a><p>[4] - <a href="https://github.com/openai/swarm">https://github.com/openai/swarm</a><p>[5] - <a href="https://microsoft.github.io/language-server-protocol/" rel="nofollow">https://microsoft.github.io/language-server-protocol/</a><p>[6] - <a href="https://xkcd.com/927/" rel="nofollow">https://xkcd.com/927/</a> (I understand the irony)<p>[7] - <a href="https://github.com/lastmile-ai/mcp-agent/tree/main/examples">https://github.com/lastmile-ai/mcp-agent/tree/main/examples</a>

Show HN: Mcp-Agent – Build effective agents with Model Context Protocol

Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](<a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a>) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions.<p>For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and prompts.<p>mcp-agent provides a higher level interface to build apps with MCP. It handles the connection management of MCP servers so you don’t have to. It also implements the Building Effective Agents patterns: - Augmented LLM (an LLM with access to one or more MCP servers) - Router, Orchestrator-Worker, Evaluator-Optimizer, and more - Swarm<p>The key design principles are composability and reusability – every pattern is an AugmentedLLM itself, so you can chain them into more complex workflows.<p>Some background: I worked on LSP [5] and language servers at Microsoft, and saw firsthand how standards and protocols can revolutionize developer workflows. Before LSP every IDE had its own esoteric ways of providing language services. LSP changed all that, and arguably made every language server better, since they can focus on improving a single implementation for all clients.<p>I think AI development is in a similar pre-LSP space right now. There are tons of frameworks [6], every model provider has its own way of handling messages, tool calls, streaming, etc. I really think we need a protocol to standardize these patterns.<p>Pretty soon every service is going to expose an MCP interface, and mcp-agent is about letting developers orchestrate these services into applications (i.e. build “MCP apps”). This can cover any use of an AI model that needs to interact with the world around it: - RAG pipelines and Q&A chatbots - Process automation via AI workflows/async tasks - Multi-agent orchestration, with human in the loop<p>The repo contains examples [7] to build RAG agents, streamlit apps and more. There’s a lot left to build, like streaming support, server auth and tighter integration with MCP clients.<p>But I wanted to share early in the hopes that you can guide me: - If you find this useful, please let me know. If it’s useful to you, I will dedicate all my time to improving it. - I really welcome contributions. If you want to collaborate, please reach out on github to help take this forward.<p>I want to help standardize AI development, so developers a few years from now can look back with horror at the pre-MCP days.<p>[1] - <a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a><p>[2] - <a href="https://modelcontextprotocol.io/introduction" rel="nofollow">https://modelcontextprotocol.io/introduction</a><p>[3] - <a href="https://www.anthropic.com/research/building-effective-agents" rel="nofollow">https://www.anthropic.com/research/building-effective-agents</a><p>[4] - <a href="https://github.com/openai/swarm">https://github.com/openai/swarm</a><p>[5] - <a href="https://microsoft.github.io/language-server-protocol/" rel="nofollow">https://microsoft.github.io/language-server-protocol/</a><p>[6] - <a href="https://xkcd.com/927/" rel="nofollow">https://xkcd.com/927/</a> (I understand the irony)<p>[7] - <a href="https://github.com/lastmile-ai/mcp-agent/tree/main/examples">https://github.com/lastmile-ai/mcp-agent/tree/main/examples</a>

Show HN: Mcp-Agent – Build effective agents with Model Context Protocol

Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](<a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a>) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions.<p>For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and prompts.<p>mcp-agent provides a higher level interface to build apps with MCP. It handles the connection management of MCP servers so you don’t have to. It also implements the Building Effective Agents patterns: - Augmented LLM (an LLM with access to one or more MCP servers) - Router, Orchestrator-Worker, Evaluator-Optimizer, and more - Swarm<p>The key design principles are composability and reusability – every pattern is an AugmentedLLM itself, so you can chain them into more complex workflows.<p>Some background: I worked on LSP [5] and language servers at Microsoft, and saw firsthand how standards and protocols can revolutionize developer workflows. Before LSP every IDE had its own esoteric ways of providing language services. LSP changed all that, and arguably made every language server better, since they can focus on improving a single implementation for all clients.<p>I think AI development is in a similar pre-LSP space right now. There are tons of frameworks [6], every model provider has its own way of handling messages, tool calls, streaming, etc. I really think we need a protocol to standardize these patterns.<p>Pretty soon every service is going to expose an MCP interface, and mcp-agent is about letting developers orchestrate these services into applications (i.e. build “MCP apps”). This can cover any use of an AI model that needs to interact with the world around it: - RAG pipelines and Q&A chatbots - Process automation via AI workflows/async tasks - Multi-agent orchestration, with human in the loop<p>The repo contains examples [7] to build RAG agents, streamlit apps and more. There’s a lot left to build, like streaming support, server auth and tighter integration with MCP clients.<p>But I wanted to share early in the hopes that you can guide me: - If you find this useful, please let me know. If it’s useful to you, I will dedicate all my time to improving it. - I really welcome contributions. If you want to collaborate, please reach out on github to help take this forward.<p>I want to help standardize AI development, so developers a few years from now can look back with horror at the pre-MCP days.<p>[1] - <a href="https://github.com/lastmile-ai/mcp-agent">https://github.com/lastmile-ai/mcp-agent</a><p>[2] - <a href="https://modelcontextprotocol.io/introduction" rel="nofollow">https://modelcontextprotocol.io/introduction</a><p>[3] - <a href="https://www.anthropic.com/research/building-effective-agents" rel="nofollow">https://www.anthropic.com/research/building-effective-agents</a><p>[4] - <a href="https://github.com/openai/swarm">https://github.com/openai/swarm</a><p>[5] - <a href="https://microsoft.github.io/language-server-protocol/" rel="nofollow">https://microsoft.github.io/language-server-protocol/</a><p>[6] - <a href="https://xkcd.com/927/" rel="nofollow">https://xkcd.com/927/</a> (I understand the irony)<p>[7] - <a href="https://github.com/lastmile-ai/mcp-agent/tree/main/examples">https://github.com/lastmile-ai/mcp-agent/tree/main/examples</a>

Show HN: Design/build of some parametric speaker cabinets with OpenSCAD

Show HN: Design/build of some parametric speaker cabinets with OpenSCAD

Show HN: Open-Source Alternative to OpenAI Platform, for Local Models

Hi everyone, we’re a small team, supported by Mozilla, who are working on re-imagining a UI for training, tuning and testing local LLMs. Everything is open source. If you’ve been training your own LLMs or have always wanted to, we’d love for you to play with the tool and give feedback on what the future development experience for LLM engineering could look like.

Show HN: Open-Source Alternative to OpenAI Platform, for Local Models

Hi everyone, we’re a small team, supported by Mozilla, who are working on re-imagining a UI for training, tuning and testing local LLMs. Everything is open source. If you’ve been training your own LLMs or have always wanted to, we’d love for you to play with the tool and give feedback on what the future development experience for LLM engineering could look like.

Show HN: Browse Anime from the Terminal

Show HN: Meelo, self-hosted music server for collectors and music maniacs

I've been working on this alternative for Plex for almost 3 years now. It's main selling point is that it correctly handles multiple versions of albums and songs. As of today, it only has a web client.<p>It tries to be as flexible as possible, but still requires a bit of configuration (including regexes, but if metadata is embedded into the files, it can be skipped).<p>I just released v3.0, making videos first-class data, and scanning + metadata matching faster.

Show HN: Meelo, self-hosted music server for collectors and music maniacs

I've been working on this alternative for Plex for almost 3 years now. It's main selling point is that it correctly handles multiple versions of albums and songs. As of today, it only has a web client.<p>It tries to be as flexible as possible, but still requires a bit of configuration (including regexes, but if metadata is embedded into the files, it can be skipped).<p>I just released v3.0, making videos first-class data, and scanning + metadata matching faster.

Show HN: Meelo, self-hosted music server for collectors and music maniacs

I've been working on this alternative for Plex for almost 3 years now. It's main selling point is that it correctly handles multiple versions of albums and songs. As of today, it only has a web client.<p>It tries to be as flexible as possible, but still requires a bit of configuration (including regexes, but if metadata is embedded into the files, it can be skipped).<p>I just released v3.0, making videos first-class data, and scanning + metadata matching faster.

Show HN: DeepSeek Your HN Profile

A fun project that I built to try out R1 Distill Llama 70B. Enjoy :)

Show HN: Orange intelligence, an open source alternative to Apple Intelligence

Hi HN! I’m excited to share Orange Intelligence, an open-source alternative to Apple Intelligence for macOS.<p>Orange Intelligence allows you to interact with any text on your macOS system in a more powerful and customizable way. It brings a floating text processor that integrates seamlessly with your workflow. Whether you’re a developer, writer, or productivity enthusiast, this tool can boost your efficiency. Key Features:<p><pre><code> Floating Text Processor: Trigger a floating window by double-tapping the Option key to process selected text. Run Any Python Function: From basic text manipulations to running large language models (LLM) like OpenAI or local LLaMA, you can execute any Python function on the fly. Full Customization: Want to add your own functions or logic? Just write them in Python, and they’ll appear in the floating window. </code></pre> How does it work?<p><pre><code> Capture: Uses AppleScript to simulate a global Cmd+C and capture selected text from any active macOS app. Process: A floating window pops up, letting you choose what to do with the text (run a function, format it, or apply an LLM). Replace: After processing, the app returns focus to the original application and pastes the processed text back with a global Cmd+V. </code></pre> Why open source?<p>I built this to overcome the limitations of Apple’s proprietary tools, and I wanted to make it fully customizable and extendable. Orange Intelligence is built with Python and PyQt6, so it’s easy to adapt, extend, and contribute to.<p>It’s not just a text processor—it’s a platform for building custom workflows, whether you want to automate simple tasks or integrate with complex AI systems.<p>If you’re on macOS and you’re interested in boosting your productivity with Python and AI, I’d love for you to try it out and give feedback: <a href="https://github.com/sharingan-no-kakashi/orange-intelligence">https://github.com/sharingan-no-kakashi/orange-intelligence</a>.<p>I’m looking forward to your thoughts, ideas, and contributions. Thanks!

Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs

ErisForge is a Python library designed to modify Large Language Models (LLMs) by applying transformations to their internal layers. Named after Eris, the goddess of strife and discord, ErisForge allows you to alter model behavior in a controlled manner, creating both ablated and augmented versions of LLMs that respond differently to specific types of input.<p>It is also quite useful to perform studies on propaganda and bias in LLMs (planning to experiment with deepseek).<p>Features - Modify internal layers of LLMs to produce altered behaviors. - Ablate or enhance model responses with the AblationDecoderLayer and AdditionDecoderLayer classes. - Measure refusal expressions in model responses using the ExpressionRefusalScorer. - Supports custom behavior directions for applying specific types of transformations.

Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs

ErisForge is a Python library designed to modify Large Language Models (LLMs) by applying transformations to their internal layers. Named after Eris, the goddess of strife and discord, ErisForge allows you to alter model behavior in a controlled manner, creating both ablated and augmented versions of LLMs that respond differently to specific types of input.<p>It is also quite useful to perform studies on propaganda and bias in LLMs (planning to experiment with deepseek).<p>Features - Modify internal layers of LLMs to produce altered behaviors. - Ablate or enhance model responses with the AblationDecoderLayer and AdditionDecoderLayer classes. - Measure refusal expressions in model responses using the ExpressionRefusalScorer. - Supports custom behavior directions for applying specific types of transformations.

Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs

ErisForge is a Python library designed to modify Large Language Models (LLMs) by applying transformations to their internal layers. Named after Eris, the goddess of strife and discord, ErisForge allows you to alter model behavior in a controlled manner, creating both ablated and augmented versions of LLMs that respond differently to specific types of input.<p>It is also quite useful to perform studies on propaganda and bias in LLMs (planning to experiment with deepseek).<p>Features - Modify internal layers of LLMs to produce altered behaviors. - Ablate or enhance model responses with the AblationDecoderLayer and AdditionDecoderLayer classes. - Measure refusal expressions in model responses using the ExpressionRefusalScorer. - Supports custom behavior directions for applying specific types of transformations.

Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs

ErisForge is a Python library designed to modify Large Language Models (LLMs) by applying transformations to their internal layers. Named after Eris, the goddess of strife and discord, ErisForge allows you to alter model behavior in a controlled manner, creating both ablated and augmented versions of LLMs that respond differently to specific types of input.<p>It is also quite useful to perform studies on propaganda and bias in LLMs (planning to experiment with deepseek).<p>Features - Modify internal layers of LLMs to produce altered behaviors. - Ablate or enhance model responses with the AblationDecoderLayer and AdditionDecoderLayer classes. - Measure refusal expressions in model responses using the ExpressionRefusalScorer. - Supports custom behavior directions for applying specific types of transformations.