Roadmap

The CLI now includes interactive setup and skill flows, install and lint commands, memory updates, and stronger terminal output patterns. We are still expanding workflow coverage and polishing command ergonomics to reduce friction in day-to-day use.

Memory management is underway. AI DevKit already supports storing, searching, and updating memory entries, and the next step is expanding that into easier browse, merge, and delete workflows so your knowledge base stays clean as projects evolve.

Agent management is now available through the CLI: you can detect running agents, list them, inspect details, focus their terminals, and send input to supported tools such as Claude Code and Codex. Broader orchestration features, richer cross-agent controls, and a more unified management surface are still in progress.

Streamline your workflow by automatically configuring agent-specific hooks, such as those for Claude Code or Cursor. This feature will enable you to define chain reactions, like automatically asking for code review immediately after an implementation step is completed, ensuring quality checks happen without you needing to remember to run them manually.

Trust that your AI is remembering the right things. This feature will introduce a testing framework for your memory bank, allowing you to define "retrieval tests" that verify whether the correct coding standards and documentation are being prioritized when your AI agent searches for context.

Reduce costs and stay within token limits without losing context. Context Compaction will implement intelligent summarization algorithms and "context packaging" to compress large documentation or conversation histories into concise, token-efficient formats that can be easily passed to new agents or threads.

Launch a static website with landing page, comprehensive documentation, project vision, and development roadmap.

AI DevKit now supports a broad set of coding agents and environments, including Cursor, Claude Code, GitHub Copilot, Gemini CLI, Codex, OpenCode, and Antigravity, with additional environments still being tested. The goal remains the same: make AI DevKit the universal bridge between your preferred AI assistants and your development workflow.

Build a local AI memory that learns from your coding habits, preferences, and team knowledge. This feature allows AI agents to access your skills, patterns, and project context directly from local, minimizing redundant prompts, speeding up workflows, and keeping your documents lightweight and focused.

Stop copy-pasting prompts and scripts between projects. Skill Management will provide a centralized registry to version, install, and share your custom AI capabilities (like specific refactoring workflows or testing patterns) across all your projects and teams with a single command.