n8n
n8n-io/n8n/AGENTS.md
backend with PostgreSQL, Redis, email, and proxy services | `pnpm --filter n8n-containers services --services postgres,redis,mailpit,proxy`, then `pnpm dev:be` | | Add editor hot reload | `pnpm dev:fe:editor
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
n8n-io/n8n/AGENTS.md
backend with PostgreSQL, Redis, email, and proxy services | `pnpm --filter n8n-containers services --services postgres,redis,mailpit,proxy`, then `pnpm dev:be` | | Add editor hot reload | `pnpm dev:fe:editor
Significant-Gravitas/AutoGPT/AGENTS.md
available use `unknown` ## Testing - Backend: `poetry run test` (runs pytest with a docker based postgres + prisma). - Frontend integration tests: `pnpm test:unit` (Vitest + RTL + MSW, primary testing approach). - Frontend
supabase/supabase/AGENTS.md
telemetry constants, feature flags | | `packages/api-types` | Generated platform Management API types | | `packages/pg-meta` | SQL builders for Postgres introspection (`SafeSqlFragment`) | | `packages/shared-data` | Static data: pricing, plans, regions, error codes | | `e2e/studio`, `e2e/docs` | Playwright E2E tests
bytedance/deer-flow/backend/AGENTS.md
scheduler.multi_instance=true` opts into lease-aware recovery across Gateway instances and requires shared Postgres, `run_ownership.heartbeat_enabled=true`, and `run_events.backend=db`; otherwise startup rejects the configuration. Live scheduled runs
amruthpillai/reactive-resume/AGENTS.md
env.local`. Three required vars: `APP_URL` (default `http://localhost:3000`), `DATABASE_URL` (default `postgresql://postgres:postgres@localhost:5432/postgres`), `AUTH_SECRET` (any non-empty string). - **S3/SeaweedFS optional.** If `S3_ACCESS
langchain-ai/langgraph/AGENTS.md
libraries. Below is a high-level overview: - **checkpoint** – base interfaces for LangGraph checkpointers. - **checkpoint-postgres** – Postgres implementation of the checkpoint saver. - **checkpoint-sqlite** – SQLite implementation of the checkpoint saver
block/buzz/AGENTS.md
huddle audio buzz-core # Core types, event verification, filter matching, kind registry buzz-db # Postgres event store and data access layer buzz-auth # Authentication and authorization buzz-pubsub # Redis pub/sub
topoteretes/cognee/AGENTS.md
source of truth: `cognee/infrastructure/databases/dataset_database_handler/supported_dataset_database_handlers.py`): - Graph — supported: Ladybug/Kuzu (default), Neo4j (needs multi-database, i.e. Enterprise/Aura), Postgres (demo), Turso. Unsupported: Neptune, ladybug-remote. - Vector — supported: LanceDB (default), PGVector, Turso. Unsupported: Neptune Analytics
kestra-io/kestra/AGENTS.md
queue implementations - `queue-jdbc` - JDBC-based queue implementation **Data Layer:** - `jdbc-*` - Database implementations (H2, Postgres, MySQL) **Testing Modules:** - `e2e` - Playwright end-to-end suite, run against a Kestra docker image
BloopAI/vibe-kanban/AGENTS.md
check` in CI) - Prepare SQLx (offline): `pnpm run prepare-db` - Prepare SQLx (remote package, postgres): `pnpm run remote:prepare-db` - Local NPX build: `pnpm run build:npx` then `pnpm pack
triggerdotdev/trigger.dev/AGENTS.md
root. See `.claude/rules/package-installation.md` for the full process. ```bash pnpm run docker # Core dev services (Postgres, Redis, Electric, MinIO, ClickHouse, s2-lite) # pnpm run docker:full # Same + observability stack (Prometheus, Grafana
NevaMind-AI/memU/AGENTS.md
service; do not add one. - Storage is pluggable across `inmemory`, `sqlite`, and `postgres`; repository contract changes require backend parity. - Scope data comes from `UserConfig.model`; validate `where` filters (`_normalize_where
MemTensor/MemOS/AGENTS.md
BaseVecDB` | `VecDBFactory` | `qdrant` / `milvus` | | Graph DB | `BaseGraphDB` | `GraphStoreFactory` | `neo4j` / `neo4j_community` / `nebular` / `polardb` / `postgres` | | Chunker | `BaseChunker` | `ChunkerFactory` | `sentence` / `markdown` / `simple` / `charactertext` | | Parser | `BaseParser` | `ParserFactory` | `markitdown` | | Reranker | `BaseReranker` | `RerankerFactory` | `cosine_local
cocoindex-io/cocoindex/AGENTS.md
Rust extension module (update when PyO3 APIs change) │ │ ├── connectors/ # External system connectors (localfs, postgres, qdrant, lancedb, google_drive) │ │ ├── connectorkits/ # Connector building utilities │ │ ├── resources/ # Abstractions: file.py (FileLike), chunk.py (Chunk), schema.py
cocoindex-io/cocoindex/examples/AGENTS.md
blanks; both `python main.py` and the `cocoindex` CLI load `.env` automatically. Common ones: - `POSTGRES_URL` — for Postgres/pgvector targets. Local instance: `docker compose -f ../../dev/postgres.yaml up -d` from inside an example
google/adk-recipes/core/python/long-horizon-harness/AGENTS.md
docs/sandbox-lifecycle.md. │ ├── scheduler/ # Cloud Scheduler (auth, dream-review/snapshot endpoints) + routines runtime (routine_store, routine_postgres_store, cron.py, routine_tick_endpoint). See "Scheduler" below + docs/routines.md. │ ├── secrets/ # Per-user secret store behind
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.