AGENTS.md · Intelligent-Internet/ii-agent
AGENTS.md from Intelligent-Internet/ii-agent: 277 lines covering Quick Start, Repository Map, Mandatory Rules, Architecture and more.
Template by Intelligent-Internet
Chalk Labs
Need help deploying AGENTS.md · Intelligent-Internet/ii-agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/Intelligent-Internet/ii-agent/main/AGENTS.md -o AGENTS.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: prompt-engineering
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.
- For
- Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
- Length
- 277 lines
- File
AGENTS.md
Sections
- Quick Start
- Repository Map
- Mandatory Rules
- Architecture
- Where to Look
- Development Workflow
- Key Commands
First lines (shown under the repo's Apache-2.0 license)
# II-Agent Contributor Guide
This file is the entry point for agents working in this repository. It provides the architecture overview plus a map to deeper documentation.
**Read `CLAUDE.md` for the full development reference** (patterns, billing system, dependency injection, code examples).
## Quick Start
```bash
uv sync --frozen # Install dependencies
./scripts/start.sh # Start the server
curl localhost:8000/health # Verify
```
## Repository Map
| Resource | What it covers |
|----------|---------------|
| [`CLAUDE.md`](CLAUDE.md) | Full development guide: patterns, billing, dependency injection, code examples |
| [`docs/DESIGN.md`](docs/DESIGN.md) | Design patterns: service pattern, Dep aliases, domain module structure |
| [`docs/PLANS.md`](docs/PLANS.md) | How to write and maintain execution plans |
| [`docs/RELIABILITY.md`](docs/RELIABILITY.md) | Billing reliability, cron recovery, Redis fallbacks |
| [`docs/SECURITY.md`](docs/SECURITY.md) | Auth flow (OAuth, JWT, API keys), secrets management |
| [`docs/FRONTEND.md`](docs/FRONTEND.md) | Socket.IO events, REST API surface, real-time event flow |
| [`docs/PRODUCT_SENSE.md`](docs/PRODUCT_SENSE.md) | Product principles, user personas, key journeys |
| [`docs/QUALITY_SCORE.md`](docs/QUALITY_SCORE.md) | Per-domain quality grades and health metrics |
| [`docs/design-docs/`](docs/design-docs/index.md) | Indexed design decisions with verification status |
| [`docs/exec-plans/`](docs/exec-plans/) | Active and completed execution plans |
| [`docs/generated/db-schema.md`](docs/generated/db-schema.md) | Database schema reference (from SQLAlchemy models) |
| [`docs/product-specs/`](docs/product-specs/index.md) | Product specifications |
| [`docs/references/`](docs/references/) | LLM-optimized reference material for key dependencies |
## Mandatory Rules
1. **Use `uv run`** for all Python commands (`uv run pytest`, `uv run python ...`).
2. **Run Ruff only on the Python files you changed** before marking work complete (`uv run ruff check --fix-only <changed_python_files>`, `uv run ruff format <changed_python_files>`, `uv run ruff check <changed_python_files>`, `uv run ruff format --check <changed_python_files>`). If you changed no Python files, skip Ruff.
3. **Never call `CreditService.deduct()` directly** for LLM/tool billing — use the reservation system (see `CLAUDE.md` Billing section).
4. **Use Dep aliases everywhere** — never bare `= Depends(get_x)` in function signatures (see `CLAUDE.md` Dependency Injection Pattern).
5. **Use `LLMExecutionService`** for any new code that calls an LLM outside the agent runtime loop.
## Architecture
### Domain Map
II-Agent is organized into domain modules under `src/ii_agent/`. Each domain owns its models, repository, service, dependencies, router, and schemas.
```text
src/ii_agent/
├── app/ # FastAPI bootstrap package, middleware, lifespan, router wiring
│
├── core/ # Shared infrastructure (no business logic)
│ ├── config/ # Pydantic settings (database, redis, storage, oauth, stripe)
│ ├── db/ # SQLAlchemy 2.0 base, async session management, migrations
│ ├── llm/ # LLM billing service, execution service, base client
│ ├── redis/ # Redis client, cache, pubsub, lock, cancel management
│ ├── secrets/ # GCP Secret Manager integration
│ ├── storage/ # File storage abstraction (GCS, local)
│ ├── container.py # ServiceContainer for complex dependency graphs
│ └── dependencies.py # DBSession, SettingsDep (shared Dep aliases)
│
├── auth/ # Authentication & authorization
│ ├── jwt_handler.py # JWT creation/verification (HS256)
│ ├── oidc_verify.py # OIDC token verification (RS/ES families)
│ ├── api_key_utils.py # API key generation
│ └── users/ # User profiles, CRUD, waitlist
│
├── billing/ # Credit ledger & billing
│ ├── credits/ # Balance, ledger, pricing, service
│ ├── reservations/ # Reserve -> settle -> release state machine
│ ├── usage/ # Usage records, LLM/tool invocation telemetry
│ ├── customers/ # Stripe customer management
│ └── webhook_handler.py # Stripe webhook processing
│
├── sessions/ # Chat session management
│ ├── models.py # Session model, SessionStateEnum, AppKind
│ ├── service.py # Session CRUD, state transitions
│ ├── fork_service.py # Session forking
│ ├── title_service.py # Auto-title generation
│ ├── wishlist/ # Session bookmarks
│ └── pin/ # Pinned sessions
│
├── agent/ # Agent execution framework
│ ├── application/ # Validation, execution orchestration
│ ├── runtime/ # Agent runtime models, streaming
│ ├── runs/ # Agent run task management
│ ├── events/ # Event handling & logging
│ ├── prompts/ # System prompts & templates
│ ├── sandboxes/ # E2B sandbox management
│ ├── socket/ # Socket.IO command handlers (query, cancel, plan)
│ └── subscribers/ # Event subscribers (metrics, database)
│
├── chat/ # Chat API & LLM providers
│ ├── api/ # Chat REST endpoints
│ ├── llm/ # LLM provider implementations (Anthropic)
│ ├── media/ # Media processing (image gen, video gen, web search)
│ ├── runs/ # Chat run management
│ ├── tools/ # Chat tools (code interpreter, tool registry)
│ └── vectorstore/ # Vector store integration (OpenAI)
│
├── content/ # Content generation
│ ├── media/ # Media templates, tools, config
│ ├── skills/ # Custom skills management
│ ├── slides/ # Slide/presentation generation + templates + design
│ └── storybook/ # Storybook generation
│
├── files/ # File upload/download service
│
├── integrations/ # External integrations
│ ├── a2a/ # Agent-to-Agent protocol
│ ├── connectors/ # External connectors (GitHub, Google Drive via Composio)
│ ├── enhance_prompt/ # Prompt enhancement
│ └── mobile/ # Mobile platform integrations (Apple, future Android)
│
├── projects/ # Project & deployment management
│ ├── cloud_run/ # Google Cloud Run deployment
│ ├── databases/ # Database provisioning
│ ├── deployments/ # Deployment orchestration
│ ├── design/ # Project design
│ ├── secrets/ # Project-level secrets
│ └── subdomains/ # Subdomain management
│
├── settings/ # User settings
│ ├── llm/ # User LLM model preferences
│ └── mcp/ # MCP server configuration
│
├── utils/ # Shared utilities
├── workers/ # Background jobs (Celery cron)
├── scripts/ # Admin scripts
└── ws_server.py # WebSocket server entry point
```
### Layer Architecture
Within each domain, code follows a fixed layer hierarchy. Dependencies flow downward only.
```text
Router (FastAPI endpoints)
|
Dependencies (Dep aliases, factory functions)
|
Service (business logic, takes db: AsyncSession)
|
Repository (data access, SQLAlchemy queries)
|
Models (SQLAlchemy 2.0 declarative models)
|
Schemas (Pydantic DTOs for request/response)
```
### Layer Rules
- **Models** may only import from `core.db` and standard library.
- **Repository** imports models and core utilities. Never imports services.
- **Service** imports repository and models. May import other services' Dep aliases for cross-domain work.
- **Dependencies** defines factory functions and Dep aliases. Imports services and repositories.
- **Router** imports Dep aliases from dependencies. Never imports repositories directly.
- **Schemas** are pure Pydantic models. No database or service imports.
### Cross-Cutting ConcernsSignals
- Stars
- 3,391
- Forks
- 526
- Open issues
- 4
- Last commit (this folder)
- Apr 2, 2026 (7 months ago)
- Last release
- Jul 29, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Intelligent-Internet/ii-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Intelligent-Internet
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get AGENTS.md · Intelligent-Internet/ii-agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
AGENTS.md · Intelligent-Internet/ii-agent. Agent Mart. https://agentmart.dev/templates/intelligent-internet-ii-agent-agents-md (last updated 2026-10-24)