All repositories

Agent frameworkse2b-dev

E2B

Isolated cloud sandboxes where an agent can safely run code and commands. One SDK call gives the model its own small computer.

Who it is for

For people letting agents execute code without risking their own machine.

How to start

  1. Install the SDK: pip install e2b or npm i e2b.
  2. Get an API key at e2b.dev/dashboard and set it as E2B_API_KEY.
  3. Start a sandbox and run a command in it, as in the README example.

Steps are taken from the README. Check the current version in the repository before running them.

Stars over the last 30 days

+535Sep 6 — Oct 6
13,65414,189

Author's description

Open-source, secure environment with real-world tools for enterprise-grade agents.

Significant-Gravitas

AutoGPT

A platform where you build agents in a visual builder or by describing them in plain words, then run them on a schedule or a trigger. Hosted version plus free self-hosting.

188Kstars+809 in 30 dPython

langchain-ai

langchain

The best-known toolkit for LLM apps: one interface to dozens of models, plus tools, chains and agents. You can swap providers without rewriting the app.

147Kstars+1.9K in 30 dPython

browser-use

browser-use

Growing fastest

A library that lets an agent drive a browser: open sites, click, fill in forms. Works with a local browser or a cloud one.

117Kstars+4.9K in 30 dPython

FoundationAgents

MetaGPT

A multi-agent framework that plays out a whole software company: product manager, architect and engineer take roles and turn one sentence into a project together.

71Kstars+639 in 30 dPython

mem0ai

mem0

A memory layer for agents: it remembers facts about the user across sessions and pulls up the right ones at the right moment, keeping context small.

67Kstars+2K in 30 dPython

microsoft

autogen

Microsoft's framework for agents that talk to each other. It has the high-level AgentChat API and AutoGen Studio, a no-code graphical interface.

61Kstars+553 in 30 dPython