Feature
Framework Integrations
One governance layer for all your AI. 100 native adapters across Python, JavaScript, Ruby, Go, Rust, Java, PHP, and .NET. Write policies once, enforce everywhere.
Try It Live
116 Framework Adapters
Native integration across 11 SDKs: Python, JavaScript, Ruby, Go, Rust, Java, PHP, .NET, Swift, Elixir, and Kotlin
LLM Provider SDKs
OpenAI SDK
Direct API
Anthropic SDK
Claude API
Google Gemini
Gemini API
AWS Bedrock
Multi-model
Azure OpenAI
Enterprise
Cohere
Chat/Embed
LangChain
Orchestration
LlamaIndex
RAG pipelines
Haystack
NLP pipelines
Semantic Kernel
Microsoft SDK
LiteLLM
100+ LLMs
Ollama
Local LLMs
vLLM
High-perf
CrewAI
Multi-agent
AutoGen
Microsoft
OpenAI Agents
Swarm SDK
MetaGPT
Multi-agent
BabyAGI
Task-driven
SuperAGI
Autonomous
AgentGPT
Browser
Pydantic AI
Type-safe
Instructor
Structured
DSPy
Declarative
Guidance
Templates
LMQL
Query lang
Outlines
Constrained
Marvin
AI functions
Guardrails AI
Validation
NeMo Guardrails
NVIDIA
Langflow
Visual
Flowise
No-code
Dify
LLMOps
ChromaDB
AI-native
Pinecone
Managed
Weaviate
Vector search
Qdrant
Similarity
Milvus
Scalable
LangSmith
Tracing
Langfuse
Analytics
Phoenix
Arize
Helicone
Monitoring
W&B
Experiments
Arize
ML Ops
Portkey
Gateway
PromptLayer
Prompts
Humanloop
Optimize
FastAPI
Async
Django
Full-stack
Flask
Micro
Express
Node.js web
Fastify
Fast & low overhead
Koa
Next-gen Node
Hono
Ultrafast web
Hapi
Plugin-based
NestJS
Enterprise Node
Next.js
React framework
Remix
Full stack React
SvelteKit
Svelte framework
Nuxt
Vue framework
Astro
Content sites
Elysia
Bun framework
Fresh
Deno framework
Bun.serve
Bun native
LangChain.js
JS chains
Vercel AI
AI SDK
tRPC
Type-safe APIs
GraphQL Yoga
GraphQL server
Socket.io
Real-time
ws
WebSocket
Rails
Full-stack Ruby
Sinatra
Micro framework
Grape
API framework
Gin
HTTP framework
Echo
High perf web
Fiber
Express-like
Chi
Lightweight router
Actix-web
Powerful actor
Axum
Tokio-based
Rocket
Type-safe web
Spring Boot
Enterprise Java
Quarkus
Cloud native
Micronaut
Modular JVM
Laravel
Full-stack PHP
Symfony
Enterprise PHP
Core
Standalone
ASP.NET Core
Web framework
Core
Standalone
Integration Examples
LangChain
from tork.adapters import LangChainAdapter
from langchain.chains import LLMChain
adapter = LangChainAdapter("policy.yaml")
# Wrap any chain
chain = LLMChain(llm=llm, prompt=prompt)
governed_chain = adapter.wrap(chain)
# Use normally - governance is automatic
result = governed_chain.run("User input here")CrewAI
from tork.adapters import CrewAIAdapter
from crewai import Crew, Agent
adapter = CrewAIAdapter("policy.yaml")
# Wrap entire crew
crew = Crew(agents=[agent1, agent2], tasks=[task1])
governed_crew = adapter.wrap(crew)
# Agent communications are governed
result = governed_crew.kickoff()OpenAI Direct
from tork.adapters import OpenAIAdapter
from openai import OpenAI
adapter = OpenAIAdapter("policy.yaml")
client = OpenAI()
# Wrap the client
governed_client = adapter.wrap(client)
# All completions are governed
response = governed_client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Hello"}]
)Why Framework Agnostic?
Write Once, Govern Everywhere
Same policy.yaml works across all frameworks. No rewriting rules when you switch.
Consistent Compliance
Whether using LangChain in prod or testing with raw OpenAI calls, same governance applies.
Easy Migration
Move from one framework to another without rebuilding your compliance layer.
Multi-Framework Support
Running CrewAI for agents and LangChain for RAG? One Tork instance governs both.
Future-Proof
New framework released? Our SDK lets you add governance in hours, not weeks.