# bash Published articles for bash. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Configure Bash History: HISTSIZE, Timestamps, Sync, and Search Shortcuts DevFeed: [Configure Bash History: HISTSIZE, Timestamps, Sync, and Search Shortcuts]() Original publisher: [Read original article]() Author: Hayden James Published: 2026-09-03T18:31:24Z Content type: tutorial Language: en Sources: [Hayden James]() Topics: [Bash](), [Scripting, bash](), [Command-line interface]() Tags: [bash](), [blog](), [command-line](), [commands](), [history](), [how-to](), [linux](), [security](), [server](), [sysadmins]() ### AI overview A tutorial on configuring Bash command history, including history size, timestamps, synchronization across terminals, search shortcuts, and excluding commands from history. ### Source excerpt Bash history does a lot more than scroll up. Learn how to configure HISTSIZE, timestamps, multi-terminal sync, and search shortcuts to get real productivity gains at the command line. Continue reading... ## Omnigent: A Meta-Harness for Coding Agents DevFeed: [Omnigent: A Meta-Harness for Coding Agents]() Original publisher: [Read original article]() Author: Daniel Beach Published: 2026-08-31T12:04:20Z Content type: opinion Language: en Sources: [Data Engineering Central]() Topics: [Artificial Intelligence](), [AI-assisted coding](), [Claude Code](), [codex](), [Model Context Protocol]() Tags: [agents](), [bash](), [claude-code](), [codex](), [coding-agents](), [cursor](), [mcp]() ### AI overview The author introduces Omnigent as a meta-harness for agents while discussing the overload of coding-agent tools, configurations, plugins, MCP servers, and Bash-command controls. ### Source excerpt I got you boo ## Practical Loop Engineering DevFeed: [Practical Loop Engineering]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-14T14:30:53Z Content type: opinion Language: en Sources: [Elevate]() Topics: [Loop Engineering](), [AI Agent](), [Claude Code](), [codex](), [Code review](), [Scripting, bash]() Tags: [agent](), [agents](), [bash](), [claude-code](), [code-review](), [codex](), [engineering](), [loops](), [workflows]() ### AI overview An opinion article about practical loop engineering for AI-assisted software development. It describes running multiple agents in parallel, delegating bounded tasks with explicit stopping conditions, and using goal- and timer-based loops in Claude Code and Codex. It emphasizes careful supervision and well-defined goals and constraints, especially for complex or high-risk codebases. ### Source excerpt Goals, loops, and the discipline of not delegating your judgment ## Practical Loop Engineering DevFeed: [Practical Loop Engineering]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-14T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Loop Engineering](), [AI Agent](), [Claude Code](), [codex](), [Bash]() Tags: [agent](), [agents](), [ai](), [ai-agent](), [bash](), [claude-code](), [code-review](), [codex](), [complexity](), [engineering](), [loops](), [workflows]() ### AI overview The article explains loop engineering as an autonomous, self-correcting feedback cycle in which an AI agent acts, tests results, and adjusts its approach toward a defined goal. It discusses Claude Code and Codex primitives, earlier Bash-based loops, and the need to define goals and constraints carefully before delegating work, especially in complex or high-risk codebases. ### Source excerpt Goals, loops, and the discipline of not delegating your judgment ## C++-техрадар: что разработчики действительно готовы брать в работу DevFeed: [C++-техрадар: что разработчики действительно готовы брать в работу]() Original publisher: [Read original article]() Author: Kaspersky\_Lab ("Лаборатория Касперского") Published: 2026-08-07T13:17:24Z Content type: article Language: ru Sources: ["Лаборатория Касперского" RU]() Topics: [C++](), [CMake](), [PostgreSQL]() Tags: [bash](), [bazel](), [c-plus-plus](), [clang](), [cmake](), [gdb](), [git](), [plus-plus-3a0baa67a2fc](), [postgresql](), [tech-radar](), [vs-code]() ### AI overview The article analyzes the C++ portion of a technical radar based on survey responses from developers at C++ Russia and HolyJS. It explains how technologies are assessed across Adopt, Trial, Assess, and Hold categories, emphasizing that the overall distribution of votes matters more than a single dominant response. The supplied evidence specifically notes CMake as a strong performer and PostgreSQL as dividing respondents. ### Source excerpt В мае на конференциях C++ Russia и HolyJS мы предложили участникам оценить технологии, инструменты и инженерные практики, с которыми они работают или за которыми следят. Так появились данные для двух технических радаров: по экосистеме C++ и по JavaScript. Сырые цифры сами по себе рассказывают немного, поэтому мы отдали результаты на разбор эксперту. Виктор Новиков, руководитель группы разработки в "Лаборатории Касперского", посмотрел на распределения голосов и поделился своим мнением, почему CMake уверенно побеждает, а PostgreSQL раскалывает аудиторию пополам. В этой статье -- его анализ C++-части исследования. Про техрадар JavaScript мы расскажем в другой статье. Посмотреть радар и принять участие в голосовании можно на странице проекта. Читать далее ## Proxmox VE Helper-Scripts: guía y buenas prácticas DevFeed: [Proxmox VE Helper-Scripts: guía y buenas prácticas]() Original publisher: [Read original article]() Author: Antonio Pérez Published: 2026-08-04T00:00:00Z Content type: tutorial Language: es Sources: [tengoping.com]() Topics: [Proxmox](), [Bash](), [Script](), [Command-line interface](), [qemu](), [GitHub]() Tags: [bash](), [community](), [github](), [http](), [proxmox](), [qemu](), [root](), [script](), [scripts](), [shell]() ### AI overview This guide explains what Proxmox VE Helper-Scripts are, how community-scripts.org uses Bash scripts to deploy applications in LXC containers or QEMU virtual machines, and how the main script downloads and runs the required components. It also highlights the security risk of executing third-party code as root on a Proxmox hypervisor. ### Source excerpt Qué son los Proxmox VE Helper-Scripts de community-scripts.org, cómo despliegan LXC y VMs con un solo comando y qué riesgos de seguridad debes valorar. ## Four Ways to Deploy More Secure AI Agents DevFeed: [Four Ways to Deploy More Secure AI Agents]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-07-30T21:09:59Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI Bots](), [Language models]() Tags: [agentic-ai-generative-ai](), [agents](), [ai-agent](), [ai-agents](), [ai-red-team](), [bash](), [featured](), [secrets](), [trustworthy-ai-cybersecurity]() ### AI overview The article examines recurring security failures in AI agents and recommends access controls, least-privilege permissions, and safeguards for tool execution, network access, and secrets. ### Source excerpt Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as "digital coworkers" offer clear benefits. For example,... ## Orchestration powered by Temporal at Zscaler: Wrap, don't rewrite DevFeed: [Orchestration powered by Temporal at Zscaler: Wrap, don't rewrite]() Original publisher: [Read original article]() Author: Abhishek Mitra Published: 2026-07-22T00:00:00Z Content type: opinion Language: en Sources: [Temporal Blog]() Topics: [Orchestration](), [Automation](), [Ansible](), [opentofu](), [Terraform](), [argocd](), [GitOps](), [Provisioning]() Tags: [ansible](), [automation](), [aws-cloudformation](), [bash](), [ci](), [cli](), [gitops](), [infrastructure-as-code](), [orchestration](), [provisioning](), [temporal-voices]() ### AI overview The article describes how Zscaler designed a durable orchestration contract above eight heterogeneous automation engines, including Ansible, Terraform, OpenTofu, Helm, ArgoCD, Crossplane, Kubernetes Cluster API, AWS CloudFormation, and Jenkins. The approach aims to coordinate existing tools without rewriting them. ### Source excerpt How one durable contract above eight automation engines changed Zscaler's architecture without changing the engines ## Opening Sublime Text from the command line DevFeed: [Opening Sublime Text from the command line]() Original publisher: [Read original article]() Author: Rob Published: 2026-06-30T10:00:00Z Content type: tutorial Language: en Sources: [Rob Allen]() Topics: [Sublime Text](), [Command-line interface](), [Bash](), [JSON](), [sessions]() Tags: [bash](), [command-line](), [computing](), [extension](), [json](), [sessions](), [shell-scripting](), [software]() ### AI overview A tutorial on using a Bash function to open Sublime Text from the command line with different window behaviors for directories and files. It extends the function to create and manage a hidden .sublime-project JSON file so open files persist across sessions. ### Source excerpt I nearly always open Sublime Text from the command line using subl and have specific requirements for when it should open a new window or re-use one. If I'm opening a directory, then I would like it to re-use the same window if I have previously opened that directory. However if I open a random file, I never want that file in the last directory window as it's unrelated. To do this I wrote a... continue reading. ## Filtering Build Output Reduced AI Coding Agent Token Consumption by Up to 30% DevFeed: [Filtering Build Output Reduced AI Coding Agent Token Consumption by Up to 30%]() Original publisher: [Read original article]() Author: Bartek Lipinski Published: 2026-06-23T16:01:03Z Content type: tutorial Language: en Sources: [Whatnot Engineering]() Topics: [AI-assisted coding](), [AI Agent](), [context window](), [context](), [Tool]() Tags: [agent](), [agentic-ai](), [ai](), [ai-agent](), [ai-coding-agents](), [bash](), [build](), [commands](), [compiler](), [context-window](), [llms](), [token](), [token-efficiency](), [tool]() ### AI overview The article explains how filtering irrelevant build output with a regex can reduce token consumption for AI coding agents by up to 30%. It describes how noisy logs fill the context window, causing repeated costs and unnecessary tool calls, and presents filtering as a way to make agent behavior more predictable. ### Source excerpt Our AI agent was burning tokens on every turn by processing build noise that provided no signal. Context windows clogged with irrelevant logs, forcing the agent to waste cycles and thrash through unnecessary tool calls. We solved this with one line of regex; a filter that cut token consumption by up to 30% and, more importantly, stopped the agent from flailing. It's not just a cost-saving trick; it makes the agent's behavior more predictable, spending its budget on the fix instead of the hunt. To grok this, imagine a chef tasked with making a soufflé with ingredients but no recipe. An expert chef, using school-honed skills, might succeed immediately or through a few refined attempts. Success is inevitable because they possess the competence to iterate. A mediocre chef eventually succeeds too, but wastes far more food in the process. AI coding agents operate similarly when facing unknowns. They iterate, try, and fail before reaching an answer. They are capable enough to succeed, but they waste significant compute and tokens during the process. The solution isn't rocket science, but just really good filtering that is specific to tasks that can be token-heavy. Here's an example of that below. For the rest of the post we will do a deep dive into what we did, how it works, and you can ultimately use the recipe for your coding agents. The asymmetry Coding agents with capable LLMs are good at knowing which tool to call. They pick the right command as they work towards their objective. But they are bad at predicting what the output will look like and where in that output to focus. The agent fires off a build command. Hundreds of lines of build output land in its context window. The relevant compiler error is buried somewhere in the middle. Reading through a log is second nature to you; you scan the text without a second thought. You scroll. Your eye snags on red text, stack traces, the word FAILED. You find what matters in seconds, and the rest of the output costs you nothi ## Building Agents that Don't Break Themselves DevFeed: [Building Agents that Don't Break Themselves]() Original publisher: [Read original article]() Published: 2026-06-08T00:00:00Z Content type: tutorial Language: en Sources: [The Fly Blog]() Topics: [AI Bots]() Tags: [agent](), [agents](), [ai](), [api](), [bash](), [cdn](), [close-to-users](), [deploy-app-servers](), [docker](), [elixir](), [fly](), [fly-io](), [heroku-alternative](), [heroku-competitor](), [hosting](), [i](), [networking](), [node-js](), [postgresql-clusters](), [sandbox](), [sandboxes](), [servers]() ### AI overview A tutorial on keeping long-lived AI agents safe by separating the agent process from risky shell execution. It recommends running each potentially destructive task in an isolated, disposable Sprite rather than letting the agent execute commands in its own environment. ### Source excerpt Building agents is fun. Rebuilding agents that break themselves... less so. A lot of Fly people are building agents with less of a penchant for self-destruction by teaching their agents to do anything risky in a Sprite. You get an agent that stays alive long enough to actually use its snazzy self-improvement features, and you can allow your agent to try things that would otherwise be battleship-scale footguns. Here's how to do it. Brains vs Hands Your agent would be pretty useless without a shell, because this is where it does agent things. Run the test suite, apply the migration, install the dependency, delete the temp files. Unfortunately, your agent's shell access is also what tends to ruin your afternoon, simply because "delete the temp files" and "delete the wrong files" are one fat-fingered glob apart, and as we're frequently warned, AI can make mistakes. This is why we have sandboxes. But a lot of people default to putting an agent that's going to do potentially scary work in a sandbox. This comes with a long list of tradeoffs that you really don't have to make, because where your agent lives and where it runs code are two entirely separate considerations. PPE for agent workers. The agent process is a loop. It calls a model, reads the response, picks a tool, rinse and repeat. It's a long-lived process that only becomes more competent and less stupid if memory, skills and history persist. So a Fly Machine that sleeps when idle and wakes on a message, a small VPS. Your laptop while you iterate. These are all fine homes for a loop calling an API, which doesn't need a blast shield. It's when you want your agent to execute that things get hairy. bash -c + whatever string the model just produced needs to be run in a padded room. Somewhere where the agent's code can't break itself or anything connected to it. And if your agent is doing more work than you are, you're going to want a whole facility of padded rooms that can be thrown away and rebuilt on a whim. One Sprit ## Webworm: New burrowing techniques DevFeed: [Webworm: New burrowing techniques]() Original publisher: [Read original article]() Author: Eric Howard Published: 2026-05-20T08:40:00Z Content type: article Language: en Sources: [WeLiveSecurity]() Topics: [Malware](), [backdoor](), [Reconnaissance](), [Discord](), [GitHub](), [API](), [Microsoft](), [Bash](), [Virtual Private Network](), [Amazon S3]() Tags: [api](), [apt](), [backdoor](), [bash](), [china](), [discord](), [eset-research](), [europe](), [github](), [ip](), [malware](), [microsoft](), [s3](), [server](), [techniques](), [tools]() ### AI overview ESET researchers analyze Webworm's 2025 activity, including its shift toward Europe, new Discord- and Microsoft Graph API-based backdoors, proxy tools, reconnaissance activity, and GitHub-hosted malware staging. ### Source excerpt ESET researchers describe new tools and techniques that the Webworm APT group recently added to its arsenal ## An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent... DevFeed: [An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent...]() Original publisher: [Read original article]() Author: Pinterest Engineering Published: 2026-05-12T16:01:00Z Content type: article Language: en Sources: [Pinterest Engineering Blog - Medium]() Topics: [Agent Skill](), [Artificial Intelligence](), [Claude Code](), [codex](), [Bash](), [iOS](), [JSON]() Tags: [agent](), [agent-skill](), [agentic-coding](), [agents](), [ai](), [ai-agents](), [analysis](), [architecture](), [bash](), [claude-code](), [code](), [codex](), [debug](), [engineering](), [engineering-culture](), [how-to](), [openai](), [pinterest](), [programming](), [skills](), [testing](), [workflows]() ### AI overview An engineer's guide to testing AI skill invocation in repositories and custom skills. It describes a Bash-based harness that runs positive and negative prompts, captures verbose logs, parses JSON-streamed output, and measures invocation reliability across an internal Codex fork and Claude Code. ### Source excerpt An Engineer's Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent Performance in Any Repository or Skill Author: Daniel Reed The tech industry is currently seeing a massive overhaul in the way we work and many are enjoying the benefits of AI agents, particularly when automating engineer workflows and serving domain-specific knowledge. However, relying on agents to consistently invoke a custom skill can be surprisingly unreliable at times. When adopting a new skill intended to help agents write code for Pinterest's iOS architecture (I'll call it rx-mvvm) we discovered that sometimes our knowledge skill wasn't being loaded into our agents. To address this, we conducted a series of tests on Pin-agent (an internal fork of OpenAI's Codex) and Claude Code to quantify the reliability of skill invocation and identify some best practices to maximize performance. This was a direct result of observing agents struggling to meet the skills bar during architectural reviews. We found that by applying different techniques we could track and drastically improve skill invocation rates on both tested agents. How to Build A Skill Test Harness Building a reliable test harness for agent skill invocation requires three key components working in concert. The Core Tool is a Bash script that orchestrates automated testing by piping prompts to your agent and capturing verbose output logs. The core execution is simple: if echo "$prompt" | claude --print --verbose --output-format stream-json > "$log_file" 2>&1; then command_success=true fi The script runs all test cases in sequence, collecting logs for later analysis. We ran the entire suite multiple times to account for the nondeterministic nature of agents. Prompts were categorized into two categories defined as arrays: Positive Cases -- 15 prompts covering the full spectrum of skill domains: CORE_PROMPTS=( "load the rx-mvvm-architecture skill" "check if this follows rx-mvvm patterns" # ... 13 more cases ) Negative Case ## Guix improves one-line deployment with more secure channel file downloads DevFeed: [Guix improves one-line deployment with more secure channel file downloads]() Original publisher: [Read original article]() Author: Ludovic Courtès Published: 2026-05-12T15:00:00Z Content type: article Language: en Sources: [GNU Guix -- Blog]() Topics: [Security](), [Deployment](), [Software](), [Bash]() Tags: [bash](), [deployment](), [reproducibility](), [research](), [security](), [software]() ### AI overview This article examines Guix one-line deployment commands and the security risks of downloading and executing arbitrary channel files. It introduces a feature for downloading channel files while addressing trust and security concerns. ### Source excerpt When offered the option to run other people's code, a prime consideration is often ease of deployment. While much progress has been made in support of rapid deployment, the security implications of those quick deployments is often overlooked. In this post, we look at a new feature of guix time-machine and guix pull in support of one-line deployment commands : the ability to download channel files, but without compromising on security. Sharing code The normal workflow to share software and make it easily deployable with Guix goes like this: someone puts their packager hat on and... ## How to run Terraform providers not meant for Apple Silicon with Rosetta DevFeed: [How to run Terraform providers not meant for Apple Silicon with Rosetta]() Original publisher: [Read original article]() Author: Tom Published: 2026-05-06T00:00:00Z Content type: tutorial Language: en Sources: [Tomasz Gągor]() Topics: [Terraform](), [x86](), [Arm]() Tags: [apple-silicon](), [architecture](), [bash](), [mac-m1](), [macos](), [provider-checksum](), [rosetta](), [terraform](), [tfenv](), [x86](), [x86-64]() ### AI overview A tutorial explains how to use Rosetta to run Terraform as x86_64 on Apple Silicon, allowing Terraform to download and use providers that do not yet support ARM and helping avoid provider checksum mismatches. ### Source excerpt Use Rosetta to run Terraform as x86_64 on Apple Silicon and avoid provider checksum mismatches. ## Setting Ghostty as default terminal on Ubuntu 26.04 DevFeed: [Setting Ghostty as default terminal on Ubuntu 26.04]() Original publisher: [Read original article]() Author: Tom Published: 2026-04-26T00:00:00Z Content type: tutorial Language: en Sources: [Tomasz Gągor]() Topics: [Terminal](), [Ubuntu](), [configuration](), [GPU]() Tags: [bash](), [configuration](), [ghostty](), [gpu](), [gpu-accelerated](), [how-to](), [iterm2](), [linux](), [performance](), [snap](), [terminal](), [ubuntu](), [ubuntu-26-04]() ### AI overview A guide to setting the GPU-accelerated Ghostty terminal as the default terminal on Ubuntu 26.04 using its new configuration method. ### Source excerpt A quick guide on how to set the GPU-accelerated Ghostty terminal as the default on Ubuntu 26.04 using the new configuration method. ## Pi versus Claude Code: An Honest Comparison of a Minimalist AI Coding Agent DevFeed: [Pi versus Claude Code: An Honest Comparison of a Minimalist AI Coding Agent]() Original publisher: [Read original article]() Author: Owain Lewis Published: 2026-04-18T17:00:15Z Content type: comparison Language: en Sources: [The AI Engineer]() Topics: [AI-assisted coding](), [Open Source](), [Claude Code](), [codex](), [TypeScript]() Tags: [bash](), [claude-code](), [code-reviews](), [coding-agents](), [extension](), [open-source](), [reviews](), [tests]() ### AI overview The article compares Pi, an open-source minimalist coding agent, with Claude Code and Codex. It examines Pi's four built-in tools, broad model support, editable system prompt, and TypeScript extensions, including a workflow for writing, reviewing, fixing, testing, and verifying code. It also discusses trade-offs such as the lack of built-in MCP, to-do tracking, sub-agents, and hooks. ### Source excerpt I spent a week with the minimalist AI coding agent Pi. Here's my honest take. ## Supabase docs over SSH DevFeed: [Supabase docs over SSH]() Original publisher: [Read original article]() Author: Greg Richardson Published: 2026-04-01T07:00:00Z Content type: release Language: en Sources: [Supabase Blog]() Topics: [Supabase](), [AI-assisted coding](), [Bash](), [OpenSSH](), [Filesystems](), [Open Source](), [TypeScript](), [Vercel]() Tags: [agent](), [ai](), [ai-coding](), [bash](), [cli](), [open-source](), [ssh](), [typescript](), [vercel]() ### AI overview Supabase introduces supabase.sh, a public SSH server that exposes Supabase documentation to AI coding agents through a bash-accessible virtual file system. The public experiment is designed to help agents browse current Markdown documentation and avoid hallucinated APIs, incorrect CLI commands, and missed configuration steps. ### Source excerpt Browse Supabase docs with grep, find, and cat. ## netlab: Switch to Lab Directory After an SSH Session Loss DevFeed: [netlab: Switch to Lab Directory After an SSH Session Loss]() Original publisher: [Read original article]() Published: 2026-03-23T07:31:00Z Content type: tutorial Language: en Sources: [ipSpace.net blog]() Topics: [ssh](), [Bash](), [Scripting, bash](), [Unix](), [Command-line interface](), [Script](), [Server]() Tags: [bash](), [netlab](), [script](), [server](), [ssh]() ### AI overview This tutorial shows how to use netlab status and jq in a Bash alias to return to the directory of a lab after reconnecting to a netlab server following an SSH session loss. ### Source excerpt I work on a laptop that loves to power down when not used (the right thing to do), which often breaks the SSH session to my netlab server (not so good). Reconnecting is trivial. Figuring out which lab I was working on and where it lives on the disk after a few hours? That's the annoying part. We solved most of that ages ago with the netlab status --all command. It shows all running labs1 and their directories, so you can quickly jump back to where you were. However, even that gets tedious the 100th time you have to do it. Read more ... ## Build knowledge agents without embeddings DevFeed: [Build knowledge agents without embeddings]() Original publisher: [Read original article]() Author: Ben Sabic Published: 2026-03-19T13:00:00Z Content type: tutorial Language: en Sources: [Vercel News]() Topics: [AI Bots](), [AI Chat]() Tags: [agents](), [ai](), [architecture](), [bash](), [debugging](), [embedding](), [open-source](), [postgres](), [sandbox](), [search](), [vector](), [vercel](), [workflow]() ### AI overview The article presents an open-source knowledge-agent template that replaces vector retrieval and embeddings with filesystem search in isolated Vercel Sandboxes. It describes source syncing, shell-based search, traceable results, and deployment options. ### Source excerpt Most knowledge agents start the same way. You pick a vector database, then build a chunking pipeline. You choose an embedding model, then tune retrieval parameters. Weeks later, your agent answers a question incorrectly, and you have no idea which chunk it retrieved or why that chunk scored highest. We kept seeing this pattern internally and for teams building agents on Vercel. The embedding stack works for semantic similarity, but it falls short when you need a specific value from structured data. The failure mode is silent: the agent confidently returns the wrong chunk, and you can't trace the path from question to answer. That's why we tried something different. We replaced our vector pipeline with a filesystem and gave the agent bash. Our sales call summarization agent went from ~$1.00 to ~$0.25 per call, and the output quality improved. The agent was doing what it already knew how to do: read files, run grep, and navigate directories. So we open-sourced the Knowledge Agent Template, a production-ready version of this architecture built on Vercel. What the template does The Knowledge Agent Template is an open source, file-system-based agent you can fork, customize, and deploy. Plug any source: GitHub repos, YouTube transcripts, documents (e.g., markdown files), or custom APIs. Ship it as a web chat app, a GitHub bot, a Discord bot, or all three at once. The template is built on Vercel Sandbox, AI SDK, and Chat SDK. Deploy to Vercel in a single click, configure your sources, and start answering questions. File-based search with Vercel Sandbox No vector database. No chunking pipeline. No embedding model. Your agent uses grep, find, and cat inside of isolated Vercel Sandboxes. Here's how it works: You add sources through the admin interface, and they're stored in Postgres Content syncs to a snapshot repository via Vercel Workflow When the agent needs to search, a Vercel Sandbox loads the snapshot The agent's bash and bash_batch tools execute file-system commands Th ## Using coding agents as modular components in developer tools DevFeed: [Using coding agents as modular components in developer tools]() Original publisher: [Read original article]() Author: Leonidas Partsas Published: 2026-03-18T17:51:32Z Content type: opinion Language: en Sources: [le0nidas]() Topics: [coding](), [Tooling](), [Terminal](), [Git](), [Bash]() Tags: [agent](), [ai](), [bash](), [beads](), [coding](), [git](), [good-practices](), [open-code](), [opencode](), [productivity](), [thoughts](), [workflow]() ### AI overview The article argues that coding agents should be embedded as focused components within developer tools rather than treated as monolithic tools. It illustrates the approach by decomposing an OpenCode-based commit workflow into Bash scripts and a custom agent, following single-responsibility and composability principles. ### Source excerpt Or to be more exact, use a coding agent in a tool. This is my new starting point every time I begin to think of a tool I want to implement. Being part of the pipeline A couple of weeks ago I thought of creating an OpenCode agent that will check my uncommitted changes, construct ... Continue reading Use AI _in_ a tool not _as_ a tool -> ## Introducing the Vercel plugin for coding agents DevFeed: [Introducing the Vercel plugin for coding agents]() Original publisher: [Read original article]() Author: Andrew Qu Published: 2026-03-17T13:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Bots]() Tags: [agents](), [bash](), [claude-code](), [codex](), [coding](), [cursor](), [deployment](), [knowledge-graph](), [next-js](), [retrieval](), [skills](), [tooling](), [validation](), [vercel]() ### AI overview Vercel announces a plugin for Claude Code and Cursor that injects project and platform knowledge into coding-agent context. It provides skills, specialist agents, slash commands, context management, and real-time validation. ### Source excerpt Claude Code and Cursor can now further understand Vercel projects using the new Vercel plugin and a full platform knowledge graph. The plugin observes real-time activity, including file edits and terminal commands, to dynamically inject Vercel knowledge into the agent's context. Key capabilities include: Platform knowledge: Access 47+ skills covering the Vercel platform, including Next.js, AI SDK, Turborepo, Vercel Functions, and Routing Middleware, powered by a relational knowledge graph Specialized tooling: Use three specialist agents (AI Architect, Deployment Expert, Performance Optimizer) and five slash commands (/bootstrap, /deploy, /env, /status, /marketplace) Context management: An injection engine and project profiler rank, deduplicate, and budget-control loaded context Code validation: PostToolUse validation catches deprecated patterns, sunset packages, and stale APIs in real time Instead of standard retrieval, the plugin compiles pattern matchers at build time and runs a priority-ranked injection pipeline across seven lifecycle hooks. Skills fire when glob patterns, bash regexes, import statements, or prompt signals match, and are then deduplicated across the session to ensure accurate agent responses. The plugin currently supports Claude Code and Cursor, with OpenAI Codex support coming soon. Install the plugin via npx: Directly in Claude Code via the official marketplace: Or directly in Cursor: Explore the source code in the Vercel plugin repository. Read more ## Prek, a pre-commit alternative DevFeed: [Prek, a pre-commit alternative]() Original publisher: [Read original article]() Author: Tom Published: 2026-02-27T00:00:00Z Content type: tutorial Language: en Sources: [Tomasz Gągor]() Topics: [pre-commit](), [Rust]() Tags: [bash](), [best-practices](), [ci-cd](), [compatibility](), [developer-tools](), [execution](), [git-hooks](), [linux](), [macos](), [performance](), [pre-commit](), [prek](), [projects](), [rust](), [script](), [speed]() ### AI overview The article describes switching from pre-commit to Prek, a Rust-based drop-in alternative that preserves configuration compatibility while providing faster hook execution. It also presents a script for converting multiple repositories. ### Source excerpt Prek is a Rust-based pre-commit alternative that maintains full config compatibility while delivering significantly faster hook execution. ## Your AI Agent Can Now Deploy to Laravel Cloud (and Write This Blog) DevFeed: [Your AI Agent Can Now Deploy to Laravel Cloud (and Write This Blog)]() Original publisher: [Read original article]() Author: Laravel Team Published: 2026-02-23T16:18:57Z Content type: article Language: en Sources: [Laravel Blog]() Topics: [AI Bots]() Tags: [agent-skills](), [ai](), [ai-agent](), [api](), [bash](), [cli](), [cloud](), [cloud-infrastructure](), [deployment](), [infrastructure](), [laravel](), [openclaw](), [rest-api]() ### AI overview Laravel Cloud's early-access API is wrapped by an OpenClaw skill that lets an AI agent manage cloud infrastructure conversationally, including deployments and other Cloud resources. ### Source excerpt Laravel Cloud's API lets AI agents deploy, scale, and manage infrastructure through conversation. See how Florian built a working OpenClaw skill in a few hours. [Next page]()