diff --git a/apps/web/src/app/hostnames.ts b/apps/web/src/app/hostnames.ts new file mode 100644 index 000000000..133e76861 --- /dev/null +++ b/apps/web/src/app/hostnames.ts @@ -0,0 +1,5 @@ +// We are in the process of migrating to the new landing page hosting. +export const landingPageWebflowHostname = 'e2b-dev.webflow.io' +export const landingPageFramerHostname = 'e2b-landing-page.framer.website' +export const blogFramerHostname = 'e2b-blog.framer.website' +export const changelogFramerHostname = 'e2b-changelog.framer.website' diff --git a/apps/web/src/app/sitemap.ts b/apps/web/src/app/sitemap.ts index 175fcf817..38cbc4b48 100644 --- a/apps/web/src/app/sitemap.ts +++ b/apps/web/src/app/sitemap.ts @@ -1,7 +1,7 @@ import { MetadataRoute } from 'next' import { XMLParser } from 'fast-xml-parser' -import { replaceUrls } from '@/utils/replaceUrls' import path from 'path' +import { replaceUrls } from '@/utils/replaceUrls' import { getPageForSitemap } from '@/utils/sitemap' type ChangeFrequency = @@ -57,7 +57,7 @@ async function getXmlData(url: string): Promise { const response = await fetch(url, { cache: 'no-cache' }) if (!response.ok) { - return { urlset: { url: [] }} + return { urlset: { url: [] } } } const text = await response.text() @@ -99,7 +99,7 @@ export default async function sitemap(): Promise { const dashboardPath = path.join(process.cwd(), 'src', 'app', '(dashboard)', 'dashboard') - const dashboardPages = getPageForSitemap(dashboardPath, 'https://e2b.dev/dashboard/', 0.5) + const dashboardPages = getPageForSitemap(dashboardPath, 'https://e2b.dev/dashboard/', 0.5) const docsDirectory = path.join(process.cwd(), 'src', 'app', '(docs)', 'docs') const docsPages = getPageForSitemap(docsDirectory, 'https://e2b.dev/docs/', 0.5).filter( diff --git a/apps/web/src/middleware.ts b/apps/web/src/middleware.ts index b9b8f317d..0f7c8274d 100644 --- a/apps/web/src/middleware.ts +++ b/apps/web/src/middleware.ts @@ -1,5 +1,11 @@ import { NextRequest, NextResponse } from 'next/server' import { replaceUrls } from '@/utils/replaceUrls' +import { + landingPageWebflowHostname, + landingPageFramerHostname, + blogFramerHostname, + changelogFramerHostname, +} from '@/app/hostnames' export async function middleware(req: NextRequest): Promise { if (req.method !== 'GET') return NextResponse.next() @@ -11,43 +17,43 @@ export async function middleware(req: NextRequest): Promise { if (url.pathname === '' || url.pathname === '/') { if (process.env.NODE_ENV === 'production') { - url.hostname = 'e2b-landing-page.framer.website' + url.hostname = landingPageWebflowHostname } else { return NextResponse.redirect(new URL('/dashboard', req.url)) } } if (url.pathname.startsWith('/terms')) { - url.hostname = 'e2b-landing-page.framer.website' + url.hostname = landingPageWebflowHostname } if (url.pathname.startsWith('/privacy')) { - url.hostname = 'e2b-landing-page.framer.website' + url.hostname = landingPageWebflowHostname } if (url.pathname.startsWith('/pricing')) { - url.hostname = 'e2b-landing-page.framer.website' + url.hostname = landingPageWebflowHostname } + // TODO: Not on the new landing page hosting yet if (url.pathname.startsWith('/ai-agents')) { - url.hostname = 'e2b-landing-page.framer.website' + url.hostname = landingPageFramerHostname } if (url.pathname === '/blog' || url.pathname === '/blog/') { url.pathname = '/' - url.hostname = 'e2b-blog.framer.website' + url.hostname = blogFramerHostname } - if (url.pathname.startsWith('/blog')) { - url.hostname = 'e2b-blog.framer.website' + url.hostname = blogFramerHostname } if (url.pathname === '/changelog' || url.pathname === '/changelog/') { url.pathname = '/' - url.hostname = 'e2b-changelog.framer.website' + url.hostname = changelogFramerHostname } if (url.pathname.startsWith('/changelog')) { - url.hostname = 'e2b-changelog.framer.website' + url.hostname = changelogFramerHostname } const res = await fetch(url.toString(), { ...req }) @@ -56,8 +62,12 @@ export async function middleware(req: NextRequest): Promise { // !!! NOTE: Replace has intentionally not completed quotes to catch the rest of the path !!! const modifiedHtmlBody = replaceUrls(htmlBody, url.pathname, 'href="', '">') + // Even though we are paying for a Webflow tier that allows us to remove the badge, it doesn't work. + // eslint-disable-next-line + const scriptRegex = / + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+
+
+
***
+
***
+
+
we just closed a new funding round of $11.5M LED by Decibel
+
+
LEARN MORE →
+ +
+
***
+
***
+
+
+
+
+ +
+
+
+
+
+
+
+
NEW
+
+
DESKTOP SANDBOX FOR COMPUTER USE
+
→
+ +
+
+
+
AI-generated code
+ + + + +
+
+
AI-generated
+ + + + +
+

RUN AI-GENERATED code SECURELY in your APP

+
+
E2B is an open-source runtime for executing AI-generated code in secure cloud + sandboxes. Made for agentic & AI use cases.
+
START FOR FREEVIEW DOCS
+
+
TRUSTED BY
+
+ + +
+ + + + + +
+
+ + + + + +
+
+
+
+
+
+
+
+
LLM
+
+ + + + +
+
+
+
+
+ +
+
+ +
+
+ + +
+
+ + + + + + + + + + +
+
+ +
+
+ + +
+
+
+
[.500]
[.873]
[.542]
[.704]
[.285]
[.717]
[.598]
[.557]
[.232]
[.746]
+
[.211]
[.013]
[.510]
[.718]
[.621]
[.223]
[.124]
[.801]
[.798]
[.117]️
+
[.817]
[.070]
[.353]



‍
[.833]
[.477]
[.620]
+
+ [.829]
[.195]
[.245]
[.891]
[.454]
[.145]
[.984]
[.634]
[.342]
[.746]
+
[.330]
[.103]
[.742]
[.004]
[.165]
[.459]
[.597]
[.910]
[.072]
[.336] +
+
+ + + + +
+
+
+
+ +
+
+ +
+
+ + +
+
+ + + + + + + + + + +
+
+ +
+
+ + +
+
+
+
+
+
]·········[
]·········[
]·········[
+ + + + + +
+
+
+
+
E2B SANDBOX
+
+ + + + +
+
+
+
RUNNING CODE…
+
+
]·····[
]·····[
]·····[
+ + + + + +
+
+
+
+
✶✶
✶✶
✶✶
✶✶



+
✶✶
✶✶
✶✶
✶✶ +
+
✶✶
✶✶
✶✶
✶✶



+
✶✶
✶✶
✶✶
✶✶ +
+
✶✶
✶✶
✶✶
✶✶



+
✶✶
✶✶
✶✶
✶✶ +
+
✶✶
✶✶
✶✶
✶✶



+
✶✶
✶✶
✶✶
✶✶ +
+
+
+ + +
+
+ + +
+
+ + +
+
+ + +
+
+
+
+
]·····[
]·····[
]·····[
+ + + + + +
+
+
[_______________]
+
[%%%%%__________]
+
[%%%%%%%%%%_____]
+
[%%%%%%%%%%%%%%%]
+
+
+
+
CPU: 8 × ▤  /  RAM: 4 GB
+
+
+
]·········[
]·········[
]·········[
+ + + + + +
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
8 – ––––– ––– ––––– ––– ––––– –––
7 + – ––––– ––– @@@@@ ––– ––––– –––
6 – ––––– + ––– @@@@@ ––– ––––– + –––
5 – @@@@@ ––– @@@@@ ––– ––––– –––
4 – + @@@@@ ––– @@@@@ ––– ––––– –––
3 – + @@@@@ ––– @@@@@ ––– @@@@@ –––
2 – @@@@@ ––– @@@@@ ––– @@@@@ –––
1 – @@@@@ ––– @@@@@ ––– @@@@@ –––
–––––––––––––––––––––––––––––––––
      A +         B         C +
+
+
+
✓ CHART-1
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
______    ______    ______
❘ +    ❘_\  ❘    ❘_\  ❘    ❘_\
╔═══════╗ ╔═══════╗ ╔═══════╗
║  CSV +  ║ ║  TXT  ║ ║  .JS  ║
╚═══════╝ ╚═══════╝ ╚═══════╝
❘______❘  ❘______❘  ❘______❘
+
+
+
✓ File
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
╔ Email ══════════════╗
║ your@email.com      + ║
╚═════════════════════╝
╔ Pw + ═════════════════╗
║ ********            ║
╚═════════════════════╝
╔═════════════════════╗
║       Sign In     +   ║
╚═════════════════════╝
+
+
+
✓ UI
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
NVDA                            @
$120.91 +                        @
+32%                          @
                       @@@ +   @
            @@@       @   @ @
          @@   @     @     @
      @@@@      @ +   @
  @@@@           @@@
 @
@
+
+
+
✓ CHART-2
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
1999 @@@@@@@@@@ │         │
1998 @@@ +        │         │
1997 @@@@@@@@@@@@@        │
1996 @@@@@@@    │         │
1995 @@@@@@@@@@@@@@@@     │
1994 + @@@@@@@@@@@@@@@@@@@@@@@@@
1993 @@@@@      │ +         │
1992 @@@@@@@@@@ │ +         │
–––––––––––––––––––––––––––––––––
      2         4         6 +
+
+
+
✓ CHART-3
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
/!\
‍
Error: + [$rootScope:inprog] $apply
already in + progress

http://errors.angular.js.org/1.3
.15/$rootScope/inprog?p0=
%24apply

at angular.js:63
+
+
+
☓ Error
+
+
+
+
+
OUTPUT
+
+ + + + +
+
+
+
8 ––––│–––––––––│–––––––––│–––––@
7 ––––│–––––––––│–––@–––––│––––@–
6 ––––│–––––––––│––@–@–@@@@–––@––
5 ––––│–––––@@@–│–@–––@–––│@–@–@@
4 @@@@│–––@@–––@│@–––@–@––│–@–@––
3 ––––@@@@––@@@@@–––@–––@@│@@@–––
2 –––@│@@@@@––––│@@@––––––│––––––
1 –@@–│–––––––––│–––––––––│––––––
–––––––––––––––––––––––––––––––––
      A +         B         C
+
+
+
✓ CHART-4
+
+
+
+
+
+
+
20K+
+
DEVELOPERS
+
+
+
250K+
+
MONTHLY DOWNLOADS
+
+
+
10M+
+
STARTED SANDBOXES
+
+
+
+
+
+
+
+
+
+
[
+
USE CASES
+
]
+
+
+
+
AI
+ + + + +
+

Build for AI
Use Cases

+
+
From running short AI-generated code snippets, up to fully autonomous AI + agents.
+
+
> HOVER (↓↓)
+
/EXPLORE
+
+
+
+
+
+
+
.CSV
+ + + +
_____
❘   ❘_\
+
+ + +
+
❘_____❘
+
+
+ + + + + + + +
+
+
+

AI Data Analysis

+
From running short AI-generated code snippets, up to fully autonomous AI + agents.
+
See docs +
+
+
+
+
+
+
+    @@@   
@@@@@@   
@@@@@@@@@
+ + + +
+
+ + + + + + + +
+
+
+

AI Data Visualization

+
Run AI-generated code to render charts, plots, and visual outputs based on + your data.
+
See docs +
+
+
+
+
+
+
 ======    
======== 
=== + ===  
<        
+ + + + + + + + + + + + + +
+
+ + + + + + + +
+
+
+

Coding Agents

+
Use sandbox to execute code, use I/O, access the internet, or start + terminal commands.
+
See docs +
+
+
+
+
+
+
╔   ═   ╗
        ╣
       
╚   +   ═  
+ + + + +
+
+ + + + + + + +
+
+
+

Generative UI

+
Use sandbox as a code runtime for AI-generated apps. Supports any language + and framework.
+
See docs +
+
+
+
+
+
+
==╔═══╗==
==║ ✓ ║== ==╚═══╝== +
+ + + + + + +
+
+ + + + + + + +
+
+
+

Codegen Evals

+
Use sandboxes for your codegen gym for popular evals like swe-benchmark or + internal evals.
+
See docs +
+
+
+
+
+
NEW
+
+
+
+ +
+
+ + + + + + + + + + + + + +
+
+
+

Computer Use

+
Use Desktop Sandbox to provide secure virtual computers in cloud for your + LLM.
+
See docs +
+
+
+
+
+
+
+
+
+
[
+
GET STARTED
+
]
+
+
+
+
A FEW LINES
+ + + + +
+

IN YOUR CODE
WITH A FEW LINES

+
+
Need help? Join Discord, check Docs or Email us.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ +
+
NODE.JS
+ +
+ + + + + + + + + +
+
PYTHON
+ +
+ +
+
VERCEL
+ +
+ +
+
OPEN AI
+ +
+ + +
+
ANTHROPIC
+ +
+ + + + + + + + + + +
+
Mistral
+ +
+ +
+
Llama
+ +
+ + + + + + + + +
+
LangChain
+ +
+ +
+
LlamaIndex
+ +
+ + + +
+
More
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
~
~
~
~
~
~
‍~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
 +
+ 
// npm install @e2b/code-interpreter
+import { Sandbox } from '@e2b/code-interpreter'
+
+// Create a E2B Code Interpreter with JavaScript kernel
+const sandbox = await Sandbox.create()
+
+// Execute JavaScript cells
+await sandbox.runCode('x = 1')
+const execution = await sandbox.runCode('x+=1; x')
+
+// Outputs 2
+console.log(execution.text)
+
+ +
+
+
+
“~/index.ts”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
~
~
~
~
~
~
‍~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
+ 
# pip install e2b-code-interpreter
+from e2b_code_interpreter import Sandbox
+
+# Create a E2B Sandbox
+with Sandbox() as sandbox:
+    # Run code
+    sandbox.run_code("x = 1")
+    execution = sandbox.run_code("x+=1; x")
+
+    print(execution.text) # outputs 2
+
+
+
“~/index.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35‍‍
+ 
// npm install ai @ai-sdk/openai zod @e2b/code-interpreter
+import { openai } from '@ai-sdk/openai'
+import { generateText } from 'ai'
+import z from 'zod'
+import { Sandbox } from '@e2b/code-interpreter'
+
+// Create OpenAI client
+const model = openai('gpt-4o')
+
+const prompt = "Calculate how many r's are in the word 'strawberry'"
+
+// Generate text with OpenAI
+const { text } = await generateText({
+  model,
+  prompt,
+  tools: {
+    // Define a tool that runs code in a sandbox
+    codeInterpreter: {
+      description: 'Execute python code in a Jupyter notebook cell and return result',
+      parameters: z.object({
+        code: z.string().describe('The python code to execute in a single cell'),
+      }),
+      execute: async ({ code }) => {
+        // Create a sandbox, execute LLM-generated code, and return the result
+        const sandbox = await Sandbox.create()
+        const { text, results, logs, error } = await sandbox.runCode(code)
+        return results
+      },
+    },
+  },
+  // This is required to feed the tool call result back to the LLM
+  maxSteps: 2
+})
+
+console.log(text)
+
+
+
“~/aisdk_tools.ts”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28‍‍
~
~
~
~
~
~
~
 +
+ 
# pip install openai e2b-code-interpreter
+from openai import OpenAI
+from e2b_code_interpreter import Sandbox
+
+# Create OpenAI client
+client = OpenAI()
+system = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send messages to OpenAI API
+response = client.chat.completions.create(
+    model="gpt-4o",
+    messages=[
+        {"role": "system", "content": system},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract the code from the response
+code = response.choices[0].message.content
+
+# Execute code in E2B Sandbox
+if code:
+    with Sandbox() as sandbox:
+        execution = sandbox.run_code(code)
+        result = execution.text
+
+    print(result)
+
+
+
“~/oai.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28‍‍
~
~
~
~
~
~
~
 +
+ 
# pip install anthropic e2b-code-interpreter
+from anthropic import Anthropic
+from e2b_code_interpreter import Sandbox
+
+# Create Anthropic client
+anthropic = Anthropic()
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send messages to Anthropic API
+response = anthropic.messages.create(
+    model="claude-3-5-sonnet-20240620",
+    max_tokens=1024,
+    messages=[
+        {"role": "assistant", "content": system_prompt},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract code from response
+code = response.content[0].text
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.logs.stdout
+
+print(result)
+
+
+
“~/anth.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30‍‍
~
~
~
~
~
+ 
# pip install mistralai e2b-code-interpreter
+import os
+from mistralai import Mistral
+from e2b_code_interpreter import Sandbox
+
+api_key = os.environ["MISTRAL_API_KEY"]
+
+# Create Mistral client
+client = Mistral(api_key=api_key)
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send the prompt to the model
+response = client.chat.complete(
+    model="codestral-latest",
+    messages=[
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract the code from the response
+code = response.choices[0].message.content
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.text
+
+print(result)
+
+
+
“~/mistral.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25‍‍
~
~
~
~
~
~
~
~
~
~
 +
+ 
# pip install ollama
+import ollama
+from e2b_code_interpreter import Sandbox
+
+# Send the prompt to the model
+response = ollama.chat(model="llama3.2", messages=[
+    {
+        "role": "system",
+        "content": "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+    },
+    {
+        "role": "user",
+        "content": "Calculate how many r's are in the word 'strawberry'"
+    }
+])
+
+# Extract the code from the response
+code = response['message']['content']
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.logs.stdout
+
+print(result)
+
+
+
“~/llama.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30‍‍
~
~
~
~
~
+ 
# pip install langchain langchain-openai e2b-code-interpreter
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from e2b_code_interpreter import Sandbox
+
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Create LangChain components
+llm = ChatOpenAI(model="gpt-4o")
+prompt_template = ChatPromptTemplate.from_messages([
+    ("system", system_prompt),
+    ("human", "{input}")
+])
+
+output_parser = StrOutputParser()
+
+# Create the chain
+chain = prompt_template | llm | output_parser
+
+# Run the chain
+code = chain.invoke({"input": prompt})
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.text
+
+print(result)
+
+
+
“~/lchain.py”
+
+
+
+
+
+
+
+  1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
~
~
~
~
~
~
~
~
~
~
~
~
 +
+ 
from llama_index.core.tools import FunctionTool
+from llama_index.llms.openai import OpenAI
+from llama_index.core.agent import ReActAgent
+from e2b_code_interpreter import Sandbox
+
+# Define the tool
+def execute_python(code: str):
+    with Sandbox() as sandbox:
+        execution = sandbox.run_code(code)
+        return execution.text
+
+e2b_interpreter_tool = FunctionTool.from_defaults(
+    name="execute_python",
+    description="Execute python code in a Jupyter notebook cell and return result",
+    fn=execute_python
+)
+
+# Initialize LLM
+llm = OpenAI(model="gpt-4o")
+
+# Initialize ReAct agent
+agent = ReActAgent.from_tools([e2b_interpreter_tool], llm=llm, verbose=True)
+agent.chat("Calculate how many r's are in the word 'strawberry'")
+
+
+
“~/llindex.py”
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
[
+
FEATURES
+
]
+
+
+
+
FEATURES
+ + + + +
+

FEATURES FOR THE
llm-powered DEVELOPERs

+
+
We built E2B with the next generation of developers in mind — software + engineering AI agents.
+
+
> MADE FOR AI
+
> DSCVR ALL (↓↓)
+
+
+
+
+
+
+ +
+
+
+
+ +
+
+
+
+ +
+
+
+
+ + + + + + + + + + +
+
+
+
+ + +
+
+
+
+ + + + + + + + +
+
+
+
+ + + + + + + + +
+
+
+
+

Works with any LLM

+
Use OpenAI, Llama, Anthropic, Mistral, or your
own custom models. E2B is + LLM-agnostic
and compatible with any model.
+
+
+ + + + +
+
+
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Quick start

+
The E2B Sandboxes in the same region as
the client start in less than + 200 ms.
+
NO COLD STARTS
+
+
+
+
+
+

Run

+
+
+ +
+
+ +
+
+ +
+
+ +
+
+ +
+
+

... or just any other AI-generated code.

+
+
AI-generated Python, JavaScript, Ruby, or C++? Popular framework + or custom library? If you can run it on a Linux box, you can run it in the E2B sandbox.
+
+
+
+
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Quick start

+
The E2B Sandboxes in the same region as
the client start in less than + 200 ms.
+
NO COLD STARTS
+
+
+
+
+
+
Control code execution context
+
+
+
inspect errors
+
+
+
install packages
+
+
+
interactive charts
+
+
+
Filesystem I/O
+
+
+
+

Features made for LLM

+
E2B features are made to turn your
LLM into a competent coder.
+
tailor-made for ai
+
+
+
+
+
+
  ^  
^ ^  
^^^^^
^^ ^^
^^^
+ + + + + + + +
+
+ + + + +
+
+
+

Secure & battle-tested

+
Sandboxes are powered by Firecracker microVM,
a VM made for running untrusted code. +
+
battle-tested
+
+
+
+
+
+
24H
+
+
[
+
+
SANDBOX RUNNING
+
]
+
+
+
+

Up to 24h long sessions

+
Run for a few seconds or several hours, each E2B
sandbox can run up to + 24 hours.
+
AVAILABLE IN PRO
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+
+
+

Install any package or system library with

+
+
+ +
+
+ + + + + + + + +
+
+ +
+
+ +
+
+

and more.

+
+
Completely customize the sandbox for your use case by creating a + custom sandbox template or installing a package when the sandbox is + running. +
+
+
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+ +
+
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+ +
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
*
+
·
+
+
+
+
+
+

Self-hosting

+
Deploy E2B in your AWS, or GCP account
and run sandboxes in your VPC. +
+
I'm interested
+
+
+
+ +
+
SOON
+
+
+
+
+
+
+
+
+
+
+
+
[
+
Cookbook
+
]
+
+
+
+
COOKBOOK
+ + + + +
+

GET INSPIRed BY
OUR COOKBOOK

+
+
Production use cases & full-fledged apps.
+
+
HOVER (↓↓)
+
+
+
+
+
+

Llama 3 with code interpreting and analyzing uploaded dataset

+
Python, Meta
+
+ +
+
+
+

AI Code Execution with Together AI models, JS/TS

+
JS, TS, Meta, Together AI
+
+ +
+
+
+

AI Code Execution with Together AI models, Python

+
Python, Meta, Together AI
+
+ +
+
+
+

Scrape and Analyze Airbnb Data with Firecrawl and E2B

+
JS, TS Firecrawl
+
+ +
+
+
+

OpenAI o1 Code Interpreter in Python

+
Python, OpenAI
+
+ +
+
+
+

OpenAI o1 Code Interpreter in JS/TS

+
JS, TS, OpenAI
+
+ +
+
+
+

Next.js app with LLM + Code Interpreter and streaming

+
JS, TS, Next.js, OpenAI
+
+ +
+
+
+

Code Interpreter with magentic and GPT-4o

+
Python, magentic, OpenAI
+
+ +
+
+
+

Llama 3 + function calling + E2B Code interpreter in Python

+
Python, Meta
+
+ +
+
+
+

Llama 3 + function calling + E2B Code interpreter

+
JS, TS, Meta
+
+ +
+
+
+

LangChain with Code Interpreting

+
Python, LangChain
+
+ +
+
+
+

LangGraph with Code Interpreting

+
Python, LangGraph
+
+ +
+
+
+

GPT-4o Code Interpreter in JS/TS

+
JS, TS, OpenAI
+
+ +
+
+
+

Running code generated by Autogen via E2B Sandbox

+
Python, Autogen
+
+ +
+
+
+

Code interpreting with Fireworks

+
Python, Fireworks AI
+
+ +
+
+
+

Visualizing Website Topics (Claude + Firecrawl + E2B)

+
Python, Anthropic, Firecrawl
+
+ +
+
+
+

AI Code Execution with Mistral's Codestral in Python

+
Python, Mistral
+
+ +
+
+
+

AI Code Execution with Mistral's Codestral in JS

+
JS, TS, Mistral
+
+ +
+
+
+

GPT-4o Code Interpreter in Python

+
Python, OpenAI
+
+ +
+
+
+

Claude Code Interpreter in Python

+
Python, Anthropic
+
+ +
+
+
+

Claude Code Interpreter in JS/TS

+
JS, TS, Anthropic
+
+ +
+
+
+
+
+
+
LOAD MORE
+
+
+
+
+
+
+
+
+
+
[
+
CUSTOMERS
+
]
+
+
+
+
COMPANIES
+ + + + +
+

USED BY TOP
COMPANIES

+
+
From running short AI-generated code snippets, up to fully autonomous AI + agents.
+
+
+
/print("
+
+ +
+
")
+
+
(↓↓)
+
+
+
+ + +
“E2B has a great product that unlocked a new + set of rich answers for our users. We love working with both the product and team behind it.”
— Denis + Yarats, CTO
+
+
Read THE CASE STUDY →
+
+
+
Data Analysis
+
+
+
+
+ +
+
+
+ + +
“It took just one hour to integrate E2B + end-to-end. The performance is excellent, and the support is on another level. Issues are resolved in + minutes.”
— Maciej Donajski, CTO
+
+
+
Finance
+
+
+
Data Processing
+
+
+
+
+ + +
“It took just one hour to integrate E2B + end-to-end. The performance is excellent, and the support is on another level. Issues are resolved in + minutes.”
— Maciej Donajski, CTO
+
+
+
Finance
+
+
+
Data Processing
+
+
+
+
+ + +
“E2B has revolutionized our agents' + capabilities. This advanced alternative to OpenAI's Code Interpreter helps us focus on our unique + product.”
— Kevin J. Scott, CTO/CIO
+
+
+
AI CHATBOT
+
+
+
+
+
+
Enterprise
+
Contact us for custom enterprise
solution with special pricing.
+
Contact Us +
(◔) GET REPLY IN 24H
+
+
+ + +
“It just works. Product is great, and the + support that E2B team provides is next level.”
— Max Brodeur-Urbas, CEO
+
+
+
Workflow Automation
+
+
+
+
+ + +
“E2B helps us gain enterprises’ trust. + Executing the code from Athena inside the sandbox makes it easy to check and automatically fix any + errors.”
— Brendon Geils, CEO
+
+
+
Data Analysis
+
+
+
+
+
+
+
+
+
+
+
+
+
+
NEW
+
+
DESKTOP SANDBOX FOR COMPUTER USE
+
→
+ +
+
+
+
Today
+ + + + +
+

GET STARTED TODAY

+
+
E2B is an open-source runtime for executing AI-generated code in secure + cloud sandboxes. Made for agentic & AI use cases.
+
START FOR FREEVIEW DOCS
+
+
/RUN CODE
+
>
>
‍
>>
+
+
+
+
+ +
+ +
+
+
+ + + + +
+
+
+ +
+
+ +
+ +
+
+
+

Github

+
See our complete codebase, Cookbook examples, and more — all in + one place.
+
STAR (7.1K+) ↗ +
+ + + + + + +
+
+
+
+
+ +
+ +
+
+
+ + + + +
+
+
+ +
+
+ +
+ +
+
+
+

Join our Discord

+
Become part of AI developers community & get support + from the E2B team.
+
Join Today ↗ +
+ + + + + + + + + + +
+
+
+
+
Docs
+ +
+ +
+

Docs

+
See the walkthrough of how E2B works, including hello world + examples.
+
Browse +
+ + + + + + + +
+
+
+
+
+
+
+
+
+
+
+
+
Site
+
ProductPricingCookbookChangelogDocsBlog
+
+
+
Company
+
CareersContactPrivacy PolicyTerms of + Service
+
+ + +
+
+
©2024 ✶ FoundryLabs, Inc.
+
+
+
+ + + + + + + + + + \ No newline at end of file diff --git a/index2.html b/index2.html new file mode 100644 index 000000000..dff0e01fe --- /dev/null +++ b/index2.html @@ -0,0 +1,1364 @@ +Open-source Code Interpreting for AI Apps — E2B + + + + + + + + + + + + +
***
***
we just closed a new funding round of $11.5M LED by Decibel
LEARN MORE →
***
***
NEW
DESKTOP SANDBOX FOR COMPUTER USE
→
AI-generated code
AI-generated

RUN AI-GENERATED code SECURELY in your APP

E2B is an open-source runtime for executing AI-generated code in secure cloud sandboxes. Made for agentic & AI use cases.
START FOR FREEVIEW DOCS
TRUSTED BY
LLM
+ + + + +
+ +
+ +
+ + +
+ + + + + + + + + + +
+ +
+ + +
[.500]
[.873]
[.542]
[.704]
[.285]
[.717]
[.598]
[.557]
[.232]
[.746]
[.211]
[.013]
[.510]
[.718]
[.621]
[.223]
[.124]
[.801]
[.798]
[.117]️
[.817]
[.070]
[.353]



‍
[.833]
[.477]
[.620]
[.829]
[.195]
[.245]
[.891]
[.454]
[.145]
[.984]
[.634]
[.342]
[.746]
[.330]
[.103]
[.742]
[.004]
[.165]
[.459]
[.597]
[.910]
[.072]
[.336]
+ +
+ +
+ + +
+ + + + + + + + + + +
+ +
+ + +
]·········[
]·········[
]·········[
E2B SANDBOX
+ + + + +
RUNNING CODE…
]·····[
]·····[
]·····[
✶✶
✶✶
✶✶
✶✶




✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶




✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶




✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶
✶✶




✶✶
✶✶
✶✶
✶✶
+ + +
+ + +
+ + +
+ + +
]·····[
]·····[
]·····[
[_______________]
[%%%%%__________]
[%%%%%%%%%%_____]
[%%%%%%%%%%%%%%%]
CPU: 8 × ▤  /  RAM: 4 GB
]·········[
]·········[
]·········[
OUTPUT
+ + + + +
8 – ––––– ––– ––––– ––– ––––– –––
7 – ––––– ––– @@@@@ ––– ––––– –––
6 – ––––– ––– @@@@@ ––– ––––– –––
5 – @@@@@ ––– @@@@@ ––– ––––– –––
4 – @@@@@ ––– @@@@@ ––– ––––– –––
3 – @@@@@ ––– @@@@@ ––– @@@@@ –––
2 – @@@@@ ––– @@@@@ ––– @@@@@ –––
1 – @@@@@ ––– @@@@@ ––– @@@@@ –––
–––––––––––––––––––––––––––––––––
      A         B         C
✓ CHART-1
OUTPUT
+ + + + +
______    ______    ______
❘    ❘_\  ❘    ❘_\  ❘    ❘_\
╔═══════╗ ╔═══════╗ ╔═══════╗
║  CSV  ║ ║  TXT  ║ ║  .JS  ║
╚═══════╝ ╚═══════╝ ╚═══════╝
❘______❘  ❘______❘  ❘______❘
✓ File
OUTPUT
+ + + + +
╔ Email ══════════════╗
║ your@email.com      ║
╚═════════════════════╝
╔ Pw ═════════════════╗
║ ********            ║
╚═════════════════════╝
╔═════════════════════╗
║       Sign In       ║
╚═════════════════════╝
✓ UI
OUTPUT
+ + + + +
NVDA                            @
$120.91                        @
+32%                          @
                       @@@   @
            @@@       @   @ @
          @@   @     @     @
      @@@@      @   @
  @@@@           @@@
 @
@
✓ CHART-2
OUTPUT
+ + + + +
1999 @@@@@@@@@@ │         │
1998 @@@        │         │
1997 @@@@@@@@@@@@@        │
1996 @@@@@@@    │         │
1995 @@@@@@@@@@@@@@@@     │
1994 @@@@@@@@@@@@@@@@@@@@@@@@@
1993 @@@@@      │         │
1992 @@@@@@@@@@ │         │
–––––––––––––––––––––––––––––––––
      2         4         6
✓ CHART-3
OUTPUT
+ + + + +
/!\
‍
Error: [$rootScope:inprog] $apply
already in progress

http://errors.angular.js.org/1.3
.15/$rootScope/inprog?p0=
%24apply

at angular.js:63
☓ Error
OUTPUT
+ + + + +
8 ––––│–––––––––│–––––––––│–––––@
7 ––––│–––––––––│–––@–––––│––––@–
6 ––––│–––––––––│––@–@–@@@@–––@––
5 ––––│–––––@@@–│–@–––@–––│@–@–@@
4 @@@@│–––@@–––@│@–––@–@––│–@–@––
3 ––––@@@@––@@@@@–––@–––@@│@@@–––
2 –––@│@@@@@––––│@@@––––––│––––––
1 –@@–│–––––––––│–––––––––│––––––
–––––––––––––––––––––––––––––––––
      A         B         C
✓ CHART-4
20K+
DEVELOPERS
250K+
MONTHLY DOWNLOADS
10M+
STARTED SANDBOXES
[
USE CASES
]
AI

Build for AI
Use Cases

From running short AI-generated code snippets, up to fully autonomous AI agents.
> HOVER (↓↓)
/EXPLORE
.CSV
_____
❘   ❘_\
+ + +
❘_____❘
+ + + + + + + +

AI Data Analysis

From running short AI-generated code snippets, up to fully autonomous AI agents.
See docs
   @@@   
@@@@@@   
@@@@@@@@@
+ + + + + + + +

AI Data Visualization

Run AI-generated code to render charts, plots, and visual outputs based on your data.
See docs
 ======    
======== 
=== ===  
<        
+ + + + + + + +

Coding Agents

Use sandbox to execute code, use I/O, access the internet, or start terminal commands.
See docs
╔   ═   ╗
        ╣
       
╚     ═  
+ + + + + + + +

Generative UI

Use sandbox as a code runtime for AI-generated apps. Supports any language and framework.
See docs
==╔═══╗==
==║ ✓ ║== ==╚═══╝==
+ + + + + + + +

Codegen Evals

Use sandboxes for your codegen gym for popular evals like swe-benchmark or internal evals.
See docs
NEW
+ +
+ + + + + + + + + + + + + +

Computer Use

Use Desktop Sandbox to provide secure virtual computers in cloud for your LLM.
See docs
[
GET STARTED
]
A FEW LINES

IN YOUR CODE
WITH A FEW LINES

Need help? Join Discord, check Docs or Email us.
+
+
+
+
+
+
+ +
NODE.JS
+ + + + + + + + + +
PYTHON
+ +
VERCEL
+ +
OPEN AI
+ + +
ANTHROPIC
+ + + + + + + + + + +
Mistral
+ +
Llama
+ + + + + + + + +
LangChain
+ +
LlamaIndex
+ + + +
More
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
~
~
~
~
~
~
‍~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
// npm install @e2b/code-interpreter
+import { Sandbox } from '@e2b/code-interpreter'
+
+// Create a E2B Code Interpreter with JavaScript kernel
+const sandbox = await Sandbox.create()
+
+// Execute JavaScript cells
+await sandbox.runCode('x = 1')
+const execution = await sandbox.runCode('x+=1; x')
+
+// Outputs 2
+console.log(execution.text)
“~/index.ts”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
~
~
~
~
~
~
‍~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
~
# pip install e2b-code-interpreter
+from e2b_code_interpreter import Sandbox
+
+# Create a E2B Sandbox
+with Sandbox() as sandbox:
+    # Run code
+    sandbox.run_code("x = 1")
+    execution = sandbox.run_code("x+=1; x")
+
+    print(execution.text) # outputs 2
“~/index.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35‍‍
// npm install ai @ai-sdk/openai zod @e2b/code-interpreter
+import { openai } from '@ai-sdk/openai'
+import { generateText } from 'ai'
+import z from 'zod'
+import { Sandbox } from '@e2b/code-interpreter'
+
+// Create OpenAI client
+const model = openai('gpt-4o')
+
+const prompt = "Calculate how many r's are in the word 'strawberry'"
+
+// Generate text with OpenAI
+const { text } = await generateText({
+  model,
+  prompt,
+  tools: {
+    // Define a tool that runs code in a sandbox
+    codeInterpreter: {
+      description: 'Execute python code in a Jupyter notebook cell and return result',
+      parameters: z.object({
+        code: z.string().describe('The python code to execute in a single cell'),
+      }),
+      execute: async ({ code }) => {
+        // Create a sandbox, execute LLM-generated code, and return the result
+        const sandbox = await Sandbox.create()
+        const { text, results, logs, error } = await sandbox.runCode(code)
+        return results
+      },
+    },
+  },
+  // This is required to feed the tool call result back to the LLM
+  maxSteps: 2
+})
+
+console.log(text)
“~/aisdk_tools.ts”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28‍‍
~
~
~
~
~
~
~
# pip install openai e2b-code-interpreter
+from openai import OpenAI
+from e2b_code_interpreter import Sandbox
+
+# Create OpenAI client
+client = OpenAI()
+system = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send messages to OpenAI API
+response = client.chat.completions.create(
+    model="gpt-4o",
+    messages=[
+        {"role": "system", "content": system},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract the code from the response
+code = response.choices[0].message.content
+
+# Execute code in E2B Sandbox
+if code:
+    with Sandbox() as sandbox:
+        execution = sandbox.run_code(code)
+        result = execution.text
+
+    print(result)
“~/oai.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28‍‍
~
~
~
~
~
~
~
# pip install anthropic e2b-code-interpreter
+from anthropic import Anthropic
+from e2b_code_interpreter import Sandbox
+
+# Create Anthropic client
+anthropic = Anthropic()
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send messages to Anthropic API
+response = anthropic.messages.create(
+    model="claude-3-5-sonnet-20240620",
+    max_tokens=1024,
+    messages=[
+        {"role": "assistant", "content": system_prompt},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract code from response
+code = response.content[0].text
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.logs.stdout
+
+print(result)
“~/anth.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30‍‍
~
~
~
~
~
# pip install mistralai e2b-code-interpreter
+import os
+from mistralai import Mistral
+from e2b_code_interpreter import Sandbox
+
+api_key = os.environ["MISTRAL_API_KEY"]
+
+# Create Mistral client
+client = Mistral(api_key=api_key)
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Send the prompt to the model
+response = client.chat.complete(
+    model="codestral-latest",
+    messages=[
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": prompt}
+    ]
+)
+
+# Extract the code from the response
+code = response.choices[0].message.content
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.text
+
+print(result)
“~/mistral.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25‍‍
~
~
~
~
~
~
~
~
~
~
# pip install ollama
+import ollama
+from e2b_code_interpreter import Sandbox
+
+# Send the prompt to the model
+response = ollama.chat(model="llama3.2", messages=[
+    {
+        "role": "system",
+        "content": "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+    },
+    {
+        "role": "user",
+        "content": "Calculate how many r's are in the word 'strawberry'"
+    }
+])
+
+# Extract the code from the response
+code = response['message']['content']
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.logs.stdout
+
+print(result)
“~/llama.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30‍‍
~
~
~
~
~
# pip install langchain langchain-openai e2b-code-interpreter
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from e2b_code_interpreter import Sandbox
+
+system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
+prompt = "Calculate how many r's are in the word 'strawberry'"
+
+# Create LangChain components
+llm = ChatOpenAI(model="gpt-4o")
+prompt_template = ChatPromptTemplate.from_messages([
+    ("system", system_prompt),
+    ("human", "{input}")
+])
+
+output_parser = StrOutputParser()
+
+# Create the chain
+chain = prompt_template | llm | output_parser
+
+# Run the chain
+code = chain.invoke({"input": prompt})
+
+# Execute code in E2B Sandbox
+with Sandbox() as sandbox:
+    execution = sandbox.run_code(code)
+    result = execution.text
+
+print(result)
“~/lchain.py”
 1
 2
 3
 4
 5
 6
 7
 8
 9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
~
~
~
~
~
~
~
~
~
~
~
~
from llama_index.core.tools import FunctionTool
+from llama_index.llms.openai import OpenAI
+from llama_index.core.agent import ReActAgent
+from e2b_code_interpreter import Sandbox
+
+# Define the tool
+def execute_python(code: str):
+    with Sandbox() as sandbox:
+        execution = sandbox.run_code(code)
+        return execution.text
+
+e2b_interpreter_tool = FunctionTool.from_defaults(
+    name="execute_python",
+    description="Execute python code in a Jupyter notebook cell and return result",
+    fn=execute_python
+)
+
+# Initialize LLM
+llm = OpenAI(model="gpt-4o")
+
+# Initialize ReAct agent
+agent = ReActAgent.from_tools([e2b_interpreter_tool], llm=llm, verbose=True)
+agent.chat("Calculate how many r's are in the word 'strawberry'")
“~/llindex.py”
[
FEATURES
]
FEATURES

FEATURES FOR THE
llm-powered DEVELOPERs

We built E2B with the next generation of developers in mind — software engineering AI agents.
> MADE FOR AI
> DSCVR ALL (↓↓)
+ +
+ +
+ +
+ + + + + + + + + + +
+ + +
+ + + + + + + + +
+ + +

Works with any LLM

Use OpenAI, Llama, Anthropic, Mistral, or your
own custom models. E2B is LLM-agnostic
and compatible with any model.
+ + + + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

Quick start

The E2B Sandboxes in the same region as
the client start in less than 200 ms.
NO COLD STARTS

Run

+ +
+ +
+ +
+ +
+ +

... or just any other AI-generated code.

AI-generated Python, JavaScript, Ruby, or C++? Popular framework or custom library? If you can run it on a Linux box, you can run it in the E2B sandbox.
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

Quick start

The E2B Sandboxes in the same region as
the client start in less than 200 ms.
NO COLD STARTS
Control code execution context
inspect errors
install packages
interactive charts
Filesystem I/O

Features made for LLM

E2B features are made to turn your
LLM into a competent coder.
tailor-made for ai
  ^  
^ ^  
^^^^^
^^ ^^
^^^
+ + + + +

Secure & battle-tested

Sandboxes are powered by Firecracker microVM,
a VM made for running untrusted code.
battle-tested
24H
[
SANDBOX RUNNING
]

Up to 24h long sessions

Run for a few seconds or several hours, each E2B
sandbox can run up to 24 hours.
AVAILABLE IN PRO
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + +

Install any package or system library with

+ +
+ + + + + + + + +
+ +
+ +

and more.

Completely customize the sandbox for your use case by creating a custom sandbox template or installing a package when the sandbox is running.
*
·
*
·
*
·
*
·
+ +
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
+ +
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·
*
·

Self-hosting

Deploy E2B in your AWS, or GCP account
and run sandboxes in your VPC.
I'm interested
+ +
SOON
[
Cookbook
]
COOKBOOK

GET INSPIRed BY
OUR COOKBOOK

Production use cases & full-fledged apps.
HOVER (↓↓)

Llama 3 with code interpreting and analyzing uploaded dataset

Python, Meta
+ +

AI Code Execution with Together AI models, JS/TS

JS, TS, Meta, Together AI
+ +

AI Code Execution with Together AI models, Python

Python, Meta, Together AI
+ +

Scrape and Analyze Airbnb Data with Firecrawl and E2B

JS, TS Firecrawl
+ +

OpenAI o1 Code Interpreter in Python

Python, OpenAI
+ +

OpenAI o1 Code Interpreter in JS/TS

JS, TS, OpenAI
+ +

Next.js app with LLM + Code Interpreter and streaming

JS, TS, Next.js, OpenAI
+ +

Code Interpreter with magentic and GPT-4o

Python, magentic, OpenAI
+ +

Llama 3 + function calling + E2B Code interpreter in Python

Python, Meta
+ +

Llama 3 + function calling + E2B Code interpreter

JS, TS, Meta
+ +

LangChain with Code Interpreting

Python, LangChain
+ +

LangGraph with Code Interpreting

Python, LangGraph
+ +

GPT-4o Code Interpreter in JS/TS

JS, TS, OpenAI
+ +

Running code generated by Autogen via E2B Sandbox

Python, Autogen
+ +

Code interpreting with Fireworks

Python, Fireworks AI
+ +

Visualizing Website Topics (Claude + Firecrawl + E2B)

Python, Anthropic, Firecrawl
+ +

AI Code Execution with Mistral's Codestral in Python

Python, Mistral
+ +

AI Code Execution with Mistral's Codestral in JS

JS, TS, Mistral
+ +

GPT-4o Code Interpreter in Python

Python, OpenAI
+ +

Claude Code Interpreter in Python

Python, Anthropic
+ +

Claude Code Interpreter in JS/TS

JS, TS, Anthropic
+ +
LOAD MORE
[
CUSTOMERS
]
COMPANIES

USED BY TOP
COMPANIES

From running short AI-generated code snippets, up to fully autonomous AI agents.
/print("
+ +
")
(↓↓)
“E2B has a great product that unlocked a new set of rich answers for our users. We love working with both the product and team behind it.”
— Denis Yarats, CTO
Read THE CASE STUDY →
Data Analysis
+ +
“It took just one hour to integrate E2B end-to-end. The performance is excellent, and the support is on another level. Issues are resolved in minutes.”
— Maciej Donajski, CTO
Finance
Data Processing
“It took just one hour to integrate E2B end-to-end. The performance is excellent, and the support is on another level. Issues are resolved in minutes.”
— Maciej Donajski, CTO
Finance
Data Processing
“E2B has revolutionized our agents' capabilities. This advanced alternative to OpenAI's Code Interpreter helps us focus on our unique product.”
— Kevin J. Scott, CTO/CIO
AI CHATBOT
Enterprise
Contact us for custom enterprise
solution with special pricing.
Contact Us
(◔) GET REPLY IN 24H
“It just works. Product is great, and the support that E2B team provides is next level.”
— Max Brodeur-Urbas, CEO
Workflow Automation
“E2B helps us gain enterprises’ trust. Executing the code from Athena inside the sandbox makes it easy to check and automatically fix any errors.”
— Brendon Geils, CEO
Data Analysis
NEW
DESKTOP SANDBOX FOR COMPUTER USE
→
Today

GET STARTED TODAY

E2B is an open-source runtime for executing AI-generated code in secure cloud sandboxes. Made for agentic & AI use cases.
START FOR FREEVIEW DOCS
/RUN CODE
>
>
‍
>>
+ +
+ +
+ +

Github

See our complete codebase, Cookbook examples, and more — all in one place.
STAR (7.1K+) ↗
+ + + + + + +
+ +
+ +
+ +

Join our Discord

Become part of AI developers community & get support from the E2B team.
Join Today ↗
+ + + + + + + + + + +
Docs

Docs

See the walkthrough of how E2B works, including hello world examples.
Browse
+ + + + + + + +
Site
ProductPricingCookbookChangelogDocsBlog
Company
CareersContactPrivacy PolicyTerms of Service
©2024 ✶ FoundryLabs, Inc.
+ + + + \ No newline at end of file