ErdosFAI · part of ErdosFL · Erdos Federated Agentic Intelligence

The execution layer for
governed AI agents.

ErdosFAI builds, tests, reinforces, and governs AI agents — then connects them to the systems you already run and drives real work to follow-through. One observable, audited runtime: composable agent cards, multi-agent pipelines, human-in-the-loop safety, continual learning, real-time insights, and a connected execution layer.

  • 60+ connectors
  • Runs offline, no key
  • Audit-ready
  • Apache-2.0
6tightly-integrated layers
60+pre-built connectors
8governed workflow templates
100%tamper-evident audit chain

How it works

From fragmented systems to governed execution

Three steps to put agents to work across the tools you already run — without replacing any of them.

01

Connect existing systems

Wire in EHRs, labs, ERPs, scheduling, and messaging with 60+ pre-built connectors. Auth lives in your vault — connectors only declare capability and whether they can write.

erdos_fai.execution.connectors
02

Configure governed workflows

Start from a healthcare- or operations-native template — or compose your own. Each declares triggers, risk thresholds, SLA & escalation ladders, and which actions require approval.

erdos_fai.execution.templates
03

Execute with full control

Dry-run first, then go live: score risk, gate every write behind RBAC approval, route tasks, escalate on breach, and capture it all in a hash-chained audit trail.

erdos_fai.execution.routing

The agentic lifecycle

Many tools. One platform.

01

Build

Compose agent cards from prompts, skills, memory, tools, and MCP servers.

BLUE
02

Test

Score agents against rigorous evaluation suites before they ship.

RED
03

Deploy

Run multi-agent pipelines with human-in-the-loop gates.

BLUE
04

Reinforce

Learn from every trajectory — agents that improve release over release.

GREEN
05

Execute & Govern

Drive work across connected systems with policy, cost, and a tamper-evident audit trail.

GREEN

Enterprise agentic technology

Six tightly-integrated layers

Each layer is a real Python package. The core is standard-library only, so it reads, runs, and ships anywhere.

01

Intelligence Layer

Composable agent cards — prompt, skills, memory, MCP servers, and a typed tool library wired into one reusable, versioned object.

erdos_fai.intelligence
02

Orchestration Layer

Multi-agent pipelines — chain agents into steps that pass artifacts forward, with approval gates between them. Low-code by construction.

erdos_fai.orchestration
03

Safety Layer

Multi-approver human-in-the-loop governance, admin-configurable write gates, and PHI/PII-aware redaction on every input and output.

erdos_fai.safety
04

Learning Layer

Trajectory-driven evaluation and optimization, dataset synthesis, and refined memories written back to agents — versioned upgrades.

erdos_fai.learning
05

Insights Layer

Real-time cost & ROI dashboards, agent metrics, event-replay tracing, and a hash-chained, tamper-evident audit trail.

erdos_fai.insights
06

Execution Layer

NEW

Connect real systems and drive governed workflows: 60+ connectors, workflow templates, risk scoring, task routing with SLA escalation, and RBAC — with dry-run simulation.

erdos_fai.execution

Build agents. Keep control.

Don't hand your agentic future to a single model provider — own the lifecycle, end to end.

Get started →

Integrations

60+ pre-built connectors

Connect the systems you already run — across 13 categories — without ripping anything out. Every connector declares whether it can write, so the Safety Layer can gate side effects.

EHR

EpicOracle HealthMEDITECHathenahealthVeradigm

Interoperability

FHIR R4HL7 v2SMART on FHIRRedoxC-CDA

Labs & Diagnostics

LabcorpQuestLISPACS / DICOMRIS

Pharmacy

SurescriptsRxNorm

Scheduling & Capacity

Epic CadenceQGendaOutlook CalendarTeamup

Messaging & Notifications

Twilio SMSWhatsAppSlackTeamsPagerDuty

ERP & Finance

SAPOracle ERPWorkdayNetSuiteCoupa

Payments & Claims

StripeChange HealthcareAvailityWaystar

Identity & Access

OktaEntra IDAuth0

Data & Storage

SnowflakePostgresS3SFTP

Analytics & BI

TableauPower BILooker

Forms & Generic

DocuSignTypeformREST / WebhookMCPGraphQL

List the full catalog any time with erdos-fai connectors.

Use cases

One layer across clinical and operational workflows

Ship-ready templates that turn signals into governed follow-through. Browse them with erdos-fai templates.

Clinical

Inpatient Deterioration & Early Escalation

Watch vitals and labs for deterioration trends and escalate to rapid response before a code.

trigger: new vitals/lab · risk ≥ 0.70 · escalates via SMS & PagerDuty

Discharge Navigation

Surface discharge barriers and route prioritized remediation tasks to nurses and case managers.

trigger: discharge order · risk ≥ 0.50 · routes to case manager

Critical Results Management

Track critical lab and imaging results to closed-loop acknowledgement with audit.

trigger: critical value · risk ≥ 0.80 · read-back to provider

Care Transitions & Follow-up

Assess discharge readiness and coordinate post-discharge appointments and med reconciliation.

trigger: transition flag · books follow-up · reconciles meds

Operational

Transfer & Capacity Planning

Surface expected capacity from admissions and discharges to plan transfers ahead of demand.

trigger: hourly recompute · forecasts net beds · reserves capacity

Hospital Capacity & Patient Flow

Optimize staff allocation against predicted census across ER, OR, and inpatient units.

trigger: census change · proposes staffing · publishes flow dashboard

Procurement Approval Routing

Route cross-system purchase requests through policy-based, multi-level approvals.

trigger: purchase request · risk ≥ 0.65 · approval by amount tier

Insurance Utilization Review

Optimize utilization-review creation and prior-authorization for case managers.

trigger: reviewable service · submits prior auth · creates review task

How it fits together

One governed runtime, end to end

03 · SAFETY — policy · redaction · HITL write gates 05 · INSIGHTS — tracing · cost/ROI · audit trail 02 · ORCHESTRATION — pipeline 01 Intake 01 Triage 01 Referral 04 · LEARNING — trajectory → evaluate → refine ↺ 06 · EXECUTION — connectors · templates · risk · routing · RBAC · dry-run

Get started

From idea to a governed, executed workflow in a few lines

Install

# clone, then from the repo root
pip install -e ./erdos-fai
# live Claude calls (optional)
pip install -e "./erdos-fai[anthropic]"

Build & run a pipeline

from erdos_fai import Agent, AgentCard, Pipeline, Step

triage = Agent(AgentCard(
    name="Triage",
    system="You triage support tickets.",
))
pipe = Pipeline("support", [
    Step("triage", triage, output_key="triage"),
])
print(pipe.run("Dashboard is down").final_output)

Connect & execute a workflow

from erdos_fai import TEMPLATES, Simulator, Signal

wf = TEMPLATES.get("inpatient-deterioration")

# dry-run before anything touches a live system
report = Simulator().simulate(wf, signals=[
    Signal("news2", 7, floor=0, ceiling=9),
])
print(report.render())   # executed=False, writes gated

No API key? It runs offline on the built-in echo provider. Try erdos-fai demo and erdos-fai execute. Set ANTHROPIC_API_KEY to run on claude-opus-4-8.

Deployment

Run it your way

ErdosFAI is open source and runs anywhere — the deployment tiers describe support and scale, not a paywall on the framework.

Open Source

FreeApache-2.0

  • All six layers, full source
  • 60+ connectors & 8 templates
  • Runs offline, no API key
  • Community support
Get the code

Enterprise / Private

Talk to usmulti-site & ICU

  • Private deployment & data residency
  • Complex inpatient & operational flows
  • SSO, audit export, compliance review
  • Priority support
Contact

The product suite

Plan · Build · Test · Execute · Govern — in one platform

Agent Builder

Compose deep agents — skills, tools, memory, MCP — with guardrails baked in.

Evaluation & QA

Continuous scoring, regression detection, and per-metric reports.

Continual Learning

Agents adapt in production, getting smarter with every run.

Workflow Execution

Connectors, templates, risk scoring, task routing, and SLA escalation.

Governance & Audit

HITL approvals, RBAC, write gates, cost control, and tamper-evident logs.

From signals to follow-through — across every connected system.

Build governed agents, connect them to your real tools, and put them to work safely.