github

A GitHub repository that publishes a week of controlled runs comparing seven Google models on the same software task, with transcripts, telemetry, screenshots, and scored benchmark artifacts.

Open-source tooling for keeping coding-agent work alive across sessions and handoffs. It preserves work state, evidence, and next steps across agents like Codex, Claude, OpenCode, and Amp, with a CLI and local workspace flow.

A repo-improving agent harness that researches a codebase, proposes ideas, waits for human approval, and then drives execution with SHA-bound merge gating.

A Git-based CMS for static site generators, packaged as a pnpm workspace with install, build, test, and demo instructions, plus documentation for usage and configuration.

A Vale style pack that lints prose for AI-like writing, inspired by ASD-STE100. It helps teams catch buzzwords, vague phrasing, self-praise, and other patterns in docs, comments, and agent-authored text.

Local, structured memory for AI coding assistants like Claude Code and Codex. The project stores decisions, constraints, and abandoned approaches in an event-sourced local log and injects them back into later sessions.

A Claude Code plugin and MCP server that keeps a persistent, read-only memory of a repo so agents can ask broad codebase questions without re-reading files every session.

GetSuperpower is a CLI and workflow bundle for coding agents that packages multi-step agent workflows into one installable skill tree.

Aharness is an open-source workflow harness for Codex that turns coding-agent processes into enforced state machines with typed gates, validated evidence, controlled transitions, repair paths, and inspectable logs.

Offload is a developer tool that lets coding agents continue long-running tasks on another machine, with support for Claude Code and Codex. It can move the project state to a remote machine, run work on a new branch, expose remote localhost services, and send status updates while the laptop sleeps or disconnects.

A CLI tool that shares Claude Code sessions across a team by storing transcripts and memory on an orphan Git branch, so teammates can pull, resume, push, and delete sessions without extra infrastructure.

HookGuard is a CLI security scanner for AI coding agent configuration files. It looks for malicious hooks, invisible Unicode, credential exfiltration patterns, and prompt-injection text in files like CLAUDE.md, AGENTS.md, Cursor rules, and GitHub Copilot instructions.

A multi-lens code review pipeline for Claude Code that runs parallel review passes, validation gates, optional Codex review, an auto-fix loop, and interactive walkthroughs for findings.

A hands-on workshop repository that walks developers through building a small GPT-style language model from scratch, including tokenization, transformer blocks, training, and text generation.

A research repo that replays real Claude Code and Mooncake traces to test prefix-cache eviction policies and compare them against LRU.

Loopback MITM proxy for Claude Code on Amazon Bedrock that can sniff, hold, edit, forward, or drop requests. The repo includes prerequisites, a quick start, flags, cost notes, and behavior limits.

Selfship is an AI operations tool for agentic applications that detects recurring failures in live traffic, diagnoses the cause, and opens an eval-backed GitHub pull request for review and merge. It works with any LLM/framework and includes a demo, pricing, docs, and FAQ.

Codexify is a Rust-based local MCP bridge for ChatGPT Web Pro that exposes tools like file access, shell commands, git operations, and project management on your machine. It also supports OpenAI’s native Secure MCP Tunnel and can aggregate other MCP servers.

AgentMachinist is a local-first, issue-to-reviewed-PR build pipeline for solo developers. It connects GitHub issues to supported harnesses like Claude Code, OpenCode, Pi, or Codex, with a human-approved spec step before implementation.

A ProtoLink example that stages autonomous agents in a fictional liability tribunal to study how agent-to-agent communication changes decisions, with replayable traces and HTML reports.

Open-source team skills for bringing shared coding standards, directives, and evals into agentic coding workflows like Claude Code and Codex.

A GitHub repository that turns untrusted source material into compact AI skills using evidence gates, validation steps, and audit output.

A GitHub repository for connecting AI agents to a real iPhone so they can call or text you, using a Claude Code plugin and a standalone agent skill/CLI.

Bookshelf adds book quotes into Claude Code and Codex sessions between turns, with optional ambient delivery, on-demand quote commands, and local privacy-focused behavior.