The best Hacker News stories from Show from the past day
Latest posts:
Show HN: A fast, dependency-free traceroute implementation in pure C
Show HN: ekoAcademic – Convert ArXiv papers to interactive podcasts
Show HN: Pipelex – Declarative language for repeatable AI workflows
We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them.<p>Why this instead of yet another workflow builder?<p>- Declarative, not glue code: you state what to do; the runtime figures out how.
- Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand.
- Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node.
- Composable: pipes can call other pipes, created by you or shared in the community.<p>Why a domain-specific language?<p>- We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand
- We need determinism, control, and reproducibility that pure prompts can't deliver
- Bonus: editors, diffs, semantic coloring, easy sharing, search & replace, version control, linters…<p>How we got there:<p>Initially, we just wanted to solve every use-case with LLMs but kept rebuilding the same agentic patterns across different projects. So we challenged ourselves to keep the code generic and separate from use-case specifics, which meant modeling workflows from the relevant knowledge and know-how.<p>Unlike existing code/no-code frameworks for AI workflows, our abstraction layer doesn't wrap APIs, it transcribes business logic into a structured, unambiguous script executable by software and AI. Hence the "declarative" aspect: the script says what should be done, not how to do it. It's like a Dockerfile or SQL for AI workflows.<p>Additionally, we wanted the language to be LLM-friendly. Classic programming languages hide logic and context in variable names, functions, and comments: all invisible to the interpreter. In Pipelex, these elements are explicitly stated in natural language, giving AI full visibility: it's all logic and context, with minimal syntax.<p>Then, we didn't want to write Pipelex scripts ourselves so we dogfooded: we built a Pipelex workflow that writes Pipelex workflows. It's in the MCP and CLI: "pipelex build pipe '…'" runs a multi-step, structured generation flow that produces a validated workflow ready to execute with "pipelex run". Then you can iterate on it yourself or with any coding agent.<p>What’s included: Python library, FastAPI and Docker, MCP server, n8n node, VS Code extension.<p>What we’d like from you<p>1. Build a workflow: did the language work for you or against you?
2. Agent/MCP workflows and n8n node usability.
3. Suggest new kinds of pipes and other AI models we could integrate
4. Looking for OSS contributors to the core library but also to share pipes with the community<p>Known limitations<p>- Connectors: Pipelex doesn’t integrate with “your apps”, we focus on the cognitive steps, and you can integrate through code/API or using MCP or n8n
- Visualization: we need to generate flow-charts
- The pipe builder is still buggy
- Run it yourself: we don’t yet provide a hosted Pipelex API, it’s in the works
- Cost-tracking: we only track LLM costs, not image generation or OCR costs yet
- Caching and reasoning options: not supported yet<p>Links<p>- GitHub: <a href="https://github.com/Pipelex/pipelex" rel="nofollow">https://github.com/Pipelex/pipelex</a>
- Cookbook: <a href="https://github.com/Pipelex/pipelex-cookbook" rel="nofollow">https://github.com/Pipelex/pipelex-cookbook</a>
- Starter: <a href="https://github.com/Pipelex/pipelex-starter" rel="nofollow">https://github.com/Pipelex/pipelex-starter</a>
- VS Code extension: <a href="https://github.com/Pipelex/vscode-pipelex" rel="nofollow">https://github.com/Pipelex/vscode-pipelex</a>
- Docs: [<a href="https://docs.pipelex.com" rel="nofollow">https://docs.pipelex.com</a>](<a href="https://docs.pipelex.com/" rel="nofollow">https://docs.pipelex.com/</a>)
- Demo video (2 min): <a href="https://youtu.be/dBigQa8M8pQ" rel="nofollow">https://youtu.be/dBigQa8M8pQ</a>
- Discord for support and sharing: <a href="https://go.pipelex.com/discord" rel="nofollow">https://go.pipelex.com/discord</a><p>Thanks for reading. If you try Pipelex, tell us exactly where it hurts, that’s the most valuable feedback we can get.
Show HN: Pipelex – Declarative language for repeatable AI workflows
We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them.<p>Why this instead of yet another workflow builder?<p>- Declarative, not glue code: you state what to do; the runtime figures out how.
- Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand.
- Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node.
- Composable: pipes can call other pipes, created by you or shared in the community.<p>Why a domain-specific language?<p>- We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand
- We need determinism, control, and reproducibility that pure prompts can't deliver
- Bonus: editors, diffs, semantic coloring, easy sharing, search & replace, version control, linters…<p>How we got there:<p>Initially, we just wanted to solve every use-case with LLMs but kept rebuilding the same agentic patterns across different projects. So we challenged ourselves to keep the code generic and separate from use-case specifics, which meant modeling workflows from the relevant knowledge and know-how.<p>Unlike existing code/no-code frameworks for AI workflows, our abstraction layer doesn't wrap APIs, it transcribes business logic into a structured, unambiguous script executable by software and AI. Hence the "declarative" aspect: the script says what should be done, not how to do it. It's like a Dockerfile or SQL for AI workflows.<p>Additionally, we wanted the language to be LLM-friendly. Classic programming languages hide logic and context in variable names, functions, and comments: all invisible to the interpreter. In Pipelex, these elements are explicitly stated in natural language, giving AI full visibility: it's all logic and context, with minimal syntax.<p>Then, we didn't want to write Pipelex scripts ourselves so we dogfooded: we built a Pipelex workflow that writes Pipelex workflows. It's in the MCP and CLI: "pipelex build pipe '…'" runs a multi-step, structured generation flow that produces a validated workflow ready to execute with "pipelex run". Then you can iterate on it yourself or with any coding agent.<p>What’s included: Python library, FastAPI and Docker, MCP server, n8n node, VS Code extension.<p>What we’d like from you<p>1. Build a workflow: did the language work for you or against you?
2. Agent/MCP workflows and n8n node usability.
3. Suggest new kinds of pipes and other AI models we could integrate
4. Looking for OSS contributors to the core library but also to share pipes with the community<p>Known limitations<p>- Connectors: Pipelex doesn’t integrate with “your apps”, we focus on the cognitive steps, and you can integrate through code/API or using MCP or n8n
- Visualization: we need to generate flow-charts
- The pipe builder is still buggy
- Run it yourself: we don’t yet provide a hosted Pipelex API, it’s in the works
- Cost-tracking: we only track LLM costs, not image generation or OCR costs yet
- Caching and reasoning options: not supported yet<p>Links<p>- GitHub: <a href="https://github.com/Pipelex/pipelex" rel="nofollow">https://github.com/Pipelex/pipelex</a>
- Cookbook: <a href="https://github.com/Pipelex/pipelex-cookbook" rel="nofollow">https://github.com/Pipelex/pipelex-cookbook</a>
- Starter: <a href="https://github.com/Pipelex/pipelex-starter" rel="nofollow">https://github.com/Pipelex/pipelex-starter</a>
- VS Code extension: <a href="https://github.com/Pipelex/vscode-pipelex" rel="nofollow">https://github.com/Pipelex/vscode-pipelex</a>
- Docs: [<a href="https://docs.pipelex.com" rel="nofollow">https://docs.pipelex.com</a>](<a href="https://docs.pipelex.com/" rel="nofollow">https://docs.pipelex.com/</a>)
- Demo video (2 min): <a href="https://youtu.be/dBigQa8M8pQ" rel="nofollow">https://youtu.be/dBigQa8M8pQ</a>
- Discord for support and sharing: <a href="https://go.pipelex.com/discord" rel="nofollow">https://go.pipelex.com/discord</a><p>Thanks for reading. If you try Pipelex, tell us exactly where it hurts, that’s the most valuable feedback we can get.
Show HN: Pipelex – Declarative language for repeatable AI workflows
We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them.<p>Why this instead of yet another workflow builder?<p>- Declarative, not glue code: you state what to do; the runtime figures out how.
- Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand.
- Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node.
- Composable: pipes can call other pipes, created by you or shared in the community.<p>Why a domain-specific language?<p>- We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand
- We need determinism, control, and reproducibility that pure prompts can't deliver
- Bonus: editors, diffs, semantic coloring, easy sharing, search & replace, version control, linters…<p>How we got there:<p>Initially, we just wanted to solve every use-case with LLMs but kept rebuilding the same agentic patterns across different projects. So we challenged ourselves to keep the code generic and separate from use-case specifics, which meant modeling workflows from the relevant knowledge and know-how.<p>Unlike existing code/no-code frameworks for AI workflows, our abstraction layer doesn't wrap APIs, it transcribes business logic into a structured, unambiguous script executable by software and AI. Hence the "declarative" aspect: the script says what should be done, not how to do it. It's like a Dockerfile or SQL for AI workflows.<p>Additionally, we wanted the language to be LLM-friendly. Classic programming languages hide logic and context in variable names, functions, and comments: all invisible to the interpreter. In Pipelex, these elements are explicitly stated in natural language, giving AI full visibility: it's all logic and context, with minimal syntax.<p>Then, we didn't want to write Pipelex scripts ourselves so we dogfooded: we built a Pipelex workflow that writes Pipelex workflows. It's in the MCP and CLI: "pipelex build pipe '…'" runs a multi-step, structured generation flow that produces a validated workflow ready to execute with "pipelex run". Then you can iterate on it yourself or with any coding agent.<p>What’s included: Python library, FastAPI and Docker, MCP server, n8n node, VS Code extension.<p>What we’d like from you<p>1. Build a workflow: did the language work for you or against you?
2. Agent/MCP workflows and n8n node usability.
3. Suggest new kinds of pipes and other AI models we could integrate
4. Looking for OSS contributors to the core library but also to share pipes with the community<p>Known limitations<p>- Connectors: Pipelex doesn’t integrate with “your apps”, we focus on the cognitive steps, and you can integrate through code/API or using MCP or n8n
- Visualization: we need to generate flow-charts
- The pipe builder is still buggy
- Run it yourself: we don’t yet provide a hosted Pipelex API, it’s in the works
- Cost-tracking: we only track LLM costs, not image generation or OCR costs yet
- Caching and reasoning options: not supported yet<p>Links<p>- GitHub: <a href="https://github.com/Pipelex/pipelex" rel="nofollow">https://github.com/Pipelex/pipelex</a>
- Cookbook: <a href="https://github.com/Pipelex/pipelex-cookbook" rel="nofollow">https://github.com/Pipelex/pipelex-cookbook</a>
- Starter: <a href="https://github.com/Pipelex/pipelex-starter" rel="nofollow">https://github.com/Pipelex/pipelex-starter</a>
- VS Code extension: <a href="https://github.com/Pipelex/vscode-pipelex" rel="nofollow">https://github.com/Pipelex/vscode-pipelex</a>
- Docs: [<a href="https://docs.pipelex.com" rel="nofollow">https://docs.pipelex.com</a>](<a href="https://docs.pipelex.com/" rel="nofollow">https://docs.pipelex.com/</a>)
- Demo video (2 min): <a href="https://youtu.be/dBigQa8M8pQ" rel="nofollow">https://youtu.be/dBigQa8M8pQ</a>
- Discord for support and sharing: <a href="https://go.pipelex.com/discord" rel="nofollow">https://go.pipelex.com/discord</a><p>Thanks for reading. If you try Pipelex, tell us exactly where it hurts, that’s the most valuable feedback we can get.
Show HN: Pipelex – Declarative language for repeatable AI workflows
We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them.<p>Why this instead of yet another workflow builder?<p>- Declarative, not glue code: you state what to do; the runtime figures out how.
- Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand.
- Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node.
- Composable: pipes can call other pipes, created by you or shared in the community.<p>Why a domain-specific language?<p>- We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand
- We need determinism, control, and reproducibility that pure prompts can't deliver
- Bonus: editors, diffs, semantic coloring, easy sharing, search & replace, version control, linters…<p>How we got there:<p>Initially, we just wanted to solve every use-case with LLMs but kept rebuilding the same agentic patterns across different projects. So we challenged ourselves to keep the code generic and separate from use-case specifics, which meant modeling workflows from the relevant knowledge and know-how.<p>Unlike existing code/no-code frameworks for AI workflows, our abstraction layer doesn't wrap APIs, it transcribes business logic into a structured, unambiguous script executable by software and AI. Hence the "declarative" aspect: the script says what should be done, not how to do it. It's like a Dockerfile or SQL for AI workflows.<p>Additionally, we wanted the language to be LLM-friendly. Classic programming languages hide logic and context in variable names, functions, and comments: all invisible to the interpreter. In Pipelex, these elements are explicitly stated in natural language, giving AI full visibility: it's all logic and context, with minimal syntax.<p>Then, we didn't want to write Pipelex scripts ourselves so we dogfooded: we built a Pipelex workflow that writes Pipelex workflows. It's in the MCP and CLI: "pipelex build pipe '…'" runs a multi-step, structured generation flow that produces a validated workflow ready to execute with "pipelex run". Then you can iterate on it yourself or with any coding agent.<p>What’s included: Python library, FastAPI and Docker, MCP server, n8n node, VS Code extension.<p>What we’d like from you<p>1. Build a workflow: did the language work for you or against you?
2. Agent/MCP workflows and n8n node usability.
3. Suggest new kinds of pipes and other AI models we could integrate
4. Looking for OSS contributors to the core library but also to share pipes with the community<p>Known limitations<p>- Connectors: Pipelex doesn’t integrate with “your apps”, we focus on the cognitive steps, and you can integrate through code/API or using MCP or n8n
- Visualization: we need to generate flow-charts
- The pipe builder is still buggy
- Run it yourself: we don’t yet provide a hosted Pipelex API, it’s in the works
- Cost-tracking: we only track LLM costs, not image generation or OCR costs yet
- Caching and reasoning options: not supported yet<p>Links<p>- GitHub: <a href="https://github.com/Pipelex/pipelex" rel="nofollow">https://github.com/Pipelex/pipelex</a>
- Cookbook: <a href="https://github.com/Pipelex/pipelex-cookbook" rel="nofollow">https://github.com/Pipelex/pipelex-cookbook</a>
- Starter: <a href="https://github.com/Pipelex/pipelex-starter" rel="nofollow">https://github.com/Pipelex/pipelex-starter</a>
- VS Code extension: <a href="https://github.com/Pipelex/vscode-pipelex" rel="nofollow">https://github.com/Pipelex/vscode-pipelex</a>
- Docs: [<a href="https://docs.pipelex.com" rel="nofollow">https://docs.pipelex.com</a>](<a href="https://docs.pipelex.com/" rel="nofollow">https://docs.pipelex.com/</a>)
- Demo video (2 min): <a href="https://youtu.be/dBigQa8M8pQ" rel="nofollow">https://youtu.be/dBigQa8M8pQ</a>
- Discord for support and sharing: <a href="https://go.pipelex.com/discord" rel="nofollow">https://go.pipelex.com/discord</a><p>Thanks for reading. If you try Pipelex, tell us exactly where it hurts, that’s the most valuable feedback we can get.
Show HN: Quibbler – A critic for your coding agent that learns what you want
Show HN: Quibbler – A critic for your coding agent that learns what you want
Show HN: Quibbler – A critic for your coding agent that learns what you want
Show HN: Butter – A Behavior Cache for LLMs
Hi HN! I'm Erik. We built Butter, an LLM proxy that makes agent systems deterministic by caching and replaying responses, so automations behave consistently across runs.<p>- It’s a chat completions compatible endpoint, making it easy to drop into existing agents with a custom base_url<p>- The cache is template-aware, meaning lookups can treat dynamic content (names, addresses, etc.) as variables<p>You can see it in action in this demo where it memorizes tic-tac-toe games: <a href="https://www.youtube.com/watch?v=PWbyeZwPjuY" rel="nofollow">https://www.youtube.com/watch?v=PWbyeZwPjuY</a><p>Why we built this: before Butter, we were Pig.dev (YC W25), where we built computer-use agents to automate legacy Windows applications. The goal was to replace RPA. But in practice, these agents were slow, expensive, and unpredictable - a major downgrade from deterministic RPA, and unacceptable in the worlds of healthcare, lending, and government. We realized users don't want to replace RPA with AI, they just want AI to handle the edge cases.<p>We set out to build a system for "muscle memory" for AI automations (general purpose, not just computer-use), where agent trajectories get baked into reusable code. You may recall our first iteration of this in May, a library called Muscle Mem: <a href="https://news.ycombinator.com/item?id=43988381">https://news.ycombinator.com/item?id=43988381</a><p>Today we're relaunching it as a chat completions proxy. It emulates scripted automations by storing observed message histories in a tree structure, where each fork in the tree represents some conditional branch in the workflow's "code". We replay behaviors by walking the agent down the tree, falling back to AI to add new branches if the next step is not yet known.<p>The proxy is live and free to use while we work through making the template-aware engine more flexible and accurate. Please try it out and share how it went, where it breaks, and if it’s helpful.
Show HN: Run a GitHub Actions step in a gVisor sandbox
Show HN: Run a GitHub Actions step in a gVisor sandbox
Show HN: Run a GitHub Actions step in a gVisor sandbox
Show HN: Meals You Love – AI-powered meal planning and grocery shopping
Meals You Love is a meal planning app that creates weekly meal plans tailored to your tastes and dietary preferences. It integrates with Kroger and Instacart's APIs so you can add your meal plan groceries directly to your cart. You can also import your own recipes to include alongside AI suggestions.<p>I originally built this to help my wife with meal planning and grocery shopping. We were always struggling to decide what to make and inevitably forgot ingredients. Most meal planners felt too rigid or generic, and few handled the grocery side well (or at all). We've also used meal kits like Home Chef in the past but they end up being quite expensive and produce a comical amount of packaging waste, plus you still wind up needing to purchase groceries anyway. In all honesty, I also wanted an excuse to try building something "real" using AI and to see if it could be used in an actually useful manner.<p>Would love feedback from anyone interested in food, meal planning, or product design!<p>Tech stack:<p>- Cloud Run<p>- Firestore<p>- Vertex AI / Gemini<p><a href="https://mealsyoulove.com" rel="nofollow">https://mealsyoulove.com</a>
Show HN: Meals You Love – AI-powered meal planning and grocery shopping
Meals You Love is a meal planning app that creates weekly meal plans tailored to your tastes and dietary preferences. It integrates with Kroger and Instacart's APIs so you can add your meal plan groceries directly to your cart. You can also import your own recipes to include alongside AI suggestions.<p>I originally built this to help my wife with meal planning and grocery shopping. We were always struggling to decide what to make and inevitably forgot ingredients. Most meal planners felt too rigid or generic, and few handled the grocery side well (or at all). We've also used meal kits like Home Chef in the past but they end up being quite expensive and produce a comical amount of packaging waste, plus you still wind up needing to purchase groceries anyway. In all honesty, I also wanted an excuse to try building something "real" using AI and to see if it could be used in an actually useful manner.<p>Would love feedback from anyone interested in food, meal planning, or product design!<p>Tech stack:<p>- Cloud Run<p>- Firestore<p>- Vertex AI / Gemini<p><a href="https://mealsyoulove.com" rel="nofollow">https://mealsyoulove.com</a>
Show HN: I made a heatmap diff viewer for code reviews
0github.com is a pull request viewer that color-codes every diff line/token by how much human attention it probably needs. Unlike PR-review bots, we try to flag not just by "is it a bug?" but by "is it worth a second look?" (examples: hard-coded secret, weird crypto mode, gnarly logic, ugly code).<p>To try it, replace github.com with 0github.com in any pull-request URL. Under the hood, we split the PR into individual files, and for each file, we ask an LLM to annotate each line with a data structure that we parse into a colored heatmap.<p>Examples:<p><a href="https://0github.com/manaflow-ai/cmux/pull/666" rel="nofollow">https://0github.com/manaflow-ai/cmux/pull/666</a><p><a href="https://0github.com/stack-auth/stack-auth/pull/988" rel="nofollow">https://0github.com/stack-auth/stack-auth/pull/988</a><p><a href="https://0github.com/tinygrad/tinygrad/pull/12995" rel="nofollow">https://0github.com/tinygrad/tinygrad/pull/12995</a><p><a href="https://0github.com/simonw/datasette/pull/2548" rel="nofollow">https://0github.com/simonw/datasette/pull/2548</a><p>Notice how all the example links have a 0 prepended before github.com. This navigates you to our custom diff viewer where we handle the same URL path parameters as github.com. Darker yellows indicate that an area might require more investigation. Hover on the highlights to see the LLM's explanation. There's also a slider on the top left to adjust the "should review" threshold.<p>Repo (MIT license): <a href="https://github.com/manaflow-ai/cmux" rel="nofollow">https://github.com/manaflow-ai/cmux</a>
Show HN: I made a heatmap diff viewer for code reviews
0github.com is a pull request viewer that color-codes every diff line/token by how much human attention it probably needs. Unlike PR-review bots, we try to flag not just by "is it a bug?" but by "is it worth a second look?" (examples: hard-coded secret, weird crypto mode, gnarly logic, ugly code).<p>To try it, replace github.com with 0github.com in any pull-request URL. Under the hood, we split the PR into individual files, and for each file, we ask an LLM to annotate each line with a data structure that we parse into a colored heatmap.<p>Examples:<p><a href="https://0github.com/manaflow-ai/cmux/pull/666" rel="nofollow">https://0github.com/manaflow-ai/cmux/pull/666</a><p><a href="https://0github.com/stack-auth/stack-auth/pull/988" rel="nofollow">https://0github.com/stack-auth/stack-auth/pull/988</a><p><a href="https://0github.com/tinygrad/tinygrad/pull/12995" rel="nofollow">https://0github.com/tinygrad/tinygrad/pull/12995</a><p><a href="https://0github.com/simonw/datasette/pull/2548" rel="nofollow">https://0github.com/simonw/datasette/pull/2548</a><p>Notice how all the example links have a 0 prepended before github.com. This navigates you to our custom diff viewer where we handle the same URL path parameters as github.com. Darker yellows indicate that an area might require more investigation. Hover on the highlights to see the LLM's explanation. There's also a slider on the top left to adjust the "should review" threshold.<p>Repo (MIT license): <a href="https://github.com/manaflow-ai/cmux" rel="nofollow">https://github.com/manaflow-ai/cmux</a>
Show HN: I made a heatmap diff viewer for code reviews
0github.com is a pull request viewer that color-codes every diff line/token by how much human attention it probably needs. Unlike PR-review bots, we try to flag not just by "is it a bug?" but by "is it worth a second look?" (examples: hard-coded secret, weird crypto mode, gnarly logic, ugly code).<p>To try it, replace github.com with 0github.com in any pull-request URL. Under the hood, we split the PR into individual files, and for each file, we ask an LLM to annotate each line with a data structure that we parse into a colored heatmap.<p>Examples:<p><a href="https://0github.com/manaflow-ai/cmux/pull/666" rel="nofollow">https://0github.com/manaflow-ai/cmux/pull/666</a><p><a href="https://0github.com/stack-auth/stack-auth/pull/988" rel="nofollow">https://0github.com/stack-auth/stack-auth/pull/988</a><p><a href="https://0github.com/tinygrad/tinygrad/pull/12995" rel="nofollow">https://0github.com/tinygrad/tinygrad/pull/12995</a><p><a href="https://0github.com/simonw/datasette/pull/2548" rel="nofollow">https://0github.com/simonw/datasette/pull/2548</a><p>Notice how all the example links have a 0 prepended before github.com. This navigates you to our custom diff viewer where we handle the same URL path parameters as github.com. Darker yellows indicate that an area might require more investigation. Hover on the highlights to see the LLM's explanation. There's also a slider on the top left to adjust the "should review" threshold.<p>Repo (MIT license): <a href="https://github.com/manaflow-ai/cmux" rel="nofollow">https://github.com/manaflow-ai/cmux</a>
Show HN: In a single HTML file, an app to encourage my children to invest
Show HN: In a single HTML file, an app to encourage my children to invest