AI Stupid Level SDKs

Official clients for the AI Stupid Level Smart Router, an OpenAI-compatible endpoint. Each request goes to the model measuring best for that kind of work, based on benchmarks that are re-run continuously. You call it with your own provider keys.

Package	Install	Source
TypeScript / JavaScript	npm install @aistupidlevel/router	packages/router
Python	pip install aistupidlevel	python
Vercel AI SDK provider	npm install @aistupidlevel/ai-sdk-provider	packages/ai-sdk-provider
MCP server (Claude, Cursor, VS Code, …)	npx -y @aistupidlevel/mcp	packages/mcp
n8n community node	Settings → Community Nodes → n8n-nodes-aistupidlevel	packages/n8n-nodes-aistupidlevel
Raycast extension	Raycast Store (in review)	integrations/raycast/aistupidlevel
LangChain chat model (ChatAISL)	pip install langchain-aistupidlevel	langchain-python
Hermes Agent provider plugin	hermes plugins install aistupidlevel	integrations/hermes/aistupidlevel
DeepSeek Harness plugin bundle	dsh plugin --profile web add @aistupidlevel/dsh-provider	packages/dsh-provider
OpenClaw provider plugin	openclaw plugins install clawhub:@aistupidlevel/openclaw-provider	packages/openclaw-provider
Pi provider extension	pi install npm:@aistupidlevel/pi-provider	packages/pi-provider
Langflow model provider + component	pip install lfx-aistupidlevel, then restart Langflow	langflow-python
Open WebUI Function (manifold pipe)	Admin Panel → Functions → Import from URL	integrations/open-webui

openapi/router-v1.json describes the API in OpenAPI 3.1, for generating a client in any other language. The live copy is at https://aistupidlevel.info/v1/openapi.json.

Quick start

import { ASLRouter } from '@aistupidlevel/router';

const router = new ASLRouter(); // ASL_ROUTER_KEY
const r = await router.chat.completions.create({ model: 'auto-coding', messages: [{ role: 'user', content: 'Fix this bug: ...' }] });
console.log(r.choices[0].message.content, r.routing.model, r.routing.reasoning);

from aistupidlevel import ASLRouter

router = ASLRouter()  # ASL_ROUTER_KEY
r = router.chat.completions.create(model="auto-coding", messages=[{"role": "user", "content": "Fix this bug: ..."}])
print(r.choices[0].message.content, r.routing.model, r.routing.reasoning)

Why use an SDK instead of an OpenAI client

Any OpenAI client works against https://aistupidlevel.info/v1. The SDKs add:

• Routing info on every answer and stream: the model and provider that answered, why they were chosen, and whether a fallback answered.
• Safe retries. An automatic Idempotency-Key means a request is answered once, even if it is retried.
• Typed errors with party and retryable. An app can tell its user to top up, to fix a provider key, or simply to try again.
• runTools / run_tools, a tool-calling loop that stays on one model.
• Sandbox mode (mock answers through real routing, at no cost), route previews, and usage.

See the API documentation.

Development

# TypeScript (the router package runs on Node 18+; the AI SDK provider needs Node 22+)
cd packages/router && npm ci && npm run build && npm test
cd packages/ai-sdk-provider && npm ci && npm run build && npm test
cd packages/mcp && npm ci && npm run build && npm test
cd packages/openclaw-provider && npm ci && npm test   # Node 24.16+, like OpenClaw
cd packages/pi-provider && npm ci && npm test         # Node 22.19+, like Pi
cd packages/n8n-nodes-aistupidlevel && npm ci && npm run build && npm run lint && npm test

# Python
cd python && pip install -e . && python -m unittest discover -s tests
cd langflow-python && pip install -e . pytest && pytest tests   # in a venv with Langflow 1.12+

The live tests run against the real router in sandbox mode, so nothing is spent. They need a router key and are skipped without one:

ASL_ROUTER_KEY=aism_... npm test
ASL_ROUTER_KEY=aism_... python -m unittest discover -s tests

Releasing

1. Bump the version in every place it appears:
   • packages/router/package.json and packages/router/src/core.ts;
   • packages/ai-sdk-provider/package.json and packages/ai-sdk-provider/src/index.ts;
   • packages/mcp/package.json, packages/mcp/src/config.ts and both versions in packages/mcp/server.json;
   • python/src/aistupidlevel/_version.py.
2. npm: npm publish --access public in each package directory. prepublishOnly builds the package and runs its tests first.
3. PyPI: cd python && python -m build && twine upload dist/*.
4. MCP Registry, after the npm release of @aistupidlevel/mcp: cd packages/mcp && mcp-publisher login github && mcp-publisher publish.
5. n8n node: n8n accepts only npm releases with provenance, so it is published by .github/workflows/n8n-publish.yml. Bump packages/n8n-nodes-aistupidlevel/package.json and its CHANGELOG.md, then push a tag n8n-v<version>.
6. Raycast: from integrations/raycast/aistupidlevel, npm run publish opens a pull request to raycast/extensions.
7. Pi: cd packages/pi-provider && npm publish (Node 22.19+). Push first: the pi.dev gallery image is read from main. The pi-package keyword lists it on pi.dev/packages; there is nothing to submit.
8. Langflow: bump langflow-python/pyproject.toml, src/lfx_aistupidlevel/__init__.py and src/lfx_aistupidlevel/extension.json (a test checks they match), then cd langflow-python && uv build && twine upload dist/* with twine 7 or later.

Licence

MIT