Articles tagged "AI Agents"

Prime Agent treats context as a variable and sub-agents as function calls via its Recursive Language Model design, paired with a Continual Harness you can CRUD-edit. Here's how Prime Intellect's MIT-licensed coding agent actually works. Updated Aug 2026.

Updated August 2026. Zed Delta is a multiplayer environment for coding with agents and reviewing what they build in real time. Here's how DeltaDB works, how it connects to Claude Code, how it relates to git, and how it compares to existing tools.

**[Herdr](https://herdr.dev/) is a terminal-based AI agent multiplexer** — run multiple AI coding agents ([Claude Code](https://claude.com/product/claude-code) / OpenCode / Codex, etc.) in parallel from **a single terminal**, with sessions **persisted server-side** (like tmux) so you can reattach from any device. **Key features**: (1) **multi-agent orchestration** — run multiple agents in independent panes, (2) **persistent sessions** — agents keep running after terminal detach, reattach from anywhere, (3) **SSH-friendly remote access** — like tmux but agent-aware, (4) **real terminal panes** — clickable layouts and mouse support, (5) **at-a-glance agent state** (blocked / working / done / idle), (6) a **Control API** (CLI + JSON socket) for programmatic session management, (7) a **mobile-friendly UI** for terminal access from phones and tablets. Ships as a **Rust binary** (not Electron) with no external dependencies. Target audience: **engineers at JetBrains / Docker / Vercel / Google / NVIDIA / AWS**. Position: paired with [Crit.md's HITL review substrate](../columns/crit-md-local-first-agent-review-2026-07), Herdr is the **"agent-operations infrastructure"** side of the coin — solving the execution environment rather than the review loop. Part of the broader "day-to-day AI-agent tooling" trend alongside our [Cloudflare-only stack](../columns/cloudflare-only-stack-viral-2026-07) and [Claude Cowork web/mobile](../columns/claude-cowork-web-mobile-launch-2026-07) coverage.

**[Hunk](https://www.hunk.dev/) is a terminal-based diff viewer purpose-built for code review and AI-agent integration** — a replacement for stock `git diff`, with review-experience as a first-class design goal. **Key features**: (1) **multi-file review sidebar** — see the whole changeset, navigate files, view change counts, (2) **inline AI annotations** — reasoning from AI agents ([Claude Code](https://claude.com/product/claude-code), [Cursor](../columns/cursor-ios-supports-2026-07-01), etc.) shows adjacent to the relevant code, (3) **adaptive layout** — split / stacked / auto-responsive views auto-adjust to terminal width, (4) **watch mode** — auto-refreshes as the working tree changes, (5) **syntax highlighting + themes** — Graphite / Midnight / Ember / Zenburn / Catppuccin, (6) multiple input methods — **keyboard, mouse, pager integration**. **CLI commands**: `hunk diff` (uncommitted changes) and `hunk show` (a commit). **Tech stack**: Node.js 18+, **MIT license**, distributed via **npm / Homebrew / Nix**. Position: the terminal counterpart to [Crit.md's browser PR-review experience](../columns/crit-md-local-first-agent-review-2026-07); alongside [Herdr (parallel agent operations)](../columns/herdr-terminal-agent-multiplexer-2026-07), it's part of the same "terminal-native AI-agent era" trend. **Target users**: developers doing code reviews, teams integrating AI tools into dev workflows, and terminal-first engineers.

A primary-source deep dive on **Loop Engineering**, the June 2026 AI-engineering trend named and codified by Google Chrome DevRel lead **Addy Osmani** in his ["Loop Engineering" blog post](https://addyosmani.com/blog/loop-engineering/) and elevated to industry attention by Anthropic Claude Code lead **Boris Cherny's** quote — **"I don it prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops."** ([reported by The New Stack](https://thenewstack.io/loop-engineering/)). Covers the four-generation lineage: Prompt Engineering (2022-2024) → Context Engineering (2025, coined by Shopify CEO Tobi Lütke, formalized in [Anthropic's Effective Context Engineering for AI Agents](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)) → Harness Engineering (early 2026) → **Loop Engineering (June 2026 onwards)**. Grounded in Peter Steinberger's seed phrase — **"you should be designing loops that prompt your agents"** — the column maps out the six building blocks: (1) Automations / Trigger (timer- or event-driven heartbeats), (2) Worktrees (isolated git checkouts to prevent parallel sub-agent collisions), (3) Skills (SKILL.md / CLAUDE.md to externalize intent and reduce "intent debt"), (4) Plugins / Connectors via MCP (execution permissions), (5) Maker / Checker Sub-agents (separating generation from verification), and (6) Durable State (memory belongs on disk, not in context). Explains Inner Loop vs Outer Loop, how Claude Code's `/goal`, Automations, Worktrees, Skills, and Sub-agents constitute a ready-made Loop Engineering toolkit, the surge of Japanese coverage on Qiita / Zenn / DevelopersIO / note / OptiMax, and the five major risk vectors: Cognitive Surrender (Osmani's central warning), Loop Brittleness, Verifier mis-grading, HITL approval fatigue, and runaway-loop cost explosion.