Skip to content

Entry

E2B

Appears in 9 awesome lists

Open-source sandboxed code execution for AI agents — Firecracker microVMs with dedicated kernels per sandbox (~150 ms cold start), fork/snapshot primitives (pause/resume with full memory state), Python/JS SDKs + MCP server, self-hostable via Terraform on AWS/GCP; used by Perplexity, Hugging Face,…

Open github.come2b-dev/e2b

Found in these lists

Awesome Ai Sdks

Section: Links

ActiveScore 69

awesome-ChatGPT-repositories

Section: NLP · Secure open source cloud runtime for AI apps & AI agents

FreshScore 87

Awesome Generative AI

Section: AI-Powered Code Generation · "Open-source platform for building AI-powered virtual software developers"

SlowScore 58

Awesome Harness Engineering

Section: Security, Sandbox & Permissions · Firecracker microVM sandboxes purpose-built for agent tool loops: ~150ms cold start, Python/JS SDKs, open source. The clearest reference implementation of "code execution as a harness primitive" rather than a CI system bolted on.

FreshScore 93

Awesome LangChain

Section: Other LLM Frameworks · Open-source platform for building & deploying virtual developers’ agents

FreshScore 94

Awesome Prompts

Section: Sandboxed Execution · Open-source sandboxed code execution for AI agents — Firecracker microVMs with dedicated kernels per sandbox (~150 ms cold start), fork/snapshot primitives (pause/resume with full memory state), Python/JS SDKs + MCP server, self-hostable via Terraform on AWS/GCP; used by Perplexity, Hugging Face,…

FreshScore 96

awesome-python

Section: LLM and Inference · Open-source, secure environment with real-world tools for enterprise-grade agents.

FreshScore 79

Awesome AI Agents: Tools, Resources, and Projects

Section: Repositories · E2B Sandbox offers secure cloud environments tailored for AI agents and apps, facilitating long-running sessions with various tools and can be integrated with any large language model github | github profile

SlowScore 66

Awesome Harness Engineering

Section: Sandboxes & Execution Infrastructure · Apache-2.0 open-source sandboxed code-execution environments purpose-built for AI agents, with isolated runtimes, filesystem/network controls, and session lifecycle primitives for safe autonomous execution.

FreshScore 93

Opik

Comet's open-source AI observability and evaluation platform: deep tracing of LLM calls, conversation logging, and agent activity, plus built-in eval metrics, prompt versioning, guardrails, and the Opik Agent Optimizer. Worth including because it unifies observability, verification, and…

In 18 listsDetails

transformers

(formerly known as pytorch-transformers and pytorch-pretrained-bert) provides state-of-the-art general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32+ pretrained models in…

In 14 listsDetails

mem0

The most-deployed memory layer for AI agents — drop-in add/search/update/delete fact storage with LLM-extracted long-term / short-term / semantic memory: automatic fact consolidation (dedup, contradiction resolution, decay) so agents keep "context that persists" without context bloat;…

In 14 listsDetails

Haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search,…

In 13 listsDetails

Semantic Kernel

Semantic Kernel is an SDK that integrates Large Language Models (LLMs) like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java. Semantic Kernel achieves this by allowing you to define plugins that can be chained together in just a few lines of…

In 11 listsDetails

Bifrost

🟢🟠 — Apache-licensed AI and MCP gateway with multi-provider routing, virtual-key access controls, budgets, rate limits, MCP aggregation, OAuth, automatic fallbacks, and load balancing. (Maxim) — note: model-provider credentials and proxied request/response data are sensitive; restrict and…;…

In 11 listsDetails

agent-qa

Source-available (FSL-1.1-ALv2) QA agent for natural-language web and mobile tests. Run agent-qa mcp for authoring, execution, artifacts, and failure triage; dashboard-backed tools need a running dashboard and dashboardUrl. Model and infrastructure costs are separate.

In 13 listsDetails

Markstream

Multi-framework streaming Markdown renderer for AI chat interfaces, with incomplete Markdown handling, Mermaid, KaTeX, Shiki/Monaco code blocks, SSR, and packages for Vue, React, Svelte, and Angular.

In 10 listsDetails