AIAny
AI Coding2026
Icon for item

hunk

Review-first terminal diff viewer that opens changesets in an interactive TUI with multi-file review stream, sidebar navigation, and inline AI/agent annotations. Supports split/stack responsive layouts, watch mode, and Git/Jujutsu pager integration.

Introduction

Most terminal diff tools show raw patches; that forces reviewers to mentally stitch context and agent comments across files. Hunk treats the changeset as a review session first — surfacing a navigable multi-file stream, inline AI/agent notes, and live layouts so reviewers (and agent workflows) stay in context instead of bouncing between editors and terminals.

What Sets It Apart
  • Review-first interactive TUI: Opens diffs as a navigable review stream (sidebar, file list, keyboard/mouse controls) rather than plain patch text, so reviewers can focus on intent and flow across files.
  • Inline AI / agent annotations: Renders agent- and AI-produced notes beside code lines and supports a skill-based agent workflow, enabling live agent interaction with the same review session — useful when patches are agent-authored or when an assistant provides explanatory comments.
  • Flexible presentation and workflow integration: Responsive split/stack layouts, pager-compatible mode, and watch mode for auto-reloading. Detects Git and Jujutsu worktrees and can be used as a Git pager to fit into existing dev workflows.
Who It's For & Tradeoffs

Great fit if you review multi-file changes frequently and want an integrated terminal-first workflow that includes agent annotations (developers using agent-assisted coding, maintainers validating agent-generated patches, or teams that want a compact TUI review loop). Look elsewhere if you need structural AST-aware diffs (Hunk focuses on human/agent review UX rather than structural transformation analysis), a GUI-based reviewer, or if you require server-hosted web reviews — Hunk is terminal-native and depends on Node.js 18+ and a capable terminal environment. Note also that inline AI/agent usefulness depends on the quality and tooling of the connected agents/LLMs.

Information

  • Websitegithub.com
  • Authorsmodem-dev
  • Published date2026/03/17

More Items

Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).