vhk
★ 12
vs
gentle-ai
★ 7.9k
vhk vs gentle-ai
vhk: VHK is a full-cycle AI coding harness designed to maintain stability regardless of the AI model or agent used. It wraps existing agents, providing persistent rules, context, and verification gates to streamline the development workflow and adapt to individual developer needs.; gentle-ai: Gentle-AI configures your existing AI coding agents with persistent memory, a planning workflow, and a curated skill library, transforming them into a robust engineering environment. It ensures consistent agent behavior across runtimes and machines, enabling verifiable output instead of just agent summaries.
01
TL;DR
vhkCode Assistant · ★ 12
Standardizing rules and guidelines across multiple AI coding agents within a project.
gentle-aiCode Assistant · ★ 7.9k
When to choose:
- You want to add persistent memory, skills, a planning workflow and MCP servers to an agent you already run.
- You want to pick components one by one or use presets.
- You want a deny list for ~/.ssh, .env and credential files.
When to skip:
- Your agent does not support sub-agents: the README says some capabilities differ by runtime.
- You only want one piece such as memory and prefer a single focused tool.
- You do not want stylistic extras such as personas and themes in your setup.
02
Side-by-Side Comparison
Field
vhkgentle-aiCategory
Code Assistant
Code Assistant
Stars
★ 12
★ 7.9k
License
MIT
MIT
Install Command
npm install -g @byh3071/vhk
curl -fsSL https://raw.githubusercontent.com/Gentleman-Programming/gentle-ai/main/scripts/install.sh | bash
Updated
2d ago
1d ago
Open Source
Yes
Yes
Tags
AI Coding Harness, Developer Tooling, CLI
AI Agent Configuration, Workflow Automation, Developer Tools
03
Features
vhk01Rule Portability: Synchronizes a single `RULES.md` to various AI agent rule files (e.g., Cursor, Claude, Copilot).
02Context & Session Persistence: Maintains session context and project brief through `.vhk/context.md` for seamless continuity.
03Evidence-Based Verification: Implements various gates like `verify`, `review`, and `receipt` to confirm completion with tangible evidence.
04Self-Evolving Rules: Accumulates lessons, patterns, and rule candidates from sessions in `.vhk/memory.json` to adapt and improve.
05Goal & Hard Stop Management: Defines and manages development goals, enforcing a `HARD_STOP` on repeated blockers.
gentle-ai01Persistent memory across sessions (Engram™).
02Spec-Driven Development (SDD) planning workflow.
03Curated library of coding skills for agents.
04Evidence-based code review with Receipt-Driven Development (RDD).
04
Use Cases
vhk↳Standardizing rules and guidelines across multiple AI coding agents within a project.
↳Ensuring continuity and consistent context for AI-assisted coding sessions, even after interruptions.
↳Automating verification and hostile code review processes with clear, machine-generated evidence.
↳Managing and progressing through development goals systematically, with built-in checks and balances.
↳Allowing AI coding agents to learn and adapt to project-specific patterns and developer preferences over time.
gentle-ai↳Developers who already use an AI coding agent daily and want it to stop starting from zero.
↳Teams that want consistent agent behavior across different agent runtimes and machines.
↳Anyone who wants to verify what an agent did instead of trusting its summary.
05
Best For
vhk—
gentle-aiEssentialTrending
FAQ
FAQ
What is the difference between vhk and gentle-ai?
Both vhk and gentle-ai are in the Code Assistant category. vhk has 12 stars, while gentle-ai has 7.9k stars.
Which is better, vhk or gentle-ai?
The best choice depends on your use case. Choose vhk if Standardizing rules and guidelines across multiple AI coding agents within a project., and gentle-ai if Developers who already use an AI coding agent daily and want it to stop starting from zero..
Is vhk free or open source?
Yes, vhk is open source on GitHub (MIT).
Is gentle-ai free or open source?
Yes, gentle-ai is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→