E2B vs Freestyle (2026)

An agent in a sandbox reaches other systems through a built in MCP gateway that runs inside the sandbox and exposes more than 200 tools from the Docker MCP Catalog (Airtable, GitHub, Browserbase, Exa and others) or custom MCP servers through one interface. Credentials are passed as secrets that resolve at egress instead of living in the sandbox.

Sourcedocs.e2b.dev/mcp-gatewayread 2026-11-03

Credentials reach outside services without entering the VM. Outbound TLS rules let Freestyle's edge add API keys to requests for services such as OpenAI, Anthropic or OpenRouter, connect to external Postgres with a password the VM never sees, sign S3 requests limited to a bucket, prefix and set of operations, route traffic through the customer's SOCKS5 proxy and reach other VMs by internal names, and WireGuard tunnels connect VMs to remote networks. There are no prebuilt connectors or tool catalog for an agent to call.

Sourcefreestyle.sh/docs/vms/network/tls-outboundread 2026-11-05

There is no workflow logic in E2B itself. The customer brings its own orchestration framework, and E2B provides the machine an agent's steps run on (commands, background processes, code contexts), not a runtime that sequences, branches, retries or routes those steps. Forking a sandbox copies its state, which is compute, not workflow logic.

Sourcee2b.dev/llms.txtread 2026-11-03

There is no workflow logic in the product. Run limits pause a VM after a set time, TTLs delete it and snapshots support branching and rollback, but sequencing, retrying and routing an agent's steps stay in the customer's own code.

Sourcefreestyle.sh/docs/vms/lifecycleread 2026-11-05

A sandbox can start without the customer's code calling it. With auto resume set, a paused sandbox resumes when activity arrives, so an agent served from a sandbox starts on an inbound request, and E2B's guides deploy agent gateways this way, for example OpenClaw answering Telegram. Sandbox lifecycle events are also pushed to the customer's webhook, signed. There is no scheduler.

Sourcedocs.e2b.dev/sandbox/auto-resumeread 2026-11-03

A paused VM wakes without the customer's code calling it. The next traffic that reaches the VM resumes it with its processes and memory intact, after a forward auth check when one is set, so an agent or app served from a Freestyle VM answers requests at its domain and pauses again when idle. There is no scheduler or webhook.

Sourcefreestyle.sh/docs/vms/lifecycleread 2026-11-05

There is no retrieval structure over the customer's content, since E2B runs the agent's code. Files uploaded to a sandbox or volume are storage the agent's code can read, not an index a query returns, and the MCP gateway's tools reach outside knowledge sources owned by others.

Sourcee2b.dev/llms.txtread 2026-11-03

No retrieval index or knowledge base over the customer's content comes with the platform. Files an agent reads live on the VM's disk, and any retrieval runs as the customer's own software inside the VM.

Sourcefreestyle.sh/docs/vmsread 2026-11-05

An agent's working state carries across sessions. A paused sandbox resumes exactly as it was, with filesystem and memory, running processes and loaded variables, and is kept until it is killed. Snapshots and forks copy that state, volumes, in private beta, keep files across sandboxes, and code contexts keep interpreter variables between executions, which the agent's code reads to continue its task. This is machine state the developer manages, with no memory layer of stated types or scope that can be reviewed, edited or deleted as memory.

Sourcedocs.e2b.dev/sandbox/persistenceread 2026-11-03

An agent's working state carries across sessions as machine state. A paused VM keeps its memory and resumes the same processes, persistent VMs keep their disks between runs, and snapshots and live cloning create new VMs that match the original for branching and recovery. Files on a paused VM stay readable without resuming it. This is machine state the developer manages, not a memory layer of stated scope that can be reviewed or deleted as memory.

Sourcefreestyle.sh/docs/vms/lifecycleread 2026-11-05

There is no approval step, consent checkpoint or escalation to a person for work inside an E2B sandbox. Egress control (allow and deny lists for each sandbox, a proxy the customer runs that fails closed, and access tokens on public URLs) limits what an agent's code can reach, but that is isolation the developer configures, not a point where a person reviews the agent's action.

Sourcee2b.dev/enterpriseread 2026-11-03

Work in a VM has no approval step, consent checkpoint or escalation to a person. A default closed firewall, forward auth on domains and credentials held at the edge limit what an agent can reach, but nothing holds an action until someone reviews it.

Sourcefreestyle.sh/docs/vms/network/firewallread 2026-11-05

E2B holds SOC 2 Type II, with the report under NDA in its trust center at trust.e2b.dev, and signs HIPAA Business Associate Agreements on Enterprise plans. Its controls protect the sandbox. Every sandbox is its own Firecracker microVM with its own kernel, egress can be allowed or denied for each sandbox, secrets are injected at the egress proxy so no sandbox holds them, and public sandbox URLs can require an access token. Who inside a customer's organization can do what has no published control yet, since E2B lists single sign on, SCIM and role based access as planned.

Sourcee2b.dev/securityread 2026-11-03

Team API keys manage resources, and client sessions give an end user or agent its own identity with access to chosen VMs and Linux users through a token that can be revoked without rotating the team key. Secrets in outbound rules are write only and sealed at rest, and every VM starts with no network access until rules allow it. SAML single sign on and SCIM come with Enterprise, and Freestyle names no compliance attestation.

Sourcefreestyle.sh/docs/vms/client-sessionsread 2026-11-05

The record covers the sandbox, not the agent. Every lifecycle event is available through an events API and delivered as a signed webhook, sandbox metrics report CPU and memory use, template builds keep logs, and on Enterprise OpenTelemetry metrics and logs export to the customer's OTLP endpoint. Prompts, tool calls, retrieved knowledge and outputs cannot be inspected step by step in E2B, since the agent's reasoning runs outside the sandbox, and there is no audit log of user actions apart from the runtime.

Sourcee2b.dev/enterpriseread 2026-11-03

Audit logs come with the Enterprise plan. No logs, metrics or traces come with the VMs, so what an agent did inside a VM is visible only through the customer's own tooling and the command output returned to the caller.

Sourcefreestyle.sh/pricingread 2026-11-05

Three deployment modes share the same SDK, CLI and API. E2B Cloud defaults to Google Cloud us-west1, and AWS us-west-2 and us-east-1 and Google Cloud europe-west1 and asia-southeast1 are available on request on every plan. With BYOC on AWS, Google Cloud or Azure on Enterprise, the data plane runs in the customer's own cloud account. E2B Embed packages the Apache-2.0 runtime for a single node self hosted install, and a private cloud option is in development.

Sourcedocs.e2b.dev/faq/egress-ip-rangesread 2026-11-03

Freestyle runs as a hosted service with no choice of region and no self hosted or customer cloud option. VPCs and WireGuard tunnels connect VMs to the customer's networks without moving where the VMs run.

Sourcefreestyle.sh/docs/vms/pricing-and-limitsread 2026-11-05

Starting points ship with the platform, including sandbox templates for Claude Code, a desktop, Docker and web app stacks, a cookbook of examples ready to run, setup guides for more than thirty agents and frameworks, and open source reference apps, Surf, a computer use agent, and Fragments, a builder that turns a prompt into an app. These are environments and examples a developer builds from, not a browsable catalog of agents a customer adopts.

Sourcedocs.e2b.dev/llms.txtread 2026-11-03

Starting points come as base snapshots and setup guides. Public base snapshots include Kali Linux and BusyBox and sit outside each plan's snapshot limit, and guides set up Claude Code, Python, Node.js, Go, Bun, Chromium, Docker, PostgreSQL, Redis, Supabase and Vite on a VM. These are environments a developer builds from, not prebuilt agents a business adopts.

Sourcefreestyle.sh/docs/vms/base-snapshotsread 2026-11-05

Compute is what E2B provides for agents, with the customer bringing its own model and orchestration framework. Sandboxes connect to any LLM and to agents and frameworks such as Claude Code, Codex, the OpenAI Agents SDK, the Vercel AI SDK, LangChain, CrewAI, Mastra and Google ADK. E2B imposes no model, so model choice stays with the customer.

Sourcee2b.dev/llms.txtread 2026-11-03

The customer chooses the agents and models that run on a VM. Outbound rules inject keys for providers such as OpenAI, Anthropic or OpenRouter, and a JSON patch rule can set or change the model field in request bodies at the edge, so the customer can pin which model an agent calls.

Sourcefreestyle.sh/docs/vms/network/tls-outboundread 2026-11-05

Outside systems can call E2B through Python and JavaScript/TypeScript SDKs, a CLI, a REST API described by a published OpenAPI 3.1 specification, and custom sandbox templates the customer builds, tags and versions. A public MCP server serves E2B's documentation to agents.

Sourcee2b.dev/llms.txtread 2026-11-03

A TypeScript SDK and the freestyle command line tool cover VMs, execution, files, snapshots, PTY sessions, domains, firewall rules, VPCs, tunnels, outbound TLS rules, client session identities and API tokens. Freestyle offers no MCP server or public REST reference.

Sourcefreestyle.sh/docs/quickstartread 2026-11-05

There are no fixtures, scoring, quality gates or comparison of agent runs. E2B is where evaluations and reinforcement learning run, not how they are scored. It lists reinforcement learning among its workloads and runs NVIDIA NeMo Gym environments in sandboxes, but the datasets, reward functions and scoring belong to the customer's framework.

Sourcee2b.dev/llms.txtread 2026-11-03

There are no test cases, scoring or quality gates for an agent's behavior. Snapshots and cloning let experiments branch and roll back, with any evaluation done in the customer's own code.

Sourcefreestyle.sh/docs/vmsread 2026-11-05

Agents control real desktops hosted by E2B. E2B Desktop sandboxes are Ubuntu machines with an XFCE desktop and preinstalled applications, and the Desktop SDK gives the agent screenshots, mouse, keyboard and scroll, with a live VNC stream so a person can watch. A cloud browser can also run in a sandbox, and Surf is E2B's open source computer use agent built on it.

Sourcedocs.e2b.dev/use-cases/computer-useread 2026-11-03

No browser or desktop for an agent to drive comes with the platform. Chromium appears among the setup guides for software to install on a VM, and an agent that needs a browser runs and drives it itself.

Sourcefreestyle.shread 2026-11-05