Code Execution Sandboxes
Isolated environments where agents run code safely. As of 2026-11-21, 45 indexed products offer it (20 with full profiles), in 7 forms: 32 MCP servers, 5 Infrastructure, 2 Agent projects, 2 Frameworks. 19 were published in the last 90 days, against 9 in the 90 days before. Daytona has the most GitHub stars, 42% of the total across 35 products with their own repository.
CapabilitySegment label: Lagging the catalogue DERScored as an opportunity
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 32 indexed · 7 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | LLM SandboxSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends. | vndee | 1.1k | 4d ago | ||
| 2 | SandBase HarnessStdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation. | sandbaseai | 643 | 3d ago | ||
| 3 | ipyboxUnified execution environment for Python code, shell commands, and programmatic MCP tool calls | gradion-ai | 76 | 5mo ago | ||
| 4 | VaayaThe best wallet for your agents: a prepaid balance and spending limits for 4,400+ paid endpoints. | vaaya.ai | 44 | 4d ago | ||
| 5 | e2bCreate and manage secure sandboxes for running AI agent code | mcparmory.com | 32 | 6mo ago | ||
| 6 | anirbanbasu-pymcpPrimarily to be used as a template repository for developing MCP servers with FastMCP in Python, P… | smithery.ai | 8 | 5d ago | ||
| 7 | SuperserveMCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs | superserve-ai | — | today |
Infrastructure 5 indexed · 5 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes. | Daytona | 71k | 4mo ago | ||
| 2 | E2BFirecracker microVM sandboxes that agents use to run untrusted code, with SDKs for files, processes and a code interpreter. | E2B | 15k | today | ||
| 3 | awesome-ai-sdksA database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents | e2b-dev | 1.2k | 4mo ago | ||
| 4 | Cloudflare Sandbox SDKSDK for running isolated containers from Workers to execute code, run commands and manage files for agents. | cloudflare | 1.2k | 11d ago | ||
| 5 | Amazon Bedrock AgentCoreSet of managed services for running agents built with any framework: serverless runtime, memory, gateway, identity, code interpreter, browser and observability. | Amazon Web Services | 786 | today |
Agent projects 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | smolvmAn embeddable, portable, branchable virtual machine to safely run Agents locally. | smol-machines | 7.2k | today | ||
| 2 | arcboxRun AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust. | arcboxlabs | 4.3k | 5d ago |
Frameworks 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | enterprise-deep-researchSalesforce Enterprise Deep Research | SalesforceAIResearch | 1.2k | 25d ago | ||
| 2 | pydantic-deepagentsOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model. | vstorm-co | 1.1k | 22d ago |
Libraries 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration. | Hugging Face | 30k | 1d ago | ||
| 2 | ANetAgent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents without a server or public IP. MCP for coding agents, a2a-x402 payments, sandboxed execution. | ANetResearch | 15 | 19d ago |
AI APIs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | OpenAI APIAPI for GPT and reasoning models via the Responses and Chat Completions endpoints, with built-in tools such as web search, file search, code interpreter and computer use. | openai | 32k | 1d ago |
Platforms 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Amazon Bedrock AgentCoreModular AWS services for deploying and operating agents built with any framework and model: a managed Harness agent loop, serverless Runtime, Memory, Gateway (APIs/Lambda to MCP tools), Identity, Code Interpreter, Browser, Observability, Evaluations, Policy, Registry and Payments. | Amazon Web Services | — | — |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 32 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 0 indexed here
26 platforms document Agent Skills support CUR, but no product offering this capability ships in this form yet.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Amazon Bedrock AgentCore | 1 |
| Claude Code | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| AWS | 1 | 2.2% |
| MySQL | 1 | 2.2% |
| PostgreSQL | 1 | 2.2% |
| Salesforce | 1 | 2.2% |
| Vercel | 1 | 2.2% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| code sandbox | 5 |
| code interpreter | 10 |
| sandboxed execution | 5 |
| e2b | 7 |
| run code safely | 0 |
| isolated environment | 0 |
| firecracker | 4 |
| microvm | 14 |
Segment statistics
Whole catalogue (45 indexed products). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.261 means stars are spread as if across about 4 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Scored as an opportunity
Score breakdownCoverage gap: Code Execution Sandboxes: score 54.1 HEU, competition High, confidence Low. Only 45 indexed products match "Code Execution Sandboxes", against 275 in Tool Use & Function Calling overall.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .