DiffLogs
AI-powered API changelog generator for lazy developers
What it does
I hate writing API changelogs. I always forget what changed, skip details, or just don't do it at all. So I built DiffLogs. Paste your old and new API spec and AI generates a clean changelog in seconds. Don't have a spec? Just type what changed in plain English. - Detects breaking changes automatically - Supports YAML, JSON, Postman, GraphQL - Shareable public changelog URLs - Team collaboration with shared history Free tier available. Built in 4 days. Would love brutal feedback.
Does a similar job
all alternatives →
- CAChangeloghub – Automatically create beautiful changelogpages (beta)2025 · changeloghub.com · ▲5
Hey HN, I built ChangelogHub (https://changeloghub.com) to automate something that is always last on my list for every release: writing clean and human-readable changelogs. Human-readable being the key phrase here. Writing changelogs manually is tedious, especially for backend/infrastructure changes that users never see but matter a lot. I wanted something that didn’t just rephrase commit messages, but actually understood the code diffs. HOW IT WORKS: - Analyzes diffs from PRs or direct commits - Summarizes the changes using OpenAI (code-diffs+custom prompt + heuristics) -…
- DADiffmatic – A daily GitHub digest for dev teams2014 · diffmatic.com · ▲67
- WBWe built an AI to review your pull requests2025 · infinitcode.ai · ▲53
Hey HN, We’re two developers (co-founders) with a team of 20 who got tired of spending hours reviewing PRs, so we built Infinitcode.ai, an AI-powered code reviewer that: - *Summarizes PRs in plain English*: No more deciphering 1,000-line diff jungles - *Catches more than bugs*: Security holes, performance pitfalls, code smells, even typos (yes, we’ll flag “vurnerabilities” and vulnerabilities) - *Zero onboarding*: Works instantly—no “let me learn your codebase for weeks” nonsense. Why we’re posting: We’re in alpha and need brutal honesty. Roast our tool, mock our UI, or tell us why AI will…
- CGChangelog Generation Tool2020 · ▲5
It's the Easter holidays here so I decided to finish one of the pet-projects that I had on my work machine. https://github.com/bdryanovski/logchanges This small package is designed to help me generate a changelog for my other projects and keep it up to date when it comes to update and handle it. The JSON part is for the cases when I want to integrate it into Single Page Apps like for example inside https://docusaurus.io/ or https://www.gatsbyjs.org/ when I want to have a lot more control on how the data is rendered. Or even make it…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com