name
# Lint / format / typecheck
make lint # ruff
make format # ruff --fix + black + prettier (frontend)
make typecheck # mypy --strict src
# Full pre-commit gate
make pre-commit # format + lint + typecheck + docs
root §"Per-template gates") **and** is copied into scaffolded projects. It drives the real `frontend/` against a real backend — it does **not** replace the backends' own integration tests.
## Stack
- **Framework
nextjs — React / Next.js frontend (projx template)
> Stack-scoped notes. The root [`../CLAUDE.md`](../CLAUDE.md) carries cross-cutting standards — read both, they compose.
>
> This directory is a **projx template**: a working
frontend — React / Vite frontend (projx template)
> Stack-scoped notes. The root [`../CLAUDE.md`](../CLAUDE.md) carries cross-cutting standards — read both, they compose.
>
> This directory is a **projx template**: a working
ClawSync is an open source AI agent platform built with React 18 + TypeScript + Vite (frontend) and Convex (backend). The agent uses @convex-dev/agent for thread management, tool calling
What tela is
A self-hostable, markdown-native team wiki: Go + PostgreSQL backend, React/TS frontend with a Milkdown editor, live Yjs collaboration, and a TypeScript MCP server so agents
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.