forma-sdk 2.0.0

FORMA — AI agent compliance SDK. Zero-config tracking, EU AI Act/DPDP/RBI compliance, cryptographic audit trails.

FORMA SDK

Make non-compliance impossible — in one line of code.

FORMA doesn't just record what your AI did; it blocks non-compliant decisions before they execute. Add enforce=[...] and PII leaks, prompt injections, and policy violations are stopped at runtime — then every decision is cryptographically signed and mapped to RBI, DPDP, EU AI Act, and ISO 42001.

---

Install

pip install forma-sdk

Import name is trustlayer:

import trustlayer as tl

Quickstart — runtime enforcement

import trustlayer as tl

tl.init(
    api_key="tl_live_YOUR_KEY",   # from forma.2bd.net → Settings
    human_sponsor="[e-mail]",
    purpose="Loan application evaluation",
    risk_level="HIGH",
    enforce=["rbi_ml_risk", "dpdp"],   # ← blocks violations BEFORE they run
)

def approve_loan(application: dict) -> dict:
    with tl.using("loan-approval-agent", risk_level="HIGH", enforce=["rbi_ml_risk"]):
        return run_underwriting_model(application)

Now, before any LLM or tool call executes:

• An Aadhaar / PAN / card number in the prompt → blocked (DPDP)
• "Ignore previous instructions…" / jailbreaks → blocked
• "Auto-approve without review" → blocked (RBI human-review rule)

A blocked action raises ComplianceViolation, and every decision (allow / warn / block) lands in your signed audit trail. The gate runs locally in ~1 ms — no network hop in your request path.

from trustlayer import ComplianceViolation

try:
    result = approve_loan(application)
except ComplianceViolation as e:
    print(e.reason)   # "PII detected in LLM prompt: Aadhaar number. ..."

Zero-config tracking (no enforcement)

import trustlayer as tl
tl.init(api_key="tl_live_YOUR_KEY")

# Every OpenAI / Anthropic / LangChain / LiteLLM call is now auto-captured —
# tokens, cost, latency, anomaly score — with no other code changes.

Human approvals (EU AI Act Article 14 / RBI human review)

import trustlayer as tl

tl.init(
    api_key="tl_live_YOUR_KEY",
    require_approval_when=lambda ctx: ctx.get("amount", 0) > 1_000_000,
    approval_message="Loan above ₹10L requires human review.",
)

def approve_loan(application: dict) -> dict:
    with tl.using("loan-approval-agent"):
        return run_underwriting_model(application)

The decision pauses in your FORMA Approvals inbox until a human approves or rejects. Fail-closed: a timeout or unreachable API is treated as a denial — a skipped review never silently passes.

---

Policy packs

Pack	Region	Enforces
dpdp	India	Aadhaar / PAN / card / phone blocked from prompts & tool args; consent-bypass blocked
rbi_ml_risk	India Banking	auto-approval-without-review blocked; fund-disbursal routed to approval
eu_ai_act	EU	human-oversight bypass (Art. 14) & logging suppression (Art. 12) blocked; PII protection
iso42001	Global	concealing AI involvement blocked

---

Manual step control

import openai
import trustlayer as tl

tracker = tl.init(api_key="tl_live_YOUR_KEY", auto_capture=False)

def my_agent(task: str) -> str:
    with tl.using("my-agent"):
        with tracker.llm_call(label="generate", model="gpt-4o", prompt=task) as step:
            resp = openai.chat.completions.create(
                model="gpt-4o",
                messages=[{"role": "user", "content": task}],
            )
            step.prompt_tokens     = resp.usage.prompt_tokens
            step.completion_tokens = resp.usage.completion_tokens
            return resp.choices[0].message.content

# For tools:  with tracker.tool_call("send_email", {"to": addr}): ...

Kill switch

Pass kill_switch=True to tl.init(). When you trigger a kill from the dashboard, the next LLM/tool call raises KillSwitchTriggered in under ~100 ms.

CI/CD compliance gate

# Blocks the deploy (exit 1) if any agent is below the threshold
trustlayer gate --pre-deploy --fail-below 80

---

tl.init() parameters

Parameter	Type	Description
api_key	str	Your FORMA API key (tl_live_… / tl_test_…)
enforce	list[str]	Framework packs enforced on every call, e.g. ["dpdp"]
human_sponsor	str	Accountable human (EU AI Act Art. 14 / RBI)
auto_capture	bool	Auto-patch OpenAI/Anthropic/LangChain/LiteLLM (default True)
kill_switch	bool	Start the process-level kill watcher (default False)
compliance	list[str]	Frameworks for scoring/reports
require_approval_when	callable	Lambda on approval context; return True to require human review
approval_message	str	Message shown in the Approvals inbox

---

Node.js / TypeScript

npm install forma-sdk

import * as forma from "forma-sdk";

forma.init({ apiKey: "tl_live_YOUR_KEY", humanSponsor: "[e-mail]" });

const { decision } = await forma.gate("agent-id", {
    actionType: "llm_call",
    prompt: userPrompt,
});

Note: The Node SDK is coming soon (not yet published to npm). Runtime enforcement (enforce) and approvals are Python-only today. The Node package will provide init + gate first; enforcement parity is on the roadmap.

---

Dashboard & docs

• Dashboard: forma.2bd.net
• Developer guide: forma.2bd.net/developer-guide
• Generate a tailored snippet: forma.2bd.net/snippet-generator

License

MIT — see LICENSE.