How coding agents use GitHits across the software development lifecycle
How coding agents inspect external open-source dependencies across the software development lifecycle (SDLC).
GitHits beta 0.9 Blog5 min read
agents
229 stories
Reducing the cognitive load of AI-generated PRs
How we designed a higher proxy for keeping a shared mental model of a fast evolving software system
Coldtea.ai Blog9 min read
AGENTS.md Explained: How to Write One File Every Coding Agent Can Read
AGENTS.md is the open standard for giving AI coding agents project context. Learn what it is, how it differs from CLAUDE.md and .cursorrules, and how to write one with a free generator.
Moxie Docs Blog8 min read
You are the worst possible judge of whether AI makes you faster
Developers rate their own productivity at a correlation of 0.17 with their measured output. In a trial they reported a 20% speedup while a stopwatch recorded a 19% slowdown. One company raised its pull requests 13.6% and its real output by 1%.
Coldtea.ai Blog21 min read
Source code as primary context for coding agents
Coding agents should inspect source code directly, use deterministic search for retrieval, and reserve model reasoning for understanding and decisions.
GitHits beta 0.9 Blog4 min read
What the 100 biggest GitHub repos put in their AGENTS.md files
We read the AGENTS.md files of the 100 most-starred repos on GitHub that have one. Here's what they instruct their coding agents, what they ban, and a copy-paste template distilled from all of it
Coldtea.ai Blog7 min read
Building a Three.js Game With and Without GitHits
We ran the same model and the same prompt twice to build a Three.js game — one agent with GitHits, one without. Here is how far each got.
GitHits beta 0.9 Blog7 min read
Claude alternatives in 2026 — when you need more than a conversation
Claude is one of the best AI models available. But a conversation that resets every time is not the same as an agent that works for you. Here is what to use when you need more.
Aramb Blog10 min read
Scaling Test-Time Compute in Search Mode
Introducing medium, high, and ultrahigh effort tiers to the Query Agent's Search Mode.
Weaviate7 min readLLM agent cost in production 2026: $0.40 for an 8-step loop
LLM agent costs in production 2026: three workload models with token math and USD totals per 1,000 runs, from a 3-call support bot to an 8-step coding loop.
LLMTest Blog6 min read
Introducing agentOS Execution API for JavaScript and Python
agentOS now has an execution API for running JavaScript (Node.js) and Python instead of using bash.
agentOS Blog6 min read
Run Your Harness Outside the Sandbox: Why and How
Why the agent harness shouldn't run inside the sandbox, and how to run it in your own backend instead.
agentOS Blog15 min read
Sandboxes vs WebAssembly → Lambda vs Workers, Round Two
Sandboxes reserve a container per agent while the agent sits idle waiting on inference. That's the same mistake Lambda made, and isolates already solved it.
agentOS Blog3 min read
Flue now supports agentOS
A lightweight alternative to sandbox VMs for your Flue agents, running on V8 isolates and WebAssembly.
agentOS Blog5 min read
Vercel's Eve now supports agentOS
A lightweight OS for every Eve agent, running in the backend you already operate. No sandboxes, VMs, or SaaS.
agentOS Blog4 min readSix Postgres 19 Features Your Coding Agent Does Not Know About
We used GitHits to explore the Postgres 19 release and surface what changed. Six features came back. A coding agent without GitHits could not reach any of them.
GitHits beta 0.9 Blog7 min read
How we built Agent Runner with AI coding tools
How Agent Runner went from a 23-minute prototype to a finished game built with coding agents, source context, generated concepts, and hand-made art.
GitHits beta 0.9 Blog6 min read
Controlling Reasoning Effort in LLMs
How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes
Sebastian Raschka25 min read
Showing 180 of 229 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts