Building M31A: A Terminal-Native AI Coding Agent That Ships, Not Just Suggests
Most AI coding assistants are glorified autocomplete on steroids. They suggest code, maybe write a function or two, but leave you holding the bag when…
Team Management
⚑ Report a ProblemLatest Team Management news from Tech News
All topics
Culture
agents
ai
api
architecture
automation
beginners
career
claude
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
productivity
programming
python
react
saas
security
showdev
softwareengineering
startup
testing
tutorial
typescript
webdev
Microsoft's Intelligent Terminal brings AI agents to the command line with familiar experience
Microsoft’s Intelligent Terminal for Windows 11 lands with a clear promise: bring GitHub Copilot–class AI assistance directly into the developer’s com…
skillscore: a CLI that scores your AI agent's SKILL.md 0–100
A vague AI agent skill is worse than no skill at all — because the agent pays for it in context budget on every single turn , whether it uses it or no…
I gave your agent access to Firefox - meet Firefox CLI
Firefox CLI is my new project - a CLI interface that lets your agent control your real Firefox session. It's a full equivalent of Agent Browser with t…
Your MCP tool surface has a token bill — here's how to read it
If you're building MCP servers, here's a cost that's easy to miss: Every tool you expose is re-sent to the model on every call. Not once at startup, e…
Shipped my first open-source repo
I independently shipped my first open-source repo this week. The tool I built was a cli which accesses quickbooks online data. While Claude Code did s…
one last peek 👀🍵 docs, a demo, and a goodbye for now
Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lr…
I built a terminal SSH manager because I was tired of scrolling bash history
I manage a handful of servers across client environments. Some use key auth, some use passwords, and most of the time I need root access once I'm in. …
The Hidden Contract of Mastery: Why Complexity Is Yours to Absorb
A few days ago, someone left a comment on one of my open source projects. They'd tried my CLI tool — a 3D print quality inspector called Printsight — …
peektea past the roadmap 👀 sorting and scrollable previews
Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lr…
peektea narrows its gaze 👀 filter-as-you-type and hidden files
Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lr…
One Schema to Rule Them All: The Config v2 Rewrite
This is part sixteen in a series about managing the growing pile of skills, scripts, and context that AI coding agents depend on. The 0.8.0 release no…
The Improvement Loop: How akm Keeps Your Agent Sharp
This is part ten in a series about managing the growing pile of skills, scripts, and context that AI coding agents depend on. Part nine covered workfl…
pingtrace 1.0: why I rewrote from npm to Go
In March I shared the first version of pingtrace here on DEV. That version answered the initial question: could I make the first minutes of a network …
peektea opens a second eye 👀 side-by-side file previews
Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lr…
Building AppForge: A Unified Project Scaffolding CLI for Modern Development
As developers, we've become accustomed to powerful tooling that helps us get started quickly. If you've worked with React, you've probably used Create…
I scanned my PC and found 457 AI agents — here's what I built to manage them
The Discovery I've been using AI coding agents heavily — Claude Code, Codex, Pi Agent. One evening I asked myself: how many agent-related files are ac…
Oneconfig: A CLI That Detects Your Stack and Provisions Your Dev Environment
Every repo has the same onboarding ritual: figure out the stack, install the right tools, start the right services, and hope the README is still accur…
## Stop Wasting Time on Dev Setup — I Built a CLI That Automates Everything
One thing that has always bothered me as a developer is how much time gets wasted setting up new projects. Creating folders, configuring Docker, setti…
Coding agents keep losing context between tools, so I built a local-first handoff CLI
The problem I often switch between Codex, OpenCode, Cline, Claude Desktop, scripts, and terminals. The annoying part is not starting a new tool. The a…
I built agmsg so Claude Code and Codex could stop using me as a copy-paste relay
My main driver is Claude Code, with Codex bolted on for the hard parts and reviews. The split works surprisingly well. But after a while I noticed som…
I built a CLI that scaffolds agentic workflows for Claude Code
Most developers using Claude Code work the same way: one long conversation, manual prompting between tasks, context that grows until the model loses t…
I built DeepWrap: a Python SDK and CLI for DeepSeek Chat
DeepSeek Chat was free in the browser. But the moment I wanted to use it like a developer, it became a different story. That annoyed me more than it p…
rdev-go-ddgen: Automating Domain Directory Boilerplate for Go Applications
When building robust backend APIs in Go, maintaining a consistent, clean architectural pattern across domain directories is essential for scalability.…
How I manage 40+ skills across Claude Code, Codex, and .agents folders
I started with three skills. A year later I had forty-something. Every Claude Code session loaded all of them. Every Codex run loaded all of them. Eve…
I Built a Next-Gen DNS Diagnostic CLI in Rust That Visualizes DNSSEC Trust Chains
If you've ever tried to debug a DNSSEC misconfiguration using dig , you know the pain. You're staring at a wall of raw text, manually cross-referencin…
From Blender Demos to Agent Toolchains: Why Terminal Skills Matter
Most AI + Blender demos still follow the same pattern: Ask the model for a prompt. Generate a scene or script. Hope the result looks close enough. Try…
What's new in llm-cli-gateway
A few weeks ago I wrote Why CLI Wrapping Beats API Proxying for Multi-LLM Development , the case for spawning claude , codex , and gemini as child pro…
Toward a more POSIX-Friendly PowerShell experience
I'm a MacOS and Debian user primarily, but my 9-5 is a Windows shop that requires I work from a Windows PC primarily due to security constraints. I al…
/disconnect for opencode — a tiny TUI plugin I wish existed before I made it
I use opencode as my daily TUI coding agent. It's good. But there's one thing that kept biting me. When you want to remove a single provider — say you…