anusara 1.0.3

Deterministic execution engine with traceable, immutable history

Anusara

Deterministic orchestration runtime for agent workflows.

---

What is Anusara?

Anusara is a deterministic runtime for executing agent workflows.

It executes graphs of agents using:

• deterministic scheduling
• event-sourced execution history
• replay-driven state reconstruction

Every execution becomes:

• replayable
• inspectable
• debuggable
• reproducible

Anusara treats workflow execution as a runtime system problem, not a collection of loosely connected function calls.

---

The Mental Model

Agent Graph
     ↓
Deterministic Execution Engine
     ↓
Event Log (source of truth)
     ↓
Replay • Debug • Observability

Execution is not hidden state.

It is a recorded, replayable system.

---

Why Anusara?

Most agent orchestration systems rely on implicit runtime behavior.

This leads to:

• nondeterministic execution
• difficult debugging
• hidden state transitions
• unreliable retries
• poor reproducibility

Anusara solves this by enforcing:

• deterministic execution
• event log authority
• replay-based debugging
• explicit lifecycle guarantees

---

Design Philosophy

Anusara = Deterministic Event-Sourced Execution Runtime

Not just orchestration.
Not just workflows.

A runtime system for reliable execution.

---

Architecture Overview

flowchart LR

Client[Client / API / CLI]
Client --> Runtime

Runtime[Execution Runtime]

Runtime --> Graph[Graph Compiler]
Runtime --> Registry[Agent Registry]
Runtime --> Router[Router]
Runtime --> Mutation[Mutation Engine]

Runtime --> EventLog[(Event Log)]

EventLog --> Replay[Replay Engine]
EventLog --> Debugger[Debugger / Analysis]

Runtime --> Observability[Observability]

---

Core Responsibilities

Layer	Responsibility
Runtime	deterministic execution of workflows
Event Log	authoritative execution history
Router	execution decision logic
Mutation Engine	controlled graph evolution
Registry	agent discovery and lifecycle
Observability	debugging, metrics, visualization

---

Quick Start

Install:

pip install anusara

Minimal example:

from anusara import ExecutionEngine, GraphDefinition

graph = GraphDefinition(
    nodes=[
        {"id": "A", "agent": agent_a},
        {"id": "B", "agent": agent_b},
    ],
    edges=[("A", "B")]
)

engine = ExecutionEngine()
result = engine.run(graph, input_data)

The runtime handles:

• scheduling
• retries
• event logging
• replay
• observability

---

Execution Graph

Workflows are defined as directed graphs.

graph LR
    A --> B
    A --> C

    subgraph Wave_0
        A
    end

    subgraph Wave_1
        B
        C
    end

Execution proceeds in deterministic waves.

---

Key Features

• deterministic execution
• event-sourced execution history
• replayable workflows
• graph-based orchestration
• built-in observability
• runtime debugging tools
• controlled workflow mutation

---

Documentation

Documentation is available in the docs/ directory.

Concepts

• deterministic execution
• event sourcing
• execution waves
• replay

Guides

• building workflows
• running executions
• debugging with replay

Architecture

• execution model
• routing model
• state machine
• replay model
• mutation model

Roadmap

See: docs/roadmap.md

---

Project Status

Anusara is under active development.

Current focus:

• developer experience (API & usability)
• onboarding workflows
• improved tooling

---

Contributing

Contributions and discussions are welcome.

• CONTRIBUTING.md
• CODE_OF_CONDUCT.md
• SECURITY.md

---

License

MIT License