Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ Full documentation lives in [`docs/`](./docs/guide/index.md) (a hosted site is o
| [`ai‑sdk`](./packages/ai-sdk) | The agent runtime: providers, the agent loop, tools, streaming, middleware, structured output, memory, and evals. The engine the rest of the AI family builds on. | [Guide](./docs/packages/ai-sdk/index.md) | [![npm](https://img.shields.io/npm/v/@gemstack/ai-sdk)](https://www.npmjs.com/package/@gemstack/ai-sdk) |
| [`ai‑skills`](./packages/ai-skills) | Portable capability bundles: load `SKILL.md` skills (instructions + tools + resources) and compose them onto an agent on demand. | [Guide](./docs/packages/ai-skills.md) | [![npm](https://img.shields.io/npm/v/@gemstack/ai-skills)](https://www.npmjs.com/package/@gemstack/ai-skills) |
| [`ai‑autopilot`](./packages/ai-autopilot) | The AI‑building framework: a Supervisor (plan → dispatch → synthesize) plus stack‑aware personas, a runner sandbox, surfaces, a decisions ledger, an event‑triggered review/QA loop with a built‑in prompt library, framework presets (Vike/Next), and a bootstrap flow that takes an app from nothing to production‑grade. | [Guide](./docs/packages/ai-autopilot.md) | [![npm](https://img.shields.io/npm/v/@gemstack/ai-autopilot)](https://www.npmjs.com/package/@gemstack/ai-autopilot) |
| [`framework`](./packages/framework) | **The (AI) Framework**: turnkey, zero‑config orchestration built on `ai-autopilot`. Wraps a coding‑agent CLI (Claude Code) as a black box and takes an idea to a running app, with a live dashboard, Open Loop domain presets, an optional Docker sandbox, and a run relay for shared sessions. | [README](./packages/framework/README.md) | [![npm](https://img.shields.io/npm/v/@gemstack/framework)](https://www.npmjs.com/package/@gemstack/framework) |
| [`ai‑mcp`](./packages/ai-mcp) | The agent/MCP bridge: consume a remote MCP server's tools as agent tools, and expose an agent as an MCP server. | [Guide](./docs/packages/ai-mcp.md) | [![npm](https://img.shields.io/npm/v/@gemstack/ai-mcp)](https://www.npmjs.com/package/@gemstack/ai-mcp) |
| [`mcp`](./packages/mcp) | A standalone framework for *authoring* MCP servers: tools, resources, prompts, decorators, OAuth 2.1, a framework-neutral HTTP handler, and a test client. Agent-agnostic. | [Guide](./docs/packages/mcp.md) | [![npm](https://img.shields.io/npm/v/@gemstack/mcp)](https://www.npmjs.com/package/@gemstack/mcp) |
| [`mcp‑connectors`](./packages/mcp-connectors) | The connector contract: define a tool connector to an external service once with `defineConnector`, and compose any number into a single MCP server with `mountConnectors`. Built on `@gemstack/mcp`; agent-agnostic. | [Guide](./docs/packages/mcp-connectors.md) | [![npm](https://img.shields.io/npm/v/@gemstack/mcp-connectors)](https://www.npmjs.com/package/@gemstack/mcp-connectors) |
Expand All @@ -32,6 +33,7 @@ graph TD
subgraph fam["AI family · depends on the agent runtime"]
skills["<b>ai-skills</b><br/>capability bundles"] --> sdk["<b>ai-sdk</b><br/>agent runtime"]
autopilot["<b>ai-autopilot</b><br/>orchestration"] --> sdk
framework["<b>framework</b><br/>turnkey app builder"] --> autopilot
aimcp["<b>ai-mcp</b><br/>agent ↔ MCP bridge"] --> sdk
end
subgraph agn["Agent-agnostic · not ai-*"]
Expand Down
23 changes: 23 additions & 0 deletions packages/ai-autopilot/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -298,6 +298,29 @@ own bodies from a directory with `loadPromptsFrom(dir)`, or add one to a library
with `library.add(...)`. The bodies are the main open-source contribution surface;
PRs that sharpen them are welcome.

## Domain presets — a loop + prompts + skills bundled per domain

A **domain preset** packages a domain's review loops, prompt bodies, and skill
pointers as one `{ loops, prompts, skills }` unit, so a run is framed for a *kind*
of work (software, web, data, product, science) instead of the generic default.
Each preset is a directory of markdown under `presets/` — a `preset.md` manifest
plus `loops/`, `prompts/`, and `skills/` — so a contributor adds one by writing
files, not code.

```ts
import { builtinDomainPresets, selectPreset } from '@gemstack/ai-autopilot'

const presets = await builtinDomainPresets() // discovers every shipped preset
const sw = selectPreset(presets, 'software-development') // sw.loops / sw.prompts / sw.skills
```

Five ship built in (`software-development`, `web-development`, `data-science`,
`product-management`, `biological-science`). Load your own with
`loadDomainPreset(dir)`, and merge several with `composeDomainPresets(...)`
(presets-of-presets). A mode variant (a `stem.<mode>.md` sibling carrying
`metadata.conditions`) swaps in a leaner loop under a mode like `technical`.
`@gemstack/framework` surfaces these to end users as `--preset`.

## Guardrails

- **`concurrency`** (optional, default 4) — max workers in flight; positive integer.
Expand Down
Loading