diff --git a/README.md b/README.md
index ef4d9c8..5224504 100644
--- a/README.md
+++ b/README.md
@@ -1,34 +1,37 @@
-# **Invariant Proxy**
+# Invariant Gateway
-Invariant Proxy is a lightweight Docker service that acts as an intermediary between AI Agents and LLM providers (such as OpenAI and Anthropic). It captures and forwards agent interactions to the [Invariant Explorer](https://explorer.invariantlabs.ai/), enabling seamless debugging, visualization, and exploration of traces.
+**LLM proxy to observe and debug what your AI agents are doing.**
-
+[Documentation](https://explorer.invariantlabs.ai/docs/gateway) | [Quickstart for Users](#quickstart-for-users) | [Quickstart for Developers](#quickstart-for-developers)
----
+Invariant Gateway is a lightweight _zero-configuration_ service that acts as an intermediary between AI Agents and LLM providers (such as OpenAI and Anthropic).
-## **Why Use Invariant Proxy?**
-- ✅ **Intercept AI interactions** for better debugging and analysis.
-- ✅ **Seamlessly forward API requests** to OpenAI, Anthropic, and other LLM providers (**supports streaming responses too**).
-- ✅ **Works with AI Agent platforms and systems** like OpenHands, SWE-agent, etc.
-- ✅ **Automatically store and organize traces** in the Invariant Explorer.
+Gateway automatically traces agent interactions and stores them in the [Invariant Explorer](https://explorer.invariantlabs.ai/), giving you insights into what your agents are doing.
+This enables you to _observe and debug_ your agents in [Invariant Explorer](https://explorer.invariantlabs.ai/).
----
+
+
-## **Getting Started**
+
+
+
-### **Run the Proxy Locally**
-To start the Invariant Proxy, run:
+
+
-```bash
-bash run.sh build && bash run.sh up
-```
+- [x] **Single Line Setup**: Just change the base URL of your LLM provider to the Invariant Gateway.
+- [x] **Intercepts agents on an LLM-level** for better debugging and analysis.
+- [x] **Tool Calling and Computer Use Support** to capture all forms of agentic interactions.
+- [x] **Seamless forwarding and LLM streaming** to OpenAI, Anthropic, and other LLM providers.
+- [x] **Store and organize runtime traces** in the [Invariant Explorer](https://explorer.invariantlabs.ai/).
-This will launch the proxy at [http://localhost:8005/api/v1/proxy/](http://localhost:8005/api/v1/proxy/docs/).
+## **Quickstart for Teams and Users**
-### **Set Up an Invariant API Key**
-1. Follow the instructions [here](https://explorer.invariantlabs.ai/docs/explorer/api/client-setup/) to obtain an API key. This allows the proxy to push traces to [Invariant Explorer](https://explorer.invariantlabs.ai).
+Looking to observe and secure AI agents in your organization? See our [no-code quickstart guide for users](#quickstart-for-users) to get started.
----
+## **Quickstart for Developers**
+
+To add Gateway to your agentic system, follow onf of the integration guides below, depending on the LLM provider.
## **Integration Guides**
@@ -37,7 +40,7 @@ This will launch the proxy at [http://localhost:8005/api/v1/proxy/](http://local
1. Follow [these steps](https://platform.openai.com/docs/quickstart#create-and-export-an-api-key) to obtain an OpenAI API key.
2. **Modify OpenAI Client Setup**
- Instead of connecting directly to OpenAI, configure your `OpenAI` client to use the proxy:
+ Instead of connecting directly to OpenAI, configure your `OpenAI` client to use Gateway:
```python
from httpx import Client
@@ -49,7 +52,7 @@ This will launch the proxy at [http://localhost:8005/api/v1/proxy/](http://local
"Invariant-Authorization": "Bearer your-invariant-api-key"
},
),
- base_url="http://localhost:8005/api/v1/proxy/{add-your-dataset-name-here}/openai",
+ base_url="https://explorer.invariantlabs.ai/api/v1/gateway/{add-your-dataset-name-here}/openai",
)
```
@@ -70,24 +73,77 @@ This will launch the proxy at [http://localhost:8005/api/v1/proxy/](http://local
"Invariant-Authorization": "Bearer your-invariant-api-key"
},
),
- base_url="http://localhost:8005/api/v1/proxy/{add-your-dataset-name-here}/anthropic",
+ base_url="https://explorer.invariantlabs.ai/api/v1/gateway/{add-your-dataset-name-here}/anthropic",
)
```
> **Note:** Do not include the curly braces `{}`. If the dataset does not exist in Invariant Explorer, it will be created before adding traces.
+
+### **🔹 OpenAI Swarm Integration**
+
+Integrating directly with a specific agent framework is also supported, simply by configuring the underlying LLM client.
+
+For instance, [OpenAI Swarm](https://github.com/openai/swarm) relies on OpenAI's Python client, the setup is very similar to the standard OpenAI integration:
+
+```python
+from swarm import Swarm, Agent
+from openai import OpenAI
+from httpx import Client
+import os
+
+client = Swarm(
+ client=OpenAI(
+ http_client=Client(headers={"Invariant-Authorization": "Bearer " + os.getenv("INVARIANT_API_KEY", "")}),
+ base_url="https://explorer.invariantlabs.ai/api/v1/proxy/weather-swarm-agent/openai",
+ )
+)
+
+
+def get_weather():
+ return "It's sunny."
+
+
+agent = Agent(
+ name="Agent A",
+ instructions="You are a helpful agent.",
+ functions=[get_weather],
+)
+
+response = client.run(
+ agent=agent,
+ messages=[{"role": "user", "content": "What's the weather?"}],
+)
+
+print(response.messages[-1]["content"])
+# Output: "It seems to be sunny."
+```
+
---
-## **OpenHands Integration**
+## Quickstart for Users
+
+If you are not building an agent yourself but would like to observe and secure AI agents in your organization, you can do so by configuring the agents to use the Gateway.
+
+See below for example integrations with popular agents.
+
+### **OpenHands Integration**
+
[OpenHands](https://github.com/All-Hands-AI/OpenHands) (formerly OpenDevin) is a platform for software development agents powered by AI.
-### **How to Integrate OpenHands with Invariant Proxy**
+#### **How to Integrate OpenHands with Invariant Gateway**
-#### **Step 1: Modify the API Base**
-Enable the `Advanced Options` toggle under settings and update the `Base URL`:
+##### **Step 1: Modify the API Base**
+
+Enable the `Advanced Options` toggle under settings and update the `Base URL` to the following
+
+```
+https://explorer.invariantlabs.ai/api/v1/gateway/{add-your-dataset-name-here}/openai
+```
-#### **Step 2: Adjust the API Key Format**
+##### **Step 2: Adjust the API Key Format**
+
Set the API Key using the following format:
```text
@@ -96,27 +152,30 @@ Set the API Key using the following format:
> **Note:** Do not include the curly braces `{}`.
-The Invariant Proxy extracts the `invariant-auth` field from the API key and correctly forwards it to Invariant Explorer while sending the actual API key to OpenAI or Anthropic.
+The Invariant Gateway extracts the `invariant-auth` field from the API key and correctly forwards it to Invariant Explorer while sending the actual API key to OpenAI or Anthropic.
---
-## **SWE-agent Integration**
+### **SWE-agent Integration**
+
[SWE-agent](https://github.com/SWE-agent/SWE-agent) allows your preferred language model (e.g., GPT-4o or Claude Sonnet 3.5) to autonomously utilize tools for various tasks, such as fixing issues in real GitHub repositories.
-### **Using SWE-agent with Invariant Proxy**
-SWE-agent does not support custom headers, so you **cannot** pass the Invariant API Key via `Invariant-Authorization`. However, **there is a workaround** using the Invariant Proxy.
+#### **Using SWE-agent with Invariant Gateway**
-#### **Step 1: Modify the API Base**
+SWE-agent does not support custom headers, so you **cannot** pass the Invariant API Key via `Invariant-Authorization`. However, **there is a workaround** using the Invariant Gateway.
+
+##### **Step 1: Modify the API Base**
Run `sweagent` with the following flag:
```bash
---agent.model.api_base=http://localhost:8005/api/v1/proxy/{add-your-dataset-name-here}/openai
+--agent.model.api_base=https://explorer.invariantlabs.ai/api/v1/gateway/{add-your-dataset-name-here}/openai
```
> **Note:** Do not include the curly braces `{}`.
-#### **Step 2: Adjust the API Key Format**
+##### **Step 2: Adjust the API Key Format**
+
Instead of setting your API Key normally, modify the environment variable as follows:
```bash
@@ -126,19 +185,38 @@ export ANTHROPIC_API_KEY={your-anthropic-api-key}|invariant-auth: {your-invarian
> **Note:** Do not include the curly braces `{}`.
-This setup ensures that SWE-agent works seamlessly with Invariant Proxy, maintaining compatibility while enabling full functionality. 🚀
+This setup ensures that SWE-agent works seamlessly with Invariant Gateway, maintaining compatibility while enabling full functionality. 🚀
+
+---
+
+## **Run the Gateway Locally**
+
+You can also operate your own instance of the Gateway, to ensure privacy and security.
+
+First, clone this repository. To start the Invariant Gateway, run:
+
+```bash
+bash run.sh build && bash run.sh up
+```
+
+This will launch Gateway at [http://localhost:8005/api/v1/gateway/](http://localhost:8005/api/v1/gateway/docs/).
+
+### **Set Up an Invariant API Key**
+
+1. Follow the instructions [here](https://explorer.invariantlabs.ai/docs/explorer/api/client-setup/) to obtain an API key. This allows the gateway to push traces to [Invariant Explorer](https://explorer.invariantlabs.ai).
---
## **Development**
### **Pushing to Local Explorer**
-By default the proxy points to the Production Explorer instance. To point it to your local Explorer instance, modify the `INVARIANT_API_URL` value inside `.env`. Follow instructions in `.env` on how to point to the local instance.
+
+By default Gateway points to the public Explorer instance at `explorer.invariantlabs.ai`. To point it to your local Explorer instance, modify the `INVARIANT_API_URL` value inside `.env`. Follow instructions in `.env` on how to point to the local instance.
### **Run Tests**
+
To run tests, execute:
```bash
./run.sh tests
```
-
diff --git a/resources/images/overview.svg b/resources/images/overview.svg
new file mode 100644
index 0000000..0deb4f1
--- /dev/null
+++ b/resources/images/overview.svg
@@ -0,0 +1,60 @@
+
+
\ No newline at end of file
+
-#### **Step 2: Adjust the API Key Format**
+##### **Step 2: Adjust the API Key Format**
+
Set the API Key using the following format:
```text
@@ -96,27 +152,30 @@ Set the API Key using the following format:
> **Note:** Do not include the curly braces `{}`.
-The Invariant Proxy extracts the `invariant-auth` field from the API key and correctly forwards it to Invariant Explorer while sending the actual API key to OpenAI or Anthropic.
+The Invariant Gateway extracts the `invariant-auth` field from the API key and correctly forwards it to Invariant Explorer while sending the actual API key to OpenAI or Anthropic.
---
-## **SWE-agent Integration**
+### **SWE-agent Integration**
+
[SWE-agent](https://github.com/SWE-agent/SWE-agent) allows your preferred language model (e.g., GPT-4o or Claude Sonnet 3.5) to autonomously utilize tools for various tasks, such as fixing issues in real GitHub repositories.
-### **Using SWE-agent with Invariant Proxy**
-SWE-agent does not support custom headers, so you **cannot** pass the Invariant API Key via `Invariant-Authorization`. However, **there is a workaround** using the Invariant Proxy.
+#### **Using SWE-agent with Invariant Gateway**
-#### **Step 1: Modify the API Base**
+SWE-agent does not support custom headers, so you **cannot** pass the Invariant API Key via `Invariant-Authorization`. However, **there is a workaround** using the Invariant Gateway.
+
+##### **Step 1: Modify the API Base**
Run `sweagent` with the following flag:
```bash
---agent.model.api_base=http://localhost:8005/api/v1/proxy/{add-your-dataset-name-here}/openai
+--agent.model.api_base=https://explorer.invariantlabs.ai/api/v1/gateway/{add-your-dataset-name-here}/openai
```
> **Note:** Do not include the curly braces `{}`.
-#### **Step 2: Adjust the API Key Format**
+##### **Step 2: Adjust the API Key Format**
+
Instead of setting your API Key normally, modify the environment variable as follows:
```bash
@@ -126,19 +185,38 @@ export ANTHROPIC_API_KEY={your-anthropic-api-key}|invariant-auth: {your-invarian
> **Note:** Do not include the curly braces `{}`.
-This setup ensures that SWE-agent works seamlessly with Invariant Proxy, maintaining compatibility while enabling full functionality. 🚀
+This setup ensures that SWE-agent works seamlessly with Invariant Gateway, maintaining compatibility while enabling full functionality. 🚀
+
+---
+
+## **Run the Gateway Locally**
+
+You can also operate your own instance of the Gateway, to ensure privacy and security.
+
+First, clone this repository. To start the Invariant Gateway, run:
+
+```bash
+bash run.sh build && bash run.sh up
+```
+
+This will launch Gateway at [http://localhost:8005/api/v1/gateway/](http://localhost:8005/api/v1/gateway/docs/).
+
+### **Set Up an Invariant API Key**
+
+1. Follow the instructions [here](https://explorer.invariantlabs.ai/docs/explorer/api/client-setup/) to obtain an API key. This allows the gateway to push traces to [Invariant Explorer](https://explorer.invariantlabs.ai).
---
## **Development**
### **Pushing to Local Explorer**
-By default the proxy points to the Production Explorer instance. To point it to your local Explorer instance, modify the `INVARIANT_API_URL` value inside `.env`. Follow instructions in `.env` on how to point to the local instance.
+
+By default Gateway points to the public Explorer instance at `explorer.invariantlabs.ai`. To point it to your local Explorer instance, modify the `INVARIANT_API_URL` value inside `.env`. Follow instructions in `.env` on how to point to the local instance.
### **Run Tests**
+
To run tests, execute:
```bash
./run.sh tests
```
-
diff --git a/resources/images/overview.svg b/resources/images/overview.svg
new file mode 100644
index 0000000..0deb4f1
--- /dev/null
+++ b/resources/images/overview.svg
@@ -0,0 +1,60 @@
+
+
\ No newline at end of file