Describe the work.
Keep the standard.
A manifest is a versioned configuration file describing work and its requirements. It gives people and agents something concrete to inspect, change, and check.
Identity
Name and version the work.
Specification
Describe the capability and requirements.
Checks & results
Apply supported controls. Inspect the outcome.
Make the decisions
durable.
Prompts describe intent. Versioned configuration preserves engineering decisions. The runtime applies the supported rules, and results show what happened.
- Review the requirements before running.
- Keep the configuration with the project.
- Check a proposed change against the same standard.
- Carry the specification into the next agent session.
Data pipelines
with requirements.
Define the pipeline, then attach a data contract at the boundary where it must hold. The loader checks records before writing.
Run this templateapi_version: pycharter.io/v2
kind: Pipeline
metadata:
name: orders_feed
version: "1.0.0"
spec:
steps:
- id: read_orders
type: extract
source:
type: file
path: orders.jsonl
format: jsonl
- id: write_orders
type: load
input: read_orders
target:
type: file
path: accepted.jsonl
format: jsonl
mode: overwrite
contract:
ref:
type: file
path: orders-contract.yaml
validate: true
coerce: true
on_error: fail
The contract block is the enforcement point. A failed record stops this file loader; a previous output file is not proof of a successful new run.
Native review unavailable
Native preview and checks are not connected in this view. Review the draft with a supported PyCharter runtime before running it.
Reading, copying or downloading these bytes does not validate or run a pipeline.
api_version: pycharter.io/v2
kind: DataContract
metadata:
name: orders
version: "1.0.0"
spec:
json_schema:
version: "1.0.0"
type: object
properties:
order_id:
type: string
minLength: 1
amount:
type: number
minimum: 0
required: [order_id, amount]
additionalProperties: false
Each order needs an ID and a nonnegative amount. The versioned file preserves the requirements for the next developer or agent.
Native review unavailable
Native preview and checks are not connected in this view. Review the draft with a supported PyCharter runtime before running it.
Reading, copying or downloading these bytes does not validate or run a pipeline.
Open your native draft
Open one UTF-8 JSON or YAML file up to 256 KiB. View and export its original bytes in this tab. Native checking is unavailable.
Keep the file in your project to reopen it later. Closing or reloading this view clears the opened draft.
Selected tools
for a defined task.
Use a native tool profile to choose the operations an agent discovers. Configure policy, credentials, and audit in the embedding runtime.
Run this template{
"profiles": {
"communications-demo": {
"include": ["pyactuator.comms.slack_send"]
}
}
}
This native PyActuator profile controls tool discovery. Policy, credentials, and durable audit are configured by the host runtime.
These are real package-native configurations. PyCharter uses its versioned YAML envelope; PyActuator uses a JSON tool profile. Optophi's direction is a consistent manifest experience across capabilities. A single universal manifest API is not yet a released interface.
Explore the ecosystem