kairos-ark 0.1.8

KAIROS-ARK: A deterministic multi-threaded scheduler for agentic AI workflows

KAIROS-ARK

The Operating System for Agentic AI

Overview

KAIROS-ARK is a high-performance, deterministic execution kernel designed for mission-critical agentic AI workflows. Unlike traditional frameworks that prioritize prompt engineering, KAIROS-ARK prioritizes system integrity, reproducibility, and industrial-grade governance.

It provides a specialized "Operating System" for agents, handling:

• Scheduling: Deterministic, multi-threaded task execution.
• Memory: Zero-copy shared memory for large datasets.
• Security: Kernel-level policy enforcement and sandboxing.
• Time: Logical clocks for bit-for-bit identical replay debugging.
• Governance: Human-in-the-Loop (HITL) approvals and cryptographic audit logs.

---

Key Features

Feature	Description
⚡ High Throughput	Process 720,000+ nodes/second with Rust-native execution.
🔒 Policy Engine	Restrict agent capabilities (Network, FS, Exec) at the kernel level.
⏱️ Time-Travel	Replay any execution from a ledger with 100% determinism.
🚀 Zero-Copy	Pass GB-sized payloads between tasks in microseconds.
🤝 Interoperability	Native adapters for LangGraph, CrewAI, and MCP tools.
🛡️ Governance	Cryptographically signed audit logs and enforced HITL protocols.

---

Installation

pip install kairos-ark

Or build from source for maximum performance:

git clone https://github.com/YASSERRMD/KAIROS-ARK.git
cd KAIROS-ARK
pip install maturin
maturin develop

---

Quick Start

1. Hello World Agent

from kairos_ark import Agent

# Create a deterministic agent
agent = Agent(seed=42)

# Add tasks (nodes)
agent.add_node("fetch", lambda: {"data": "raw data"})
agent.add_node("process", lambda: {"status": "processed"})

# Connect workflow
agent.connect("fetch", "process")

# Execute
results = agent.execute("fetch")
print(f"Executed {len(results)} nodes")

2. Parallel Execution

KAIROS-ARK uses a Rayon-backed thread pool for true parallelism:

# Fork execution into parallel branches
agent.add_fork("start_parallel", ["scrape_web", "query_db", "check_cache"])

# Join results
agent.add_join("sync_results", ["scrape_web", "query_db", "check_cache"])

agent.execute("start_parallel")

---

Core Capabilities

🛡️ Security & Policy Engine

Prevent "excessive agency" by sandboxing tools at the kernel level.

from kairos_ark import Agent, Policy, Cap

# Define a restrictive policy
policy = Policy(
    allowed_capabilities=[Cap.LLM_CALL],       # Only allow LLM calls
    max_tool_calls={"web_search": 5},          # Rate limit specific tools
    forbidden_content=["password", "api_key"]  # Automatic redaction
)

# Run agent with policy
agent.run("start", policy=policy)

💾 Persistence & Time-Travel Debugging

Debug "Heisenbugs" by replaying execution logs exactly as they happened.

# 1. Save execution ledger
agent.save_ledger("run_001.jsonl")

# 2. Replay later (reconstructs state without re-running side effects)
state = agent.replay("run_001.jsonl")
print(f"Final State: {state['node_outputs']}")

# 3. Create Snapshots for fast recovery
agent.create_snapshot("checkpoint.json", "run_001")

🚀 Zero-Copy Shared Memory

Pass large objects (images, embeddings, codebases) between Python/Rust without serialization overhead.

# Write 1GB data once (~5µs latency)
handle = agent.kernel.write_shared(large_data_list)

# Pass unique handle to other nodes
result = agent.kernel.read_shared(handle)

🤝 Interoperability & Ecosystem

KAIROS-ARK acts as a native backend for other frameworks, with built-in adapters.

# 1. LangGraph Adapter (Native Checkpointer)
from kairos_ark.integrations.langgraph import ArkNativeCheckpointer
checkpointer = ArkNativeCheckpointer(agent)

# 2. Universal Connectors
from kairos_ark.connectors import (
    ArkGeminiConnector,
    ArkOpenAIConnector,
    ArkClaudeConnector,
    ArkOllamaConnector,
    ArkCohereConnector
)

# Gemini (Google)
llm = ArkGeminiConnector(model_name="gemini-2.0-flash-lite")

# Cohere (Enterprise)
cohere = ArkCohereConnector(model="command-r-plus")

# OpenAI / Groq / DeepSeek
groq = ArkOpenAIConnector(
    base_url="https://api.groq.com/openai/v1",
    api_key="gsk_...",
    model="llama3-70b-8192"
)

# Local (Ollama)
local_llm = ArkOllamaConnector(model="llama3")

# 3. Native Tools (Zero-Copy Ready)
from kairos_ark.tools import ArkTools
results = ArkTools.tavily_search("KAIROS-ARK Architecture")

Kernel-Level Support

# State Store (~4µs access)
agent.kernel.state_set("messages", json.dumps(history))

# MCP Tool Registry
agent.kernel.mcp_register_tool("search", "Search tool")

⚖️ Governance & HITL

Industrial-grade compliance features built-in.

# 1. Human-in-the-Loop (HITL) Interrupts
req_id = agent.kernel.request_approval("run_1", "deploy", "Deploy to prod?")
# Execution suspends until approved
agent.kernel.approve(req_id, "admin_user")

# 2. Cryptographic Verification
ledger = agent.get_audit_log_json()
signed = agent.kernel.sign_ledger(ledger, "run_1")
is_valid = agent.kernel.verify_ledger(signed)

---

Documentation

• Getting Started Guide: Build your first agent in 5 minutes.
• The Scheduler: Deep dive into logical clocks and determinism.
• Policy Engine: Configuring capabilities and sandboxes.
• Zero-Copy Memory: Optimizing for large-scale data.
• Time-Travel Debugging: Mastering the Replay Engine.

---

Benchmarks

KAIROS-ARK is built for speed.

[!NOTE] All benchmarks were executed with native execution only. Python was not present in the hot path.

Category	Metric	Performance	Verdict
Core	Kernel Overhead	8.37 µs / node	🚀 10x Faster than Frameworks
Core	Tool Chaining	0.45 ms (Total)	⚡ Instant
Core	Determinism	Byte-for-Byte Match	✅ Exact Replay
Core	Parallelism	206ms (4x 200ms)	🧵 True Parallel Fan-out
Throughput	Node Throughput	720,000+ nodes/sec	High Frequency
Latency	Task Dispatch	~1.4 µs	Real-time
Latency	Policy Check	~3.0 µs	Zero-Cost Security
Latency	State Store	~4.0 µs	Fast IPC

---

License

MIT License - see LICENSE for details.

Author

YASSERRMD