Agentic Coding
Agentic coding uses AI agents to plan and carry out software development tasks, such as exploring a codebase, editing files, running tests, and revising changes. It can reduce manual effort on multi-step work and help coordinate coding activities, while leaving people responsible for reviewing decisions and results. These systems vary in how much autonomy they allow and how they interact with developers and development environments.
Open source tools in this area include coding agents, workflow orchestrators, project-context systems, and utilities for testing or coordinating multiple agents. When choosing one, consider its license, maintenance activity, model and runtime requirements, supported languages, integrations, and safeguards for reviewing or limiting changes. Agentic coding can be useful to individual developers, teams, and researchers exploring AI-assisted software workflows, especially when the tools fit existing practices and their output can be checked.
3 repositories · updated September 27, 2026
Spec Kitty: Spec-Driven Development for AI Coding Agents and Software Factories
Spec Kitty is an open-source CLI that enables spec-driven development for AI coding agents and multi-agent workflows. It transforms product intent into a structured, repo-native AI coding workflow, providing isolated git worktrees and a clear lifecycle for development tasks. This tool helps teams build governed software factories, ensuring visibility and traceability in AI-assisted software development.
AIWG: Reusable Context & Workflows for AI-Augmented Development
AIWG is a cognitive architecture designed to enhance AI-augmented software development. It provides reusable project context and specialist workflows, enabling structured development, review, and operational tasks across various AI tools and platforms.
claude-code-codex-bridge: Sync Your Claude Code Setup with Codex
The `claude-code-codex-bridge` is a Python tool that automatically synchronizes your Claude Code setup, including plugins, skills, agents, and commands, with Codex. This one-way bridge ensures that any changes made in Claude Code are reflected in Codex, keeping both environments equally effective. It streamlines the management of AI coding tools by allowing you to configure once and deploy across both platforms.