ct-toolkit 0.3.16

Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems

Computational Theseus Toolkit (CT Toolkit)

Identity Continuity Guardrails for Agentic Systems

CT Toolkit is an open-source security layer designed to preserve the identity continuity of AI agents over time. It implements the Nested Agentic Architecture (NAA) framework to prevent Sequential Self-Compression (SSC) in multi-agent hierarchies.

---

📖 Official Documentation

For full API reference, architecture details, examples, and integration guides, visit our documentation site: 👉 https://hakandamar.github.io/ct-toolkit/

• Live Examples & Case Studies: Real-world scenarios like Financial Auditor Integrity.

---

Why CT Toolkit?

In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.

• Staged Approval (Cooldown): Verify risky kernel updates in a sandbox via shadow requests before production promotion.
• Passive Context Compression Detection: Automatically detects silent provider-side history compression (e.g., OpenAI/Anthropic).
• Constitutional Kernels: Axiomatic identity anchors.
• Standalone Auditor CLI: Rapidly audit any LLM endpoint for identity drift without writing code.
• Autonomous Self-Correction: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
• Divergence Engine: Multi-tiered drift analysis (L1/L2/L3).
• Hierarchical Propagation: Mother-to-child constraint inheritance.
• Provenance Log: Immutable HMAC-signed interaction history.

---

Quick Start

pip install ct-toolkit

from ct_toolkit import TheseusWrapper, WrapperConfig

# Protect against silent provider context compression
config = WrapperConfig(compression_passive_detection=True)

# One-line injection for any LLM provider
client = TheseusWrapper(provider="openai", config=config)

# Guardrails and drift analysis applied automatically
response = client.chat("What are your core security axioms?")

print(response.content)
print(f"Divergence Score: {response.divergence_score}")

🔍 Standalone Auditor (CLI)

Audit any LLM endpoint (OpenAI, Ollama, LM Studio) directly from your terminal:

# Audit a local Ollama model
ct-toolkit audit --url http://localhost:11434/v1 --kernel defense

# List available kernels and templates
ct-toolkit list-kernels
ct-toolkit list-templates

---

🚦 Project Health & Status

Metric	Status
Tests	✅ 293 passed, 3 skipped, 13 warnings (93% coverage)
Downloads
Last Phase	✅ v0.3.16: Added custom judge_model and fixed Ollama L3 runner
Current Goal	🔶 Phase 7: Multi-Agent Synchronization (Integration)

Framework & Model Support

Seamlessly integrate with your favorite frameworks and local models:

• Local Models: Support for LM Studio, Ollama, and local Qwen/Llama endpoints.
• LangChain & Deep Agents: wrap_deep_agent_factory.
• CrewAI: TheseusCrewMiddleware.apply_to_crew.
• AutoGen: register_reply hooks.

---

Theoretical Foundation

Translating the framework proposed in The Computational Theseus (2025) into engineering practice.

---

License

Apache License 2.0.