A bitwise reproducible deep learning framework
Hacker News (score: 20)Description
More from Hacker
Show HN: Tascli, a command line based (human) task and record manager
Show HN: Tascli, a command line based (human) task and record manager `cargo install tascli`<p>Manages your own task and records in the terminal simply with tascli - tiny, fast and simple.
Fast trigram based code search
Fast trigram based code search
Langjam Gamejam: Build a programming language then make a game with it
Langjam Gamejam: Build a programming language then make a game with it
Show HN: Runprompt – run .prompt files from the command line
Show HN: Runprompt – run .prompt files from the command line I built a single-file Python script that lets you run LLM prompts from the command line with templating, structured outputs, and the ability to chain prompts together.<p>When I discovered Google's Dotprompt format (frontmatter + Handlebars templates), I realized it was perfect for something I'd been wanting: treating prompts as first-class programs you can pipe together Unix-style. Google uses Dotprompt in Firebase Genkit and I wanted something simpler - just run a .prompt file directly on the command line.<p>Here's what it looks like:<p>--- model: anthropic/claude-sonnet-4-20250514 output: format: json schema: sentiment: string, positive/negative/neutral confidence: number, 0-1 score --- Analyze the sentiment of: {{STDIN}}<p>Running it:<p>cat reviews.txt | ./runprompt sentiment.prompt | jq '.sentiment'<p>The things I think are interesting:<p>* Structured output schemas: Define JSON schemas in the frontmatter using a simple `field: type, description` syntax. The LLM reliably returns valid JSON you can pipe to other tools.<p>* Prompt chaining: Pipe JSON output from one prompt as template variables into the next. This makes it easy to build multi-step agentic workflows as simple shell pipelines.<p>* Zero dependencies: It's a single Python file that uses only stdlib. Just curl it down and run it.<p>* Provider agnostic: Works with Anthropic, OpenAI, Google AI, and OpenRouter (which gives you access to dozens of models through one API key).<p>You can use it to automate things like extracting structured data from unstructured text, generating reports from logs, and building small agentic workflows without spinning up a whole framework.<p>Would love your feedback, and PRs are most welcome!
No other tools from this source yet.