> ## Documentation Index
> Fetch the complete documentation index at: https://www.edgee.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Welcome to Edgee
> The Agent Gateway for Claude Code, Codex, OpenCode, and any coding agent. Compress, Route, Observe.
Edgee is an **Agent Gateway**, the infrastructure layer between your coding agent (Claude Code, Codex, OpenCode, Cursor) and the LLM provider APIs (Anthropic, OpenAI, GLM, others). It applies three things to every request: **compression of context**, **intelligent routing across providers**, and **observability of token consumption**.
## The three pillars
Surgical removal of redundancy from what enters and leaves the model. Two layers: **Input** (\~99% of token volume) and **Output** (\~1%, high ROI).
Per-request fallback on provider 5xx and timeouts. Plan-cap continuity for Claude Pro/Max users when quota is hit. Configurable provider chain.
Every request, every compression event, every cost delta — at session level locally and at team level in the managed console.
## Coding agents, start in seconds
```bash theme={"dark"}
curl -fsSL https://install.edgee.ai | bash
```
```bash theme={"dark"}
brew install edgee-ai/tap/edgee
```
```powershell theme={"dark"}
irm https://install.edgee.ai/install.ps1 | iex
```
```bash theme={"dark"}
edgee launch claude
```
```bash theme={"dark"}
edgee launch codex
```
```bash theme={"dark"}
edgee launch opencode
```
Your coding agent now runs through Edgee with compression, routing, and metering active. The CLI prints a session-analytics link on exit.
## Use the API directly
```typescript theme={"dark"}
import Edgee from 'edgee';
const edgee = new Edgee("your-api-key");
const response = await edgee.send({
model: 'gpt-5.2',
input: 'What is the capital of France?',
});
console.log(response.text);
if (response.compression) {
console.log(`Tokens saved: ${response.compression.saved_tokens}`);
}
```
```python theme={"dark"}
from edgee import Edgee
edgee = Edgee("your-api-key")
response = edgee.send(
model="gpt-5.2",
input="What is the capital of France?"
)
print(response.text)
if response.compression:
print(f"Tokens saved: {response.compression.saved_tokens}")
```
```go theme={"dark"}
package main
import (
"fmt"
"log"
"github.com/edgee-ai/go-sdk/edgee"
)
func main() {
client, _ := edgee.NewClient("your-api-key")
response, err := client.Send("gpt-5.2", "What is the capital of France?")
if err != nil {
log.Fatal(err)
}
fmt.Println(response.Text())
if response.Compression != nil {
fmt.Printf("Tokens saved: %d\n", response.Compression.SavedTokens)
}
}
```
```rust theme={"dark"}
use edgee::Edgee;
let client = Edgee::with_api_key("your-api-key");
let response = client.send("gpt-5.2", "What is the capital of France?").await.unwrap();
println!("{}", response.text().unwrap_or(""));
if let Some(compression) = &response.compression {
println!("Tokens saved: {}", compression.saved_tokens);
}
```
```typescript theme={"dark"}
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://api.edgee.ai/v1",
apiKey: process.env.EDGEE_API_KEY,
});
const completion = await openai.chat.completions.create({
model: "gpt-5.2",
messages: [
{ role: "user", content: "What is the capital of France?" }
],
});
console.log(completion.choices[0].message.content);
```
```typescript theme={"dark"}
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
baseURL: 'https://api.edgee.ai',
apiKey: process.env.EDGEE_API_KEY,
});
const message = await client.messages.create({
model: 'claude-sonnet-4.5',
max_tokens: 1024,
messages: [
{ role: 'user', content: 'What is the capital of France?' }
]
});
console.log(message.content);
```
```python theme={"dark"}
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
import os
llm = ChatOpenAI(
base_url="https://api.edgee.ai/v1",
api_key=os.getenv("EDGEE_API_KEY"),
model="gpt-5.2",
)
response = llm.invoke([HumanMessage(content="What is the capital of France?")])
print(response.content)
```
```bash theme={"dark"}
curl https://api.edgee.ai/v1/chat/completions \
-H "Authorization: Bearer $EDGEE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.2","messages":[{"role":"user","content":"What is the capital of France?"}]}'
```
Edgee works with any OpenAI or Anthropic-compatible client by setting `baseURL` to `https://api.edgee.ai`.
## Next steps
The longer pitch — three pillars, OSS ecosystem, all the receipts.
Talk to us about the managed Edgee console for teams.