nocobase
nocobase/nocobase/AGENTS.md
existing code that uses `any`, narrow it to a concrete type whenever feasible. - For frontend components and pages, prefer Ant Design v5 components and follow its conventions. Reference https://ant.design
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
nocobase/nocobase/AGENTS.md
existing code that uses `any`, narrow it to a concrete type whenever feasible. - For frontend components and pages, prefer Ant Design v5 components and follow its conventions. Reference https://ant.design
1Panel-dev/MaxKB/AGENTS.md
agentic workflows, and MCP tool-use. Backend is Python 3.11 / Django 5.2 / LangChain; frontend is Vue 3 / Vite. Data layer is PostgreSQL + pgvector and Redis; Celery for async work
JetBrains/intellij-community/java/AGENTS.md
java-impl` holds the code insight: the completion, the intentions, and the refactorings. - `java-frontend`, `java-backend` and `java-frontback-impl` serve the split mode. Read the `remote-dev-code
kortix-ai/suna/AGENTS.md
complete self-host preview for the branch — its own PostgreSQL, Supabase, API, gateway, frontend, and HTTPS origin. This is how work is shared and reviewed internally. **Sharing never requires merging
pydantic/pydantic-ai/docs/realtime/AGENTS.md
rule lives here), `turns.md`, `tools.md` (tools only), `capabilities.md` (per-hook support story), `history.md`, `deployment.md` (frontend transports), `lifecycle.md` (connection lifecycle only), `observability.md`, `troubleshooting.md` (the symptom-first index — per-page "Edge cases
nukeop/nuclear/AGENTS.md
backend lives in `packages/player/src-tauri/src/`. Modules: - `bridge/` - bidirectional RPC. Lets Rust servers call into the frontend (`Bridge::call` emits a `bridge:request` event, frontend replies via the `bridge_respond` command). - `http
GoogleCloudPlatform/generative-ai/search/gemini-enterprise/ge-demo-generator/AGENTS.md
mixed. Handed a menu of languages, the model sometimes picks one off it. The frontend already knows the intended language — the Template Hub selector, or the research language while research
yusufkaraaslan/Skill_Seekers/AGENTS.md
faiss, qdrant, pinecone. ## Web UI (Seeker HUD) Local web app: React 19 + Vite + Tailwind/shadcn frontend in `ui/`, FastAPI backend in `src/skill_seekers/web/`. ```bash # Run the app (opens browser
siteboon/claudecodeui/AGENTS.md
Apply it only to backend code; do not impose those architecture rules on the frontend. ## Frontend code For every task that creates, modifies, refactors, or reviews frontend code under
Untrivial-ai/agent-orchestrator/AGENTS.md
loopback HTTP daemon, services, SQLite storage, lifecycle/reaper, runtime/workspace/agent/tracker adapters, terminal mux, and tests. - `frontend/` — Electron + React supervisor wired to the daemon via the generated typed client. Treat
cocoindex-io/cocoindex/examples/AGENTS.md
port 8000`; it runs the CocoIndex app in live mode, then start the frontend from `frontend/`. - `csv_to_kafka`, `kafka_to_lancedb`: `cocoindex update -L main.py` - `rust/ `: follow that example
google/adk-recipes/core/python/ambient-expense-agent/AGENTS.md
events and resumes the workflow via `POST /run`: ``` ... PAUSED ... -> manager approves/rejects in approval UI -> frontend POST /approve -> backend POST /run (functionResponse) -> process_decision (logs approved/rejected, emits final summary) -> done
google/adk-recipes/core/python/deep-search/AGENTS.md
composes a report with **inline citations** back to web sources. It ships a React frontend over an ADK-powered FastAPI backend. There is no datastore, no ingestion pipeline
google/adk-recipes/core/python/genmedia-for-commerce/AGENTS.md
wiring them into an ADK agent, a **FastAPI** REST surface, and a **React** frontend. - The user needs a **Veo/Gemini retail-media** example with automated quality validation (rotation-consistency + glitch detection
google/adk-recipes/core/python/long-horizon-harness/AGENTS.md
web/README.md`) is a real part of the repo — read it if the frontend is what you're after; it's just outside the ADK harness interfaces this guide teaches. When
omnigent-ai/omnigent/AGENTS.md
Demo** — a **video or images** showing the change. Expected on contributor PRs for UI / frontend changes (check the "UI / frontend change" box under *Type of change*) so reviewers
Kuberwastaken/claurst/AGENTS.md
mode or pipe into `head`. ### Testing the TUI in a controlled terminal The ratatui frontend is sensitive to terminal size and key encoding. For repeatable manual tests use tmux: ```bash
cloudflare/cloudflare-os/AGENTS.md
used extensively for client-server communications. * packages/workshop-shared/src/api.ts: Defines the RPC API used between the frontend and backend. The project structure is: * packages/workshop-frontend: The Gadgets Workshop UI. * This is a pure
cloudflare/cloudflare-os/packages/ui/AGENTS.md
patterns and composed components. ## Ownership - Add a component here when at least two independent frontends need the same feature-independent behavior or when consistency across those frontends is an explicit
cloudflare/cloudflare-os/packages/workshop-frontend/AGENTS.md
Workshop Frontend This package is the Workshop single-page application. It uses React, TanStack Router, Tailwind, and Kumo. Follow the repository-wide guidance in `../../AGENTS.md` in addition to this file
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.