| AGENTS.md - the new standard filename across LLM code tooling providers for agent guidanceagents.md | Open Standard / Open standard specification with documentation and examples / Free and open source | It seems that the main LLM coding AI inference and tooling providers have finally come together to make a standard filename for repositories. As of this writing, I've seen as… |
|---|
| memdoor/examples/workflows/team-solve at main · guregodevo/memdoorgithub.com | AI Agent Workflow / open-source code repository / open source on GitHub | Five roles (planner, two ideators, solver, manager, repair worker) communicate only through files on disk, not through model-to-model calls |
|---|
| GitHub - feimacode/open-design-agent-kit: Pro-grade UI design built into the coding agent you already use — GitHub Copilot Chat, Claude Code, Codex, Cursor. 270+ design skills, 150+ brand design systems, 160+ remixable examples. No desktop app, no daemon, no API keys — just files in your repo.github.com | Developer Tool / open-source toolkit / GitHub repository / open source, free via npx, VS Code extension, or MCP server | Integrates natively into each agent's own mechanism (VS Code languageModelTools, Claude Code plugins, MCP server) rather than wrapping a separate UI |
|---|
| GitHub - cloudflare/security-audit-skill: A coding-agent skill for multi-phase security audits with independently verified, machine-readable findingsgithub.com | Security Automation Tool / open-source GitHub repository / open source on GitHub | Orchestrates six distinct audit phases using isolated sub-agents to prevent context contamination between stages |
|---|
| GitHub - reflection-oss/mirror: Mirror is Reflection’s coding harnessgithub.com | AI Coding Agent / open-source CLI tool / open source, free to install via uv or build from source | Terminal-based coding agent that operates directly in your project directory |
|---|
| GitHub - kenn-io/agentsview: Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.github.com | Developer Tool / open-source CLI tool with web UI / open source, free, single binary install | Supports 20+ AI coding agents including Claude Code, Codex, and Devin CLI with unified session search and analytics |
|---|
| GitHub - parthh01/sphinx: Outsource your thinking, not your understanding. A comprehension checkpoint for agent-assisted development.github.com | Developer Tool / open-source CLI tool / open source, requires external LLM API account | Blocks pushes to configured branches until the user passes scenario-based comprehension questions about the committed change |
|---|
| Sphinx — outsource your thinking, not your understandingsphinx-six-theta.vercel.app | Developer Tool / open-source CLI tool with landing page / free, open source, npm install | Intercepts git push and asks scenario-based questions about the diff's failure modes before allowing the push to proceed |
|---|
| wuyoscar/jev-skill: An awesome collection of Jev use cases, workflows, and agent skills.github.com | AI Agent Skills Repository / curated repository with demos, skills, and examples / open source on GitHub | Jev acts as a decision layer that classifies and scores options while coding agents handle evidence gathering and execution |
|---|
| GitHub - getsentry/toolkit: Agentic tooling for Sentrygithub.com | Developer Tool / open source repository with hosted service / open source on GitHub; hosted service at mcp.sentry.dev; stdio via npx | Remote MCP middleware between coding assistants and Sentry API, optimized for debugging workflows |
|---|
| SwiftUI Agent Skill - Write better code with Claude, Codex, and other AI toolshackingwithswift.com | AI Coding Tool / long-form article / free and open source | Open-source agent skill that improves AI-generated SwiftUI code by fixing deprecated APIs, performance issues, and accessibility gaps |
|---|
| Pi Durable | Earendilearendil.com | AI Agent Framework / Long-form blog post / Open source package | Ships alongside Pi 1.0 as an experimental package, not a replacement for the Pi coding agent |
|---|
| GitHub - dzhng/jevgrep: Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.github.com | Developer CLI Tool / open-source CLI tool with documentation / open source, MIT licensed, npm install | Uses Jev to judge relevance across folders, files, and declarations, returning verbatim source excerpts and reading leads in one stdout response |
|---|
| GitHub - 1jehuang/jcode: The most RAM efficient harnessgithub.com | AI Coding Agent / open-source software with documentation / open source, free to install via curl or PowerShell | Uses 27.8 MB PSS per session with local embedding off, compared to 386.6 MB for Claude Code and 371.5 MB for OpenCode |
|---|
| GitHub - superagents-lab/xcode27-skills: Apple’s official Agent Skills exported from Xcode 27 — SwiftUI, UIKit modernization, Swift Testing, C bounds-safety, and security hardening for AI coding agents.github.com | AI Agent Skills Repository / open-source repository / free online, open source | Seven self-contained skills covering SwiftUI, UIKit modernization, Swift Testing, C bounds-safety, security auditing, and device verification |
|---|
