How real projects summarise themselves for language models.
metravodllms.txtmetravod/zymi-core/llms.txt
README §"zymi as an MCP server" - [Store backends](docs/store-backends.md): SQLite (default) vs Postgres (multi-process `zymi serve` against a shared store) - [Events and replay](docs/events-and-replay.md): event-sourcing model, stream
saifeldeen911llms.txtsaifeldeen911/actionfence/llms.txt
peer dependency (only needed for PostgreSQL storage) - Receipts default to SQLite; set `storage: { adapter: 'postgres', connectionString: '...' }` for horizontally-scaled deployments - Receipt persistence failures default to backward-compatible allow mode (`receipt
Speraxllms.txtSperax/sperax-skills/llms-full.txt
# Sperax Skills — Complete Reference > Full content of all 38 skills. For summary, see llms.txt
Amey-Thakurllms.txtAmey-Thakur/AI-SKILLS/docs/llms.txt
# AI Skills > Plug-and-play skills and prompts for every AI coding agent. Each
ahnafnafeellms.txtahnafnafee/ahnafnafee.dev/public/llms.txt
fields across nine sports worldwide, using an Expo and React Native app on Supabase Postgres with PostGIS, a Cloudflare D1 edge replica for court reads, GPS proof-of-presence check
Abloataillms.txtAbloatai/circle-ablo/llms.txt
same data in real time. > Built on Ablo (write path + sync stream) over Neon Postgres, with Drizzle for > migrations, Better Auth for identity, eve for the agent runtime, and Next.js
ANIBIT14llms.txtANIBIT14/zolva/llms.txt
before provider calls, evals, feedback loop, hash-chained > audit with pluggable storage (SQLite or Postgres), human handover with a > resume path, and synthetics attach to every step via a middleware
backblaze-labsllms.txtbackblaze-labs/awesome-agent-infrastructure/llms.txt
prototyping. - docs: https://docs.trychroma.com - [pgvector](https://github.com/pgvector/pgvector): Open-source vector similarity extension for Postgres. Exact and approximate nearest-neighbour with HNSW and IVFFlat. - [Weaviate](https://weaviate.io): Vector search with
csnyder256llms.txtcsnyder256/org-memory-os/docs/llms.txt
lives in files and a database whose authority is explicitly ordered (an append-only Postgres claim ledger is truth, git-Markdown is a projection of it, the hybrid vector-plus
Moai-Team-LLCllms.txtMoai-Team-LLC/AgenticMind/docs/llms.txt
judge-gated loop that promotes validated knowledge back into the corpus. > Self-hosted on Postgres alone, zero-key local (bge-m3) embeddings, multilingual. > Apache-2.0. Reference implementation of the Agentic
theyoungastronautsllms.txttheyoungastronauts/polaris/llms.txt
django` | backend | `server` | Django/DRF patterns + verification | | `nextjs-fullstack` | backend | `web` | Full-stack Next.js (Drizzle, Postgres, Redis, BullMQ, Auth.js) — pair with a Next.js frontend profile | | `nextjs` | frontend | `web` | Next.js (DaisyUI) + React/Tailwind
vvooki-sysllms.txtvvooki-sys/loomem/docs/llms-full.txt
with no external datastore. Mem0 (Apache-2.0) orchestrates an external vector store (Qdrant) plus Postgres. Zep is built on Graphiti and needs a graph database (Neo4j, FalkorDB, or Kuzu
Ayithamsetty-Vamsi-krishnallms.txtAyithamsetty-Vamsi-krishna/claude-skills/llms.txt
Generics, BaseModel, AuditMixin, SoftDeleteMixin, dual FK serializers, audit log, multi-tenancy, feature flags, Postgres FTS, Elasticsearch, field encryption, GDPR - **django-auth-dev**: Pattern C multi-user auth (StaffUser + CustomerUser
helbertparanhosllms.txthelbertparanhos/easypanel-mcp-server/llms.txt
primary_domain`: Set the primary domain for a service - `create_database`: Create a Postgres, MySQL, MariaDB, MongoDB or Redis service - `inspect_database`: Get database details including credentials and connection string
MachuraHarryllms.txtMachuraHarry/pipe/website/llms.txt
host. `mcp_use_stdio` connects to any community MCP server (GitHub, Filesystem, Postgres, Slack, Brave Search, ...) directly from code. - **AI builtins**: 36 AI builtins + 13 MCP builtins across 4 providers
10xHubllms.txt10xHub/agentflow-docs/static/llms.txt
framework for building production-grade multi-agent AI systems. Typed StateGraph orchestration, durable Redis + Postgres persistence, a built-in REST and SSE API server, and a typed TypeScript client
andyazizllms.txtandyaziz/claude-code-ultimate-guide/machine-readable/llms.txt
Hooks** - Event-driven automation (security, formatting, logging) 8. **MCP Servers** - Serena, Context7, Sequential, Playwright, Postgres 9. **Advanced Patterns** - Trinity, CI/CD, feedback loops, vibe coding 10. **Reference** - Commands, shortcuts, troubleshooting, checklists
bharath31llms.txtbharath31/nominee/llms.txt
store, atomic durable receipt store with `delivery: 'strict'`, and durable provider approval state. `nominee-postgres` supplies the stores. - **Adapters**: `nominee-ai` (Vercel AI SDK + Cloudflare Agents: `guardTools`, `nomineeTool`), `nominee
ctalallms.txtctala/skool-api-docs/llms.txt
Skool BI dashboard — scheduled actor runs export members and engagement to NocoDB, Airtable or Postgres for churn tracking. - [Auto-approve Skool members by deterministic criteria (no LLM needed)](https://skool-api.cristiantala.com
FrancoisChastelllms.txtFrancoisChastel/sydonia-toolkit/docs/llms-full.txt
Spin one up with Docker in one line: ```bash docker run --name customs -e POSTGRES_PASSWORD=customs -p 5432:5432 -d postgres:16 ``` Then prefix the commands below with
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
