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: $0.6256 (3 commits)
  • 👤 Human dev: ~$221 (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 mcp-cursor-json — wygeneruj konfigurację Cursor.

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 · konfiguracja Cursor (21 serwerów z wronai/* + semcod/*): examples/mcp-cursor.json

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-0.2.4.tar.gz (23.5 kB view details)

Uploaded Source

Built Distribution

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

todomat-0.2.4-py3-none-any.whl (26.9 kB view details)

Uploaded Python 3

File details

Details for the file todomat-0.2.4.tar.gz.

File metadata

  • Download URL: todomat-0.2.4.tar.gz
  • Upload date:
  • Size: 23.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for todomat-0.2.4.tar.gz
Algorithm Hash digest
SHA256 b6ec2fc63f7eada8f4584b8578b1467ef150aa71040d86fbcc60e09771894efb
MD5 4b9fa382bf0b2294e3c716ec6b4f7835
BLAKE2b-256 21b4ef80eaf4b4974d9f455390498536119622a257f73062782dcfcf29a64fa4

See more details on using hashes here.

File details

Details for the file todomat-0.2.4-py3-none-any.whl.

File metadata

  • Download URL: todomat-0.2.4-py3-none-any.whl
  • Upload date:
  • Size: 26.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for todomat-0.2.4-py3-none-any.whl
Algorithm Hash digest
SHA256 c8d37986d00104308bcfa8c9b996c6955f5d6ddc64a56be1c93e812c18615be2
MD5 fa0d17e1a11d0f32d0623dc2097cae5b
BLAKE2b-256 c95806e44262275f43ad3c107a6e60658c89ff370c3de903fc89cc0f2892071d

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