#ai

Agent Shelf

yoclo

Manage reusable agent resources across projects.

Trumbo

trumbo

Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.

norrin — inline review for Claude Code

norrin

Cursor-style red/green review of every Claude Code edit, in your real files. Accept or reject per change; Claude never waits.

AskFirst

EKhurgin

Refines your AI prompts by asking clarifying questions first, then rewriting the prompt. Runs locally via Ollama.

mindset-ctx

mindset-ctx

Generate and keep AI context files (CLAUDE.md, AGENTS.md, architecture docs) fresh, and wire the MCP server into Claude Code / Cursor, without leaving the editor.

Grasp — Explain AI Code Changes

GraspbyAlex

Understand AI-written and existing code in plain language. Hover a changed line (or select any code) for a beginner-friendly explanation, right inside the editor.

H1VE

h1ve

See your current branch's feature state — stage, blockers, sign-offs, spec — from H1VE, the governance & memory layer for teams building with AI.

Knot AI

freshgoldfish

Zero-config, fully local AI coding assistant for VS Code. Autocomplete, chat, and codebase search powered by Ollama. Nothing ever leaves your machine.

Derba

krave

Explicit, checkbox-driven context for AI chat — you choose what the model sees

Sufficit Symposium

sufficit

Symposium (συμπόσιον) — host and conduct dialogue sessions with multiple AI agents (Claude Code, Codex CLI, GitHub Copilot CLI) side by side inside VS Code.

CodeMore

CodeMore

The static analyzer your AI agent reads — finds production-blocking bugs in vibe-coded apps (CLI, GitHub Action, MCP server).

Tracks lines of code added/removed by AI (Kiro/Copilot) vs Human across sessions. Provides GitLab-like file change history and contribution percentages.