33,075 results for act · 2.583s

News for “act”
17 results • 2576 ms server time
Moozonian News
heyrepairo.in• Aug 11, 2026• 1 min read
Show HN: Repairo-I built CLI tool that detects breaking API changes and fixes itGuys check it out i have build this tool which detects breaking API changes when a vendor like striker or any companies does REPAIRO scans the codebase and fixes the code using AST parsing and pull a GitHub pull request.Its Depandabot but for refactoring code third party API changes. Guys please check it out and sign up for the beta
Moozonian News
bing.com• Aug 11, 2026• 1 min read
AI Without A Source Of Truth Is Just Confident GuessingIt can summarize a problem, recommend a path, trigger a workflow and explain its reasoning with the calm and confident tone of a person who knows exactly what they’re doing. But, of course, confidence ...
Advertisement
Moozonian News
seedle.loch.tools• Aug 11, 2026• 1 min read
Show HN: Seedle, daily -dle for Minecraft seedsIf you're not familiar with RNGdle, it's a daily game that randomly generates a 6 digit code. Pure dopamine delivery with little else of substance, but what else do you really need?I love the RNGdle idea, but I thought it might be even more fun as a way to discover Minecraft seeds. So I spent the day making this.For the uninitiated, Minecraft is deterministic, so you can determine what exactly the spawn point of a new world looks like if you know the seed number. This project gamifies that discovery process by assigning value to certain generated features, culminating in an overall score. It's just a little dopamine hit + small potential value for people who actually play Minecraft.
Moozonian News
github.com• Aug 11, 2026• 1 min read
Show HN: Sketchling – a hand-drawn animation language for coding agentsI built sketchling this weekend to see if agents can draw something that looks natural and hand-drawn if given the right primitives. This was inspired by Manim after watching how powerful an agent-native way to produce animations can be.It is a small typescript library with shapes that take character parameters like weight, looseness, and energy. It renders through rough.js and GSAP through a headless chromium browser. It has tools like a built-in linter and is meant to be agent-native.As a test, I gave the library to Devin cold with minimal instructions and it came back with a 3 minute, 9 scene short film which I found cool! I also had 5 more agents each try a different style, pixel art, clean line, clay, 3D, even a jazz club scene with its own music, and they all came out looking different which was awesome to see.I have added procedural walk cycles, camera movement, particle movement, and a small sound library as well. It is very early and has Chromium and ffmpeg as dependencies, wh
Advertisement
Moozonian News
trysecondstate.com• Aug 11, 2026• 1 min read
Show HN: SecondState – what if Hebbia started with raw ERP data?Hi HN,I have been tinkering on a project for quite some time now. Most AI finance tools begin after the data is ready. Financial Diligence and audits don’t.I built SecondState to start one layer earlier.The interesting pieces:- Agentic data transformation: It has kind of cursor for “data engineers” : you declare what you want and the agent builds the DAG and materialize it with a human-in-the-loop approval gate.- Just-in-time Analytics: once you have some clean data, you can ask whatever question and it builds a dashboard on demand, helping users narrow the aperture on what’s valuable to look at.The problem originates from my previous experience at a BIG 4 :Every deal starts with a data room: General ledgers. Accounting records. Contracts. Financial statements & Endless spreadsheets.And before anyone can understand operate on top, a loot of offshore teams in poor countries have to reconstruct it by hand and inject it into a dashboard.Does this kill Hebbia? No. But I think the winning p
Moozonian News
github.com• Aug 10, 2026• 1 min read
Show HN: Pyrig – One command to set up a production-ready Python projectI built pyrig because I did the same setup everytime I started a proper python project. I genuinely believe this can be a great tool, for me it has already genuinely simplified my python project development. I would love feedback on this of any kind. Below is a description of what pyrig is and does.pyrig generates and maintains a complete, production-ready Python project from a single command. It creates all the files you need — source structure, tests, CI/CD, documentation, configs — and keeps them in sync as your project evolves.uv inituv add pyriguv run pyrig initYou get: package structure with a CLI entry point, test framework with 90% coverage enforcement, GitHub Actions (CI/CD, releases, docs deployment), pre-commit hooks, MkDocs documentation site, and container support.The key difference from templates like cookiecutter is that pyrig isn't a one-shot scaffold. It's idempotent — rerun it anytime to update configs, add missing files, or sync with the latest defaults. It merges mi
Moozonian News
github.com• Aug 10, 2026• 1 min read
Show HN: Keen Code – an agentic-engineered coding agentHello community!I am here to share a coding agent I have built solo from scratch using agentic engineering. Written in Go, it's a proper coding agent, has features you expect from a useful agent for your daily work, with a minimal and simple UI.I have named it Keen Code. The repo is here: https://github.com/mochow13/keen-codeEven though it started as an experiment, it is now a full-fledged coding agent for real software engineering work. It supports multiple providers, skills, MCPs, multi-agent orchestration through subagents, automatic compaction, etc.I have been using it for real production-grade work myself, and also for developing itself.Notably, I have worked on two separate ideas in this coding agent:1. Turn MemoryIn a multi-turn conversation, tool outputs are removed, only tool call traces are retained. Within a single agent loop, agent sees full tool results but in the next turn, it doesn't see the tool results anymore.The greatest benefit of this approach is that a lot of tool
Moozonian News
kmcheung12.github.io• Aug 10, 2026• 1 min read
Show HN: My local climbing gym from photogrammetryCommented on yesterday's Ask HN: What are you working on? (August 2026), thought I might as well submit a Show HN.If you see climbing world cup/championship, there is this 3D modelling thing [1]. I want that for my weekly bouldering.I scanned my local climbing gym into 3D mesh using iphone. Built a simple editor to trim, merge, move/rotate meshes. You can interact with the mesh, view routes, view climb, etc. So this is unlike many gaussian splatting projects where the main use is for viewing. I built a pipeline in updating climbing walls. Climbing routes are manually annotated. Climbing videos are registered against the 3D mesh. Based on one input video, body positions resolved into 3D/4D space. you can view the body landmarks from different angle.COLMAP, OpenMVS, fastapi, svelte, database is just local json files. A read only build is exported so I can host on github pageIf you climb, or know someone who climbs, would love to hear your feedback. Do you usually record your climbs? If I
Moozonian News
oqoqo.ai• Aug 10, 2026• 1 min read
Show HN: Oqoqo – build evals and custom benchmarks for real-world tasksMost benchmarks today exist in curated environments and do not translate well to the real world.We built Oqoqo to bridge this gap. Oqoqo makes it super simple to build realistic evals and custom benchmarks for tasks users actually care about.Oqoqo can:- Reliably measure how agent friendly your product surfaces are against Codex, Claude Code, OpenClaw, Hermes, Pi, Opencode, Cursor, GitHub Copilot - Regression test MCP, CLI, skills, SDK, and any agent facing interface (we are continuously using Oqoqo to dogfood and improve our own MCP/CLI) - Create and share custom benchmarks for how agents discover and use your product - Compare models and harnesses for domain specific tasks - See whether new versions improve agent experienceWould love to hear feedback and thoughts on what kind of evals you are running today, if you are benchmarking agent facing interfaces, and whether you have published a custom benchmark.