🛠️ AI Workspace
Manage shared AI agent skills, configs, and automation across multi-repo workspaces. Works with Cursor, Claude Code, Codex, Amp, and 40+ AI coding tools.
External Links
Achievements
Enterprise Adoption
Adopted by multiple enterprise companies in the UK to standardize AI agent configurations across their engineering teams.
𝗦𝗶𝘁𝘂𝗮𝘁𝗶𝗼𝗻
AI agents only see the repo they run in. An agent working in a frontend repo has no visibility into the backend, API contracts, or shared conventions — so it assumes and hallucinates. Each developer configures AI tools differently, so skills, instructions, and rules drift between projects and team members.
𝗧𝗮𝘀𝗸
Build a tool that acts as a canonical source for AI agent configurations, enabling teams to share skills, rules, and instructions across multiple repos and AI coding tools from a single workspace.
𝗔𝗰𝘁𝗶𝗼𝗻
Created a workspace repo pattern where running npm install mirrors configs to the parent root, symlinks skills for every AI tool, and installs git hooks to keep everything in sync.
Implemented a knowledge hierarchy with nearest-wins semantics — workspace-wide instructions, skills, and rules can be overridden at the per-project level.
Built a skill management CLI supporting add, remove, create, list, find, update, and check commands with lockfile tracking for reproducible setups.
Designed a generic config sync system that walks root-config/ and mirrors new config types (Cursor rules, Claude settings, Codex config) automatically with no script changes.
Added an upgrade mechanism using a dual-remote git setup (origin for the team, upstream for the template) so teams can pull the latest scripts without touching their customizations.
𝗥𝗲𝘀𝘂𝗹𝘁
AI Workspace provides a single source of truth for AI agent configurations across multi-repo workspaces, eliminating configuration drift and giving agents the cross-repo context they need to produce accurate results.