Skip to main content

Todomat — TODO orchestration with NLP2DSL, ITERUN, and curllm pipelines

Project description

Todomat

AI Cost Tracking

PyPI Version Python License AI Cost Human Time Model

  • 🤖 LLM usage: $0.6359 (4 commits)
  • 👤 Human dev: ~$225 (2.2h @ $100/h, 30min dedup)

Generated on 2026-06-07 using openrouter/qwen/qwen3-coder-next


Stack testowy strony www dla klientów wdrażających automatyzację przez prompty.

Łączy Open WebUI z curllm (dane online), NLP2DSL (procesy biznesowe) i ITERUN (usługi/API/stacki) przez OpenAI-compatible router.

Szybki start

cp .env.example .env
make bootstrap          # lub: ./scripts/bootstrap.sh
make test-local         # lub: ./scripts/test-local.sh

make help — lista celów (install, MCP, testy). make goal-a — goal z załadowanym .env (OpenRouter dla pfix).

Endpointy

Usługa URL
Open WebUI http://localhost:3000
Pipeline Router http://localhost:9099/v1
Trigger Gateway http://localhost:8084/trigger
curllm API (opcjonalnie) http://localhost:8810

curllm — dane z internetu

./scripts/start-curllm.sh   # opcjonalnie, pełny browser+LLM

Domyślnie adapter używa lekkiego HTTP fetch (CURLLM_LIGHT_FETCH=1). Pełny curllm: CURLLM_LIGHT_FETCH=0 + uruchomiony API na :8810.

Open WebUI — połączenie

Admin → Settings → Connections:

Base URL: http://pipeline-router:9099/v1   # gdy Open WebUI w sieci todomat
API Key:  dev-key

Jeśli Open WebUI działa poza compose: http://host.docker.internal:9099/v1. Po ./scripts/bootstrap.sh kontener openwebui jest automatycznie podłączany do sieci todomat_todomat-net.

Przykładowe prompty

Zob. examples/prompts/ — w tym orchestration.md (usługi, getv, desktop, workflow).

MCP (Cursor / agenty)

Jeden router MCP routuje do curllm, nlp2dsl, iterun i nlp2uri:

make install-mcp          # pip install -e ".[mcp]" — wymagane dla todomat-mcp
make start-mcp            # lub: ./scripts/start-mcp.sh

Pełny stack (nlp2uri, getv, sibling MCP):

make install-mcp-stack    # ./scripts/install-mcp-stack.sh

pip install -e . instaluje tylko zależności bazowe (httpx, pydantic, beautifulsoup4). SDK MCP (mcp>=1.0) jest w extrasie [mcp] — bez niego todomat-mcp kończy się błędem ModuleNotFoundError: No module named 'mcp'.

Dokumentacja: docs/MCP.md · Cursor: make install-cursor-mcp (pełna) lub make install-cursor-mcp ARGS=--minimal (todomat + koru)

Orchestracja (URI, MCP, wiele usług)

Przewodnik uruchomienia i kontroli usług, artefaktów, zmiennych getv i zadań:

./scripts/sync-env-from-getv.sh llm/groq   # zmienne → .env
./scripts/install-mcp-stack.sh             # MCP + nlp2uri + getv

Dokumentacja

License

Licensed under Apache-2.0.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

todomat-0.2.5.tar.gz (29.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

todomat-0.2.5-py3-none-any.whl (32.6 kB view details)

Uploaded Python 3

File details

Details for the file todomat-0.2.5.tar.gz.

File metadata

  • Download URL: todomat-0.2.5.tar.gz
  • Upload date:
  • Size: 29.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for todomat-0.2.5.tar.gz
Algorithm Hash digest
SHA256 3157dd84d05587e1fca3292a8af7f4d832409487dfbd8a1a4be7a93831805a37
MD5 834267508cdf5b936e3104410da0e7c7
BLAKE2b-256 0e46f4104aafc9b7c236ec7d70fd92697d6e10b5eb82cdb9cd8c633a2e8892c2

See more details on using hashes here.

File details

Details for the file todomat-0.2.5-py3-none-any.whl.

File metadata

  • Download URL: todomat-0.2.5-py3-none-any.whl
  • Upload date:
  • Size: 32.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for todomat-0.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 fc61370553a072371294f6e75e17c85b747199cc80755216351ceb48fe254817
MD5 892d9152375a35c631d1f69d69cca0ff
BLAKE2b-256 d377c5050771560753e3c8e55a047f993affd02c86f8740945df873651a82bce

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page