Alternatives
Products that do what Pairing LLM code generation with traditional templates does
Hi, I’ve been exploring Claude 3.5 code generation abilities for a while and it looks like it can generate more consistent code than other models. However it would still be unmaintainable if you ask it to write a lot of code and it still sucks at system design. So, I’ve been playing around the idea of using the code repository with a template for directory layout and infrastructure, then adding the repository information to Claude and asking it to generate code. It seems that it works, if I pass the structure of some OpenAPI based backend it can update the API definition and implementation…
- 1
- 2
- 3IB
Hey everyone, recently I've been theorizing how claude code's agentic capabilities and overall structure can be extended to image generation. And so, I created this concept where an image is generated, and an agentic evaluation loop identifies what's wrong with the image and fixes it.
2025 · agent.trybezel.com
- 4AP
As a former CIO who managed teams working with millions of lines of legacy code (Visual Basic, Sybase, Oracle Forms, and worse), I feel the pain of maintaining and onboarding developers to legacy systems. Believing that LLM-enabled tools can play a role in solving this, I've built a tool that automatically generates documentation for legacy codebases using the Model Context Protocol (MCP) & Claude Sonnet. At first glance, I think this approach has merit. Some samples are in the README. I welcome your thoughts. The Problem: - Legacy codebases are notoriously difficult to understand and…
2025 · github.com
- 5UA
I've been using LLMs for long discovery and research chats (papers, repos, best practices), then distilling that into phased markdown (build plan + tests), then handing those phases to Codex/Claude to implement and test phase by phase. The annoying part was always the distillation and keeping docs and architecture current, so I built Unpack: a lightweight GitHub template plus docs structure and a few commands that turns conversations into phases/specs and keeps project docs up to date as the agent builds. It can also generate Mintlify-friendly end-user docs. There are other…
Feb 2026 · github.com
- 6PM
This is my attempt in building a memory that evolves and persist for claude code. My approach is inspired from Zettelkasten method, memories are atomic, connected and dynamic. Existing memories can evolve based on newer memories. In the background it uses LLM to handle linking and evolution. I have only used it with claude code so far, it works well with me but still early stage, so rough edges likely. I'm planning to extend it to other coding agents as I use several different agents during development. Looking for feedbacks!
Jan 2026 · github.com
- 7LT
Firstly, I’m not a developer — but I am a very technical, over-50, product person and entrepreneur. This project started shortly after Claude Code launched. I had already worked on a few other AI coding projects, and decided to see how far I could realistically take something end-to-end. While I had some help from a developer, I increasingly felt capable of taking on more work myself. So about 9 months in the making, working full time on it past 2 months. Stack: Postgres, Next.js on Render. Monorepo with both frontend and backend services. Some takeaways from using Claude Code on this…
Dec 2025 · jetogo.com
- 8GC
I have been using a Spec-Driven Development approach for all mid+ size coding tasks since Feb 2026: https://news.ycombinator.com/item?id=48231575. One of the reasons for developing my own plugin (sddw - spec driven development workflow https://github.com/sermakarevich/sddw/) was to adjust it to my specific needs and the typical size of the features I build. Since then, this approach (sddw) has been presented at a few companies, including Google Poland. One of the conclusions from these conversations was that some teams would also like to adapt the…
May 2026
- 9LB
For the past few months I've been building a lot of things with LLMs (GPT-3, Codex, etc.) as I've been trying to push them to their limits (especially towards applying them to the tabular data domain) When working on this, I've found there are some common patterns for solving problems (templating, chaining, functional-programming style operations, etc.) As I've iterated, I've come to believe that a functional style interface is likely going to power a new wave of systems I'm calling "prompt-machines"(systems where the core new unit of work is a "named" LLM prompt, extending the "function"…
2022 · github.com
- 10AH
hey guys, i wanted to show one of my side projects. The idea is a coding harness (independent of models) natively designed for C/C++ developer workflows. I'm a C++ dev and do not find claude code work well with C++ toolchain like gdb and perf. The current version has integrations for gdb, clang-tidy, cppcheck, sanitizers, perf, benchmarking, compile DB navigation, Godbolt, symbolization, binary inspection, and decompilation. It supports Anthropic, OpenAI, Gemini, and self-hosted models. There are editor workflows for VS Code, CLion, emacs, neovim, and cursor.
Jul 2026 · byteask.ai
- 11SD
We built a Claude Code plugin that adds fine-grained authorization to apps. Works for creating new apps, adding features to existing apps, and migrating legacy authorization layers. The plugin helps design the permission model, write a SpiceDB schema, identify authorization points in the code base, generate SpiceDB client code, and test the authorization model. We designed the plugin around different modes of working with Claude Code: 1. Guided workflow. /spicedb-dev:plan is the single entry point for anyone unsure where to start. It scans your data model, produces an authorization…
Apr 2026 · github.com
- 12MA
2024 · repo-distillery.vercel.app
- 13SS
Hola HN! Long time lurker, sometimes commentor, first time poster here. I’ve been working alongside my two co-founders and a few colleagues on a project I’m excited (and a little nervous) to share with you all! Like many of us, I’ve lived a tortured existence with AI coding (is it vibes?) over the past few months - I think November was a big moment with this. But, one thing I’ve noticed after building orchestration layer after orchestration layer is that the thing I always came back to was “what the hell is Claude Code actually doing?” Perhaps it’s because of the time Claude Code got…
Jun 2026 · backplanes.com
- 14EC
I participated in the Nvidia + Vercel 2 hour hackathon in SF tonight, and built something I've wanted, but hadn't tried building. I implemented an MCP Server and VS Code extension to allow Claude Desktop to place breakpoints, step through code, and execute expressions (assuming language support). So you can ask it a question that requires actually stepping through the code and now it can actually do that - check values for you, etc. It's _definitely_ not perfect. Have improvements? Please make a PR!
2025 · github.com
- 15CC
I’ve found coding agents to be great at 1/ finding everything they need across large codebases using only bash commands (grep, glob, ls, etc.) and 2/ building new things based on their findings (duh). What if, instead of a codebase, the files were all your workplace docs? There was a `Google_Drive` folder, a `Linear` folder, a `Slack` folder, and so on. Over the last week, we put together Craft to test this out. It’s an interface to a coding agent (OpenCode for model flexibility) running on a virtual machine with: 1. your company's complete knowledge base represented as…
Jan 2026
- 16CC
I’ve been exploring LLM-driven developer workflows and built a demo where Claude Code acts like a Replit-style frontend for infrastructure. - You write a prompt in Claude - Claude generates a workload spec - Humanitec receives the spec and deterministically deploys infra to GCP (via Terraform) - App is up in under 1 minute — no pipelines, no DevOps tickets The backend is policy-enforcing and built for enterprise use cases (used by large orgs like Apple, ABB, etc.), but the flow feels like magic for devs or agents. demo: https://www.youtube.com/watch?v=jvx9CgBSgG0 Repo:…
Oct 2025
- 17DX
Hey HN — I'm Michael from Decipher (https://getdecipher.com). We build infrastructure for autonomously generating and maintaining end-to-end tests. Today we’re launching our Claude Code integration. We built this because as teams ship more code, especially with coding agents, they need more regression coverage. Claude can already generate a decent Playwright file from a repo and prompt. That solves first-draft generation. It does not solve repeatability. A generated test is still a static guess. The real problems start when it meets the live app: the browser is logged out, a modal…
Mar 2026 · docs.getdecipher.com
- 18AD
Hey HN, as a former data analyst, I’ve been tooling around trying to get agents to do my old job. The result is this system that gets you maybe 80% of the way there. I think this is a good data point for what the current frontier models are capable of and where they are still lacking (in this case — hypothesis generation and general data intuition). Some initial learnings: - Generating web app-based reports goes much better if there are explicit templates/pre-defined components for the model to use. - Claude can “heal” broken charts if you give it access to chart images and run a…
Mar 2026 · rubenflamshepherd.com
- 19TM
Dec 2025 · claudekit.cc
- 20PA
Claude Code is amazing at writing code, but it will happily build from under-specified requirements, implement the same thing different ways, and fail to write great tests unless you specifically ask it to. Prawduct is a set of prompts, skills, hooks, and artifact templates that help focus Claude Code on product development rather than code development. You can start from something a simple as "make a website with a scientific calculator" or as complex as "create a MMO with clients for iOS, Android, and web". You can specify as much or as little arch standards or implementation details as…
Mar 2026 · github.com
- 21OA
Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Mar 2026 · openui.com
- 22SI
Claude Code is amazing for individuals but terrible for teams. I spent the last six months building my perfect mix of MCP servers, subagents, commands and skills. Claude Code writes 100% of the code now, but sharing this with my team? Painful. 1. Blog posts and workshops don't work (and don't scale) 2. Committing tools to N repos means N PRs. A tool changes? N more PRs. 3. Same tools, different files or folders for each AI assistant; not everyone uses Claude Code It is like 1999 all over again; FTPing files up to prod and versioning with ".bak" suffixes. So I built sx. It is your team's…
Jan 2026 · github.com
- 23PC
Hi, We’ve built Pantheon-CLI, an fully open-source project that aims to be the “Python Claude Code + Notebook” — but designed for data analysis instead of just coding. Unlike most AI coding assistants, Pantheon-CLI runs entirely on your machine (or server). No data upload required. It blends natural language and code in a single workflow, keeping variables in memory and letting you switch seamlessly between typing code and asking in plain English. What it does: 1. Chat with your data: Directly process CSV, Excel, AnnData, Pickle, Torch tensors, or any format supported by…
2025 · github.com
- 24FG
Open-source tutorial series teaching real-time graphics programming with SDL's GPU API. Covers everything from Hello Window to SSAO, with math lessons, engine lessons, and a UI track building font rendering from scratch. Every lesson is a standalone C program with commented code explaining why, not just what. The whole project was built with Claude Code. Each lesson also distills into a reusable Claude Code skill — copy them into your own project and build games with AI that actually understands the GPU patterns.
Feb 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →