AgentSmith
Verification framework for AI coding agents with project rules and proof
Visit agentsmith.diy ↗What is AgentSmith?
AgentSmith is an open-source, local-first framework that adds structure and accountability to AI-assisted development. It gives coding agents project rules, automated quality checks, and a verifiable handoff process, ensuring work is proven before completion. Designed for developers using Claude Code, Codex, and other AI agents, it captures evidence of what passed, what failed, and what actually ran.
The tool operates through bounded work loops: agents receive clear boundaries and checks, run their tasks, pass automated verification phases, and leave recorded evidence and resumable state. AgentSmith supports multiple agent clients through a registry, with native configuration for Claude Code and Codex, and adapters for GitHub Copilot, Cursor, Cline, and others.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered AgentSmith automatically. Evidence: GitHub PromptPartner/agentsmith; repo has AGENTS.md. View source.
Similar vibe-coded apps
Turn your codebase into a queryable knowledge graph for AI coding assistants
Operating layer for AI coding agents with skills, memory, planning and security
Self-hosted AI agent with persistent memory and multi-platform messaging
Open-source AI platform for short-form video and animated series creation
Open-source canvas workbench for AI-powered image and video creation
Community marketplace for DeepSeek Harness Web themes, pets, plugins
Open-source, AI-native knowledge base with Evernote-style interface