Open Source · MIT License · Python 3.10+

Build Python Systems
That Survive Failures

Two open-source SDKs built around one belief — the biggest AI problems in production are not model problems. They are runtime problems.

"Runtime systems don't justify unreliable agents.
They acknowledge that failures are inevitable —
and handle them in a controlled, recoverable way."
No GPU Required No External Services No Cloud Lock-in Pure Python MIT License
Built in public.  ·  Real experiments.  ·  Real failures.  ·  Real recovery.  ·  Open source under MIT.

// open source sdks

Two SDKs. One mission.

Two approaches to the same problem: building Python systems that survive failures.

Entry Level · Start Here
ALGOgent Runtime
Lightweight Runtime Intelligence SDK

A self-contained SDK for building resilient automation scripts and AI pipelines. Synchronous, plug-and-play, zero configuration. Drop it into any Python project and get retry logic, state persistence, checkpoint recovery, and confidence scoring without any external services or async overhead.

Runtime Engine Retry + Backoff State Persistence Checkpoint Recovery Confidence Scoring Event Bus Structured Logging Runtime Metrics
Python 3.10+ Synchronous JSON State MIT
View on GitHub
Advanced · Advanced Runtime Layer
Adaptive Runtime
Runtime Intelligence Layer for Stateful AI Systems

A full async runtime intelligence layer built for production AI systems that need to survive real conditions. Five core engines work together to analyze context, score confidence, make decisions, persist state to SQLite, and recover from crashes automatically — without GPU, without cloud, without heavy ML frameworks.

Context Engine Confidence Engine Decision Engine State Engine Recovery Engine Async Event Bus SQLite Persistence Runtime Metrics
Python 3.11+ Full Async SQLite State MIT
View on GitHub

// side by side

Which one is right for you?

Feature ALGOgent Runtime Adaptive Runtime ★
Target use caseAutomation, simple AI pipelinesLong-running AI systems and automation workloads
Execution modelSynchronousFull async (asyncio)
State persistenceJSON fileSQLite (async)
Checkpoint recovery Built-in Built-in
Confidence scoring Basic Adaptive (decay + history)
Context engine— Risk + stability analysis
Decision engine— Rule-based action selection
Event bus Sync pub/sub Async pub/sub
Structured logging Color-coded
Setup complexityZero configMinimal (pydantic, aiosqlite)
GPU required Never Never
Runs on $5 VPS Designed for it
LicenseMITMIT

// real world experiments

Proof Through Execution

These SDKs are not theoretical concepts.
The following examples were executed using real Python code and runtime scenarios.

algogent — sender.py
$ python -m algogent.examples.sender
SUCCESS
Message Email sent successfully
Status SUCCESS
Provider Gmail SMTP
Execution Completed
ALGOgent Runtime
Existing Automation Script

A third-party Gmail automation script was executed through ALGOgent Runtime without modification.

  • Existing code reused
  • Email delivery successful
  • Pure Python execution
  • No cloud dependency
  • No infrastructure required
Real execution result
algogent — sender.py
$ python -m algogent.examples.sender
FAILED
Message Error sending email
Code 535
Reason Authentication Failed
Status FAILED
Error BadCredentials
ALGOgent Runtime
Failure Detection

The same automation workflow was executed after removing Gmail credentials.

  • Authentication failure detected
  • Error surfaced safely
  • Runtime remained stable
  • Failure path verified
Real failure scenario
adaptive — decision_engine.py
$ python -m adaptive.examples.runtime
SIMULATION
service_overload → throttle_requests
anomaly_detected → flag_for_review
timeout → cache_warmup
degraded_service → health_check
recovery_needed → run_recovery
Adaptive Runtime
Runtime Decision Flow

Multiple runtime events were injected into the system to observe contextual decision making.

  • Context analyzed
  • Confidence calculated
  • Action selected
  • State persisted
  • Recovery workflow triggered
Runtime simulation

// open development

Built in Public

Stateflow Labs is developed openly on GitHub.
Every feature, experiment, and iteration is visible to the community.

View GitHub Follow Development

// runtime philosophy

"Most AI problems in production
are not model problems.
They are runtime problems."

Both SDKs are built around the belief that future AI systems need memory that survives crashes, resilience with checkpoints and retry logic, contextual behavior that adapts to real conditions, and confidence awareness — knowing how certain a decision is.

Not just prompts. Not just workflows. Runtime intelligence.