puras

The Python SDK + CLI for Puras — deploy long-running, multi-step agentic skills and call them from anywhere.

pip install puras        # or: uv tool install puras  /  uvx puras

You get two things in one package:

  • import puras — the runtime SDK your deployed skills use (media.generate_image/video/audio, media.transcribe, secret, load_path, subagent.run).
  • puras — a CLI to scaffold, deploy, run, and tail skills from your terminal and CI.

Quickstart

puras login                       # paste a workspace API key (created in the dashboard)
puras init --name "My Skillpack"  # creates the skillpack + writes puras.yaml + scaffolds my-skill/
puras deploy                      # zips ./ and pushes an active deployment
puras run my-skill -i prompt="hi" # submit a job and wait for the result

Want a worked example instead of a blank slate? puras init --template hello-world scaffolds the full hello-world pack — an agentic skill, a deterministic skill, a custom tool, and two subagents.

Auth

  • Interactive: puras login stores your key in ~/.puras/config.json.
  • CI: set PURAS_API_KEY (and optionally PURAS_API_BASE) in the environment — no login step, no browser.
PURAS_API_KEY=puras_live_… puras deploy --skillpack <id>

Commands

Command What it does
puras login / logout / whoami manage stored credentials
puras init create a skillpack, write puras.yaml, scaffold a starter (--template hello-world for the full example)
puras skillpacks list your skillpacks
puras deploy [path] bundle a dir and push a deployment (--no-activate)
puras deployments list deployments for the current skillpack
puras activate <version|id> make a deployment the active one
puras run <skill> -i k=v submit a job and wait (--async, --json)
puras logs <job_id> stream a job's events until it finishes
puras secrets set/ls/rm manage skillpack secrets
puras pull download the active bundle

The skillpack is resolved from --skillpack <id|slug>, else the nearest puras.yaml. The CLI is a convenience over the public HTTP API (POST /v1/jobs, /v1/skillpacks/{id}/deployments, …) — anything it does, you can do with curl and a Bearer key.

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.20.0)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for purasco from gravatar.com purasco

Credits

Author: Puras

Requires

Python >=3.10

Provides Extra

local

Tags

agents ai backend cli mcp puras sdk

Classifiers

Report project as malware

Download files

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

Source Distribution

puras-0.18.0.tar.gz (34.5 kB view details)

Uploaded Source

Built Distribution

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

puras-0.18.0-py3-none-any.whl (41.4 kB view details)

Uploaded Python 3

File details

Details for the file puras-0.18.0.tar.gz.

File metadata

  • Download URL: puras-0.18.0.tar.gz
  • Upload date:
  • Size: 34.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for puras-0.18.0.tar.gz
Algorithm Hash digest
SHA256 92775556007db914f79550b384c0eeb4be2b547bfff4d56692d8e213aefc4bad
MD5 a702e0f7650b070e476092f780d26418
BLAKE2b-256 ff48dafbe835a877733be9020b05682d6adb6aa46fe225580cfb3ef8bd16d6c9

See more details on using hashes here.

Provenance

The following attestation bundles were made for puras-0.18.0.tar.gz:

Publisher: publish.yml on PurasAI/puras

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file puras-0.18.0-py3-none-any.whl.

File metadata

  • Download URL: puras-0.18.0-py3-none-any.whl
  • Upload date:
  • Size: 41.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for puras-0.18.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2bebd0fc33a4bf029d718545f4167cc8157fb1d264a4a08b2b15803bbfa28416
MD5 b3d17ff5222c44b38d4234876e228b29
BLAKE2b-256 14fa7011e4f90e852f42c83b2cdc84fbc57eb7264c4aa501a24bc2dfbfb14c37

See more details on using hashes here.

Provenance

The following attestation bundles were made for puras-0.18.0-py3-none-any.whl:

Publisher: publish.yml on PurasAI/puras

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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