Python SDK · Code agent

Three calls. That's it

Your agent keeps its tools, prompts, and LLM. Momentum answers one question: may this step continue, must a person look, or must this case stop?

1 · Wrap the run

@fe.governed

One case = one run. This is required before the other two calls.

2 · Report a fact

fe.emit_event(...)

Send what happened. Policy decides continue, pause, or block.

3 · Ask a human

fe.request_approval(...)

Always pauses. The next line runs only after Approve on Feed.

Before you start

Two values from Momentum. Put both in the environment — never in git.

Register the agent on Feed → Add Agent (Code agent). Copy the agent_id.
Create a live key on API Key (fe_live_…). It is shown once.

.env

FORCEEQUALS_API_KEY=fe_live_paste_your_key_here
FORCEEQUALS_AGENT_ID=loan-agent

Install

Requires Python 3.10+. The package is forceequals on pypi.org/project/forceequals. Run this in the agent folder.

Terminal

pip install forceequals

Quick start

Create the client, wrap the run, report facts, ask a human when needed. Paste this, swap in your event names, and run it.

agent.py

import os
from forceequals import (
    ForceEquals,
    GovernanceBlockedError,
    GovernanceRejectedError,
)

fe = ForceEquals(
    api_key=os.getenv("FORCEEQUALS_API_KEY"),
    agent_id=os.getenv("FORCEEQUALS_AGENT_ID"),
)


@fe.governed
def handle_application(payload: dict) -> dict:
    fe.emit_event("loan.risk.calculated", {
        "loan_amount": payload["amount"],
        "risk_score": payload["risk_score"],
    })

    fe.request_approval(
        title="Approve disbursement",
        context={"amount": payload["amount"]},
    )

    # your side-effect after Approve
    return {"ok": True}


try:
    result = handle_application({"amount": 12000, "risk_score": 0.4})
    print("Done", result)
except GovernanceBlockedError as exc:
    print("Blocked:", exc.reason)
except GovernanceRejectedError as exc:
    print("Rejected:", exc.reason)

What each call does

Call	When to use it
@fe.governed	Wrap one business run (one loan, one ticket, one PR).
fe.emit_event(name, data)	Report a fact. Policy decides continue, pause, or block.
fe.request_approval(title=..., context=...)	Ask a human on Momentum Feed. Your process waits until they resolve it.

If emit_event is blocked, the SDK raises GovernanceBlockedError. If a pause is rejected, it raises GovernanceRejectedError. Approve resumes the next line.

Review on Feed

Open Momentum → Feed while the agent is waiting.
Approve resumes the next line (disburse, merge, send). Reject closes this case. Request change stops this run so you can resubmit.

Every decision is also stored on History.

Environment

Variable	Purpose
FORCEEQUALS_API_KEY	Live key from Momentum (fe_live_…).
FORCEEQUALS_AGENT_ID	Same id you registered in Connect Agent.
FORCEEQUALS_BASE_URL	Optional override. Defaults to the hosted API — you can omit this.
FORCEEQUALS_POLL_SECONDS	How often to check a paused run (default 2).

You can pass api_key and agent_id in the constructor instead of using env vars.

If something fails

What you see	What to do
No module named forceequals	Run pip install forceequals with the same Python you use to start the agent.
401 / invalid or revoked key	Generate a new key on API Key. Confirm FORCEEQUALS_API_KEY has no extra spaces.
execution_id required	Put @fe.governed on the function that handles one case.
Nothing appears on Feed	agent_id in code must match Connect Agent. A silent continue will not create a card — pause or fe.request_approval(...) will.

Built the agent on a canvas instead? Use the no-code guide. To put this org's policies into Cursor, Claude, or Codex — without emitting events — connect on the MCP tab.

Three calls. That's it

Your agent keeps its tools, prompts, and LLM. Momentum answers one question: may this step continue, must a person look, or must this case stop?

1 · Wrap the run

@fe.governed

One case = one run. This is required before the other two calls.

2 · Report a fact

fe.emit_event(...)

Send what happened. Policy decides continue, pause, or block.

3 · Ask a human

fe.request_approval(...)

Always pauses. The next line runs only after Approve on Feed.

Before you start

Two values from Momentum. Put both in the environment — never in git.

Register the agent on Feed → Add Agent (Code agent). Copy the agent_id.
Create a live key on API Key (fe_live_…). It is shown once.

.env

FORCEEQUALS_API_KEY=fe_live_paste_your_key_here
FORCEEQUALS_AGENT_ID=loan-agent

Install

Requires Python 3.10+. The package is forceequals on pypi.org/project/forceequals. Run this in the agent folder.

Terminal

pip install forceequals

Quick start

Create the client, wrap the run, report facts, ask a human when needed. Paste this, swap in your event names, and run it.

agent.py

import os
from forceequals import (
    ForceEquals,
    GovernanceBlockedError,
    GovernanceRejectedError,
)

fe = ForceEquals(
    api_key=os.getenv("FORCEEQUALS_API_KEY"),
    agent_id=os.getenv("FORCEEQUALS_AGENT_ID"),
)


@fe.governed
def handle_application(payload: dict) -> dict:
    fe.emit_event("loan.risk.calculated", {
        "loan_amount": payload["amount"],
        "risk_score": payload["risk_score"],
    })

    fe.request_approval(
        title="Approve disbursement",
        context={"amount": payload["amount"]},
    )

    # your side-effect after Approve
    return {"ok": True}


try:
    result = handle_application({"amount": 12000, "risk_score": 0.4})
    print("Done", result)
except GovernanceBlockedError as exc:
    print("Blocked:", exc.reason)
except GovernanceRejectedError as exc:
    print("Rejected:", exc.reason)

What each call does

Call	When to use it
@fe.governed	Wrap one business run (one loan, one ticket, one PR).
fe.emit_event(name, data)	Report a fact. Policy decides continue, pause, or block.
fe.request_approval(title=..., context=...)	Ask a human on Momentum Feed. Your process waits until they resolve it.

If emit_event is blocked, the SDK raises GovernanceBlockedError. If a pause is rejected, it raises GovernanceRejectedError. Approve resumes the next line.

Review on Feed

Open Momentum → Feed while the agent is waiting.
Approve resumes the next line (disburse, merge, send). Reject closes this case. Request change stops this run so you can resubmit.

Every decision is also stored on History.

Environment

Variable	Purpose
FORCEEQUALS_API_KEY	Live key from Momentum (fe_live_…).
FORCEEQUALS_AGENT_ID	Same id you registered in Connect Agent.
FORCEEQUALS_BASE_URL	Optional override. Defaults to the hosted API — you can omit this.
FORCEEQUALS_POLL_SECONDS	How often to check a paused run (default 2).

You can pass api_key and agent_id in the constructor instead of using env vars.

If something fails

What you see	What to do
No module named forceequals	Run pip install forceequals with the same Python you use to start the agent.
401 / invalid or revoked key	Generate a new key on API Key. Confirm FORCEEQUALS_API_KEY has no extra spaces.
execution_id required	Put @fe.governed on the function that handles one case.
Nothing appears on Feed	agent_id in code must match Connect Agent. A silent continue will not create a card — pause or fe.request_approval(...) will.

Built the agent on a canvas instead? Use the no-code guide. To put this org's policies into Cursor, Claude, or Codex — without emitting events — connect on the MCP tab.

Three calls. That's it

Your agent keeps its tools, prompts, and LLM. Momentum answers one question: may this step continue, must a person look, or must this case stop?

1 · Wrap the run

@fe.governed

One case = one run. This is required before the other two calls.

2 · Report a fact

fe.emit_event(...)

Send what happened. Policy decides continue, pause, or block.

3 · Ask a human

fe.request_approval(...)

Always pauses. The next line runs only after Approve on Feed.

Before you start

Two values from Momentum. Put both in the environment — never in git.

Register the agent on Feed → Add Agent (Code agent). Copy the agent_id.
Create a live key on API Key (fe_live_…). It is shown once.

.env

FORCEEQUALS_API_KEY=fe_live_paste_your_key_here
FORCEEQUALS_AGENT_ID=loan-agent

Install

Requires Python 3.10+. The package is forceequals on pypi.org/project/forceequals. Run this in the agent folder.

Terminal

pip install forceequals

Quick start

Create the client, wrap the run, report facts, ask a human when needed. Paste this, swap in your event names, and run it.

agent.py

import os
from forceequals import (
    ForceEquals,
    GovernanceBlockedError,
    GovernanceRejectedError,
)

fe = ForceEquals(
    api_key=os.getenv("FORCEEQUALS_API_KEY"),
    agent_id=os.getenv("FORCEEQUALS_AGENT_ID"),
)


@fe.governed
def handle_application(payload: dict) -> dict:
    fe.emit_event("loan.risk.calculated", {
        "loan_amount": payload["amount"],
        "risk_score": payload["risk_score"],
    })

    fe.request_approval(
        title="Approve disbursement",
        context={"amount": payload["amount"]},
    )

    # your side-effect after Approve
    return {"ok": True}


try:
    result = handle_application({"amount": 12000, "risk_score": 0.4})
    print("Done", result)
except GovernanceBlockedError as exc:
    print("Blocked:", exc.reason)
except GovernanceRejectedError as exc:
    print("Rejected:", exc.reason)

What each call does

Call	When to use it
@fe.governed	Wrap one business run (one loan, one ticket, one PR).
fe.emit_event(name, data)	Report a fact. Policy decides continue, pause, or block.
fe.request_approval(title=..., context=...)	Ask a human on Momentum Feed. Your process waits until they resolve it.

If emit_event is blocked, the SDK raises GovernanceBlockedError. If a pause is rejected, it raises GovernanceRejectedError. Approve resumes the next line.

Review on Feed

Open Momentum → Feed while the agent is waiting.
Approve resumes the next line (disburse, merge, send). Reject closes this case. Request change stops this run so you can resubmit.

Every decision is also stored on History.

Environment

Variable	Purpose
FORCEEQUALS_API_KEY	Live key from Momentum (fe_live_…).
FORCEEQUALS_AGENT_ID	Same id you registered in Connect Agent.
FORCEEQUALS_BASE_URL	Optional override. Defaults to the hosted API — you can omit this.
FORCEEQUALS_POLL_SECONDS	How often to check a paused run (default 2).

You can pass api_key and agent_id in the constructor instead of using env vars.

If something fails

What you see	What to do
No module named forceequals	Run pip install forceequals with the same Python you use to start the agent.
401 / invalid or revoked key	Generate a new key on API Key. Confirm FORCEEQUALS_API_KEY has no extra spaces.
execution_id required	Put @fe.governed on the function that handles one case.
Nothing appears on Feed	agent_id in code must match Connect Agent. A silent continue will not create a card — pause or fe.request_approval(...) will.

Built the agent on a canvas instead? Use the no-code guide. To put this org's policies into Cursor, Claude, or Codex — without emitting events — connect on the MCP tab.