Agents UI
Posts tagged “ai-coding”
32 articles on ai-coding. Back to all posts.
MCP Server Not Connecting? A Practical Debugging Guide
Debug MCP connection failures with a step-by-step workflow for server startup, stdio output, HTTP endpoints, authentication, and tools missing from your agent.
Claude Code Context Window: How to Reduce Token Usage
Diagnose Claude Code context usage, choose between compact and clear, and reduce wasted tokens with focused prompts, smaller tool output, and useful handoffs.
Git Bisect Tutorial: Find Regressions with AI Coding Agents
Find the commit that introduced a bug with git bisect. Includes an automated Python probe, exit-code handling, worktree isolation, and a focused AI agent workflow.
Agent UI Design for Enterprise AI: How to Make Agents Actually Work
A practical guide to designing enterprise agent UIs that earn trust: scoped autonomy, visible plans, approvals, audit trails, context, orchestration, and measurable outcomes.
The AI Coding Agent Runbook: A Practical Checklist for Reliable Changes
A copy-paste runbook for using AI coding agents on real codebases: scope the task, protect the repo, define checks, review the diff, and hand off cleanly.
Agentic Coding: A Developer's Guide to Working with Autonomous AI Agents
What agentic coding actually means in 2026, how it differs from AI autocomplete, and the practical workflow patterns that make autonomous coding agents productive instead of chaotic.
Claude Code Hooks: A Practical Guide to Automating AI Agent Workflows
Claude Code hooks let you run shell commands automatically at key points in the agent loop — before tools run, after edits, when sessions end. A working developer's guide with real configurations.
Best MCP Servers for Developers in 2026: A Curated Guide
A practical roundup of the most useful Model Context Protocol servers for developers — filesystem, git, database, browser, and terminal MCP servers that actually earn their place in a coding agent setup.
Using AI Coding Agents on Large Codebases: Monorepos, Microservices, and Scale
Practical strategies for using AI coding agents effectively on large codebases — from scoping context and navigating monorepos to coordinating changes across microservices.
Automate Terminal Workflows with Python: The Agents UI SDK
How to use the open-source Agents UI Python SDK to script terminal sessions, automate deployments, and orchestrate AI agents programmatically.
Refactoring Legacy Code with AI Coding Agents: A Practical Approach
How to use AI coding agents to refactor, migrate, and modernize legacy codebases safely — from scoping the work to verifying changes at scale.
Cursor vs Claude Code vs Aider: IDE vs Terminal AI Coding Compared
A practical comparison of IDE-based and terminal-based AI coding tools — Cursor, Claude Code, and Aider — covering workflows, strengths, and when to use each.
Model Context Protocol for Developers: A Practical Guide
What MCP is, why AI coding agents use it, and how developers can design practical tool surfaces for files, terminals, projects, and remote workflows.
AI Agent Handoffs: How to Preserve Context Between Sessions
A practical system for handing work from one AI coding session to another without re-explaining the codebase, losing state, or repeating mistakes.
Test-First Workflows for AI Coding Agents
How to use failing tests, tight scopes, and small verification loops to make AI coding agents produce more reliable changes.
Reviewing AI-Generated Code: A Developer's Checklist
A systematic approach to reviewing code written by AI coding agents, with checklists and patterns for catching common issues before they reach production.
How to Configure AI Coding Agents with Project-Level Instructions
A practical guide to CLAUDE.md, .cursorrules, .aider.conf.yml, and other project-level configuration files that make AI coding agents work better with your codebase.
Git Worktrees for AI Agent Development: Parallel Workflows Without Conflicts
Learn how to use git worktrees to run multiple AI coding agents on the same repository without merge conflicts or context contamination.
Debugging with AI Coding Agents: A Practical Workflow
How to use AI coding agents like Claude Code and Aider to debug effectively — from reproducing issues and isolating root causes to fixing bugs without introducing new ones.
Prompt Engineering for AI Coding Agents: What Actually Works
Practical prompt patterns that get better results from AI coding agents like Claude Code, Codex, and Aider — from scoping constraints to incremental task decomposition.
Warp Terminal Alternatives in 2026: What Developers Are Switching To
Looking for a Warp terminal alternative? We compare iTerm2, Kitty, Alacritty, Ghostty, and Agents UI — covering privacy, performance, AI agent support, and why developers are moving away from Warp.
Remote GPU Server Workflow: Running AI Agents with SSH and Port Forwarding
A complete guide to setting up a productive remote GPU development workflow — SSH configuration, port forwarding, file sync, and running AI coding agents on powerful remote hardware.
Running Local LLMs with Ollama: A Developer's Guide
A practical guide to running large language models locally with Ollama — covering installation, model management, the REST API, custom Modelfiles, and integrating local LLMs into development workflows.
Managing Multiple AI Agent Sessions Without Losing Your Mind
Practical strategies for organizing multiple AI coding agent sessions — from terminal layouts and naming conventions to context isolation and project-based workflows.
How to Fine-Tune an LLM with QLoRA: A Practical Guide
A step-by-step guide to fine-tuning large language models using QLoRA — covering dataset preparation, LoRA configuration, training with SFTTrainer, and merging adapters for deployment.
Open Source AI Developer Tools Worth Using in 2026
A curated list of the best open-source AI developer tools in 2026 — from coding agents and code review to testing, documentation, and terminal workflows.
Solo Developer Workflow: AI Agents + SSH + One Terminal
How solo developers and indie hackers can use AI coding agents, SSH workflows, and project-based terminal organization to ship like a small team.
How to Deploy an LLM with vLLM: A Production-Ready Guide
A hands-on guide to deploying large language models with vLLM — covering installation, offline inference, OpenAI-compatible API serving, GPU memory tuning, quantization, and Docker deployment.
Agents UI vs Warp vs iTerm2: Which Terminal for AI-First Development?
A detailed comparison of three macOS terminals for developers running AI coding agents — covering multi-session support, SSH workflows, persistence, and architecture.
The Multi-Agent Future: Why Developers Will Run 3+ AI Coding Agents
AI coding agents are specializing fast. Here's why running multiple agents in parallel is becoming the default developer workflow — and what that means for tooling.
How to Run Claude Code and Codex Side by Side
Step-by-step guide to running multiple AI coding agents in parallel terminal sessions for faster development workflows.
Best Terminal for AI Coding Agents in 2026
A practical comparison of terminal apps for running AI coding agents like Claude Code, Codex CLI, and Gemini CLI — from iTerm2 to Warp to Agents UI.
Try Agents UI
A native terminal for AI coding agents with persistent sessions, SSH workflows, and built-in editing.