AgentSidekick

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 directory

Profiled 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

Code Execution Sandboxes: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1LLM SandboxSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.vndee1.1k4d ago
2SandBase HarnessStdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.sandbaseai6433d ago
3ipyboxUnified execution environment for Python code, shell commands, and programmatic MCP tool callsgradion-ai765mo ago
4VaayaThe best wallet for your agents: a prepaid balance and spending limits for 4,400+ paid endpoints.vaaya.ai444d ago
5e2bCreate and manage secure sandboxes for running AI agent codemcparmory.com326mo ago
6anirbanbasu-pymcpPrimarily to be used as a template repository for developing MCP servers with FastMCP in Python, P…smithery.ai85d ago
7SuperserveMCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMssuperserve-ai—today

Infrastructure 5 indexed · 5 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1DaytonaSandbox infrastructure that starts isolated environments for running AI-generated code quickly, with SDKs for files, git and processes.Daytona71k4mo ago
2E2BFirecracker microVM sandboxes that agents use to run untrusted code, with SDKs for files, processes and a code interpreter.E2B15ktoday
3awesome-ai-sdksA database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agentse2b-dev1.2k4mo ago
4Cloudflare Sandbox SDKSDK for running isolated containers from Workers to execute code, run commands and manage files for agents.cloudflare1.2k11d ago
5Amazon Bedrock AgentCoreSet of managed services for running agents built with any framework: serverless runtime, memory, gateway, identity, code interpreter, browser and observability.Amazon Web Services786today

Agent projects 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: Agent projects by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1smolvmAn embeddable, portable, branchable virtual machine to safely run Agents locally.smol-machines7.2ktoday
2arcboxRun AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.arcboxlabs4.3k5d ago

Frameworks 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1enterprise-deep-researchSalesforce Enterprise Deep ResearchSalesforceAIResearch1.2k25d ago
2pydantic-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-co1.1k22d ago

Libraries 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1smolagentsMinimal Python library for agents that write and execute Python code as their actions, with sandboxed execution options and Hub integration.Hugging Face30k1d ago
2ANetAgent 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.ANetResearch1519d ago

AI APIs 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: AI APIs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1OpenAI 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.openai32k1d ago

Platforms 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Code Execution Sandboxes: Platforms by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Amazon 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 platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Amazon Bedrock AgentCore1
Claude Code1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
AWS12.2%
MySQL12.2%
PostgreSQL12.2%
Salesforce12.2%
Vercel12.2%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
code sandbox5
code interpreter10
sandboxed execution5
e2b7
run code safely0
isolated environment0
firecracker4
microvm14

Segment statistics

Whole catalogue (45 indexed products). Calculated 2026-11-21.

45DERIndexed products20 with full profiles
19DERLaunched, last 90 days9 in the 90 days before
29DERMomentum vs catalogue50 = same pace as the catalogue
42%DERLargest project's share of starsAcross 35 products with their own repository
0.261DERConcentration (HHI)About 4 equal-sized projects’ worth; highly concentrated
11SRCMedian starsPer product with its own repository
67%DEROpen sourceMarked open source; unknown counts as not

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 breakdown

Coverage 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 .