discovery, observability, and governance — a
multi-module project with a Java backend, a React/TypeScript frontend, a Python ingestion framework,
and Docker infrastructure.
## Stack at a glance
- **Backend**: Java 21 + Dropwizard
zilliz/claude-context-core`) — the indexing engine. All real logic lives here; the other packages are thin frontends over it.
- `packages/mcp` (`@zilliz/claude-context-mcp`) — stdio MCP server, the primary product. ESM (`"type": "module"`).
- `packages/vscode-extension` (`semanticcodesearch
agent-orchestrator** — do **not** re-flag old design-reference mismatches.
When showing or demoing frontend changes, run `ao preview [url]` from inside the
session so the change renders
integration / end-to-end cases under `tests/` |
The main repo has no frontend stack, so no `frontend-dev` is provided; TypeScript sub-projects under `apps/` use their own AI configuration
project is a web-based NGINX management interface built with Go backend and Vue.js frontend.
## Package Manager
- **Use Bun exclusively** for all frontend package management operations
- Commands: `bun install
/.config/dev.humanlayer.wui/logs/`
Logs include output from the WUI backend, daemon stderr (prefixed with [Daemon]), and frontend console logs (prefixed with [Console]). The log files automatically rotate at 50MB. The application
byte-identical. Assets are served from `/pkg/assets/…` (**not** `/assets/`, which belongs to the hub frontend) and staged into the bundle by `tools/stage-web-assets.sh`, which `check-wasm-bundle.sh` runs as step 4 and both
ports are `StoragePort` and `DeliveryPort`
(`modules/payments-v2/ports.ts`) — independent, swappable, contract-test-enforced
(`tests/unit/payments-v2/contracts/`); the Sphere frontend is a **view** — no provider-specific
logic outside implementations; custody (`intoInventory`) is a composition-time
agent AI system acting as a virtual corporate executive. Python backend (FastAPI) + Next.js 15 frontend. The "Executive" is a single coherent persona backed by 8 specialist sub-agents, all powered
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.