# Baponi

> Baponi is a sandboxed code execution platform for AI agents. Send code via API, get stdout/stderr/exit_code back. Sub-20ms sandbox overhead. Python, Node.js, and Bash. MCP native. Deploy as cloud SaaS or self-hosted in your VPC.

Every page on this site has a markdown alternate: append `.md` to the path (e.g. https://baponi.ai/pricing.md, https://baponi.ai/docs/api/execute.md), or send `Accept: text/markdown` with your request.

## Docs

- [Quickstart: First Execution in 60 Seconds](https://baponi.ai/docs/getting-started/quickstart/): Get from zero to running code in a Baponi sandbox in under 60 seconds. Sign up, create an API key, and execute your first Python, Node.js, or Bash command via curl, Python SDK, or MCP.
- [How Baponi Works](https://baponi.ai/docs/getting-started/how-it-works/): Baponi is a sandboxed code execution platform for AI agents. One API call, sub-20ms overhead, no lifecycle management. Understand the execution model, thread_id persistence, BYOB storage, connectors, and LLM integration.
- [API Overview](https://baponi.ai/docs/api/overview/): Baponi API reference: authentication with API keys, base URLs, Stripe-style error responses, rate limiting, and available SDKs. Everything you need to integrate sandboxed code execution into your AI agent.
- [Execute Code](https://baponi.ai/docs/api/execute/): POST /v1/sandbox/execute. Run Python, Node.js, or Bash code in an isolated sandbox with sub-20ms overhead. Full request/response reference with examples.
- [Executions](https://baponi.ai/docs/api/executions/): GET /v1/executions/{trace_id} and /output. Retrieve execution status, results, and reconnect to streaming output after a disconnect. Full request/response reference.
- [Files API](https://baponi.ai/docs/api/files/): List, upload, download, and delete files in Baponi threads and volumes. Signed URLs for direct cloud storage transfers up to 10 GiB.
- [MCP Protocol](https://baponi.ai/docs/api/mcp/): Baponi MCP server reference. Model Context Protocol 2025-11-25 implementation. Streamable HTTP transport, sandbox_execute and files_download tools, stateless design.

## Guides

- [LangChain Deep Agents](https://baponi.ai/docs/guides/deep-agents/): Add sandboxed code execution to your LangChain Deep Agent in 3 lines. BaponiSandbox gives your agent file read/write, code execution, grep, and glob with persistent state, per-call overrides, real-time streaming, and lifecycle management.
- [Remote Claude Code Sessions](https://baponi.ai/docs/guides/claude-code/): Run Claude Code in a sandboxed Baponi environment with automatic credential injection for Anthropic API keys and GitHub access. Clone repos, run headless agent sessions, and push results, all fully isolated.
- [Storage Path Scoping: Multi-Tenant Data Isolation for AI Agents](https://baponi.ai/docs/guides/storage-path-scoping/): Control exactly which subdirectories AI agents can access in your S3, GCS, or Azure buckets. Three levels of path constraints - connection, API key, and per-request - enforce least-privilege access with zero application code.
- [Workload Identity Federation](https://baponi.ai/docs/guides/workload-identity-federation/): Connect your GCS or S3 buckets to Baponi without sharing secrets, using cross-project/cross-account trust.

## Pages

- [Homepage](https://baponi.ai/): Product overview, key differentiators, and quick start.
- [Features](https://baponi.ai/features/): BYOB storage, growing connector ecosystem, sub-20ms performance, hardened nsjail sandbox isolation, custom OCI runtimes, MCP + REST + Python SDK.
- [Pricing](https://baponi.ai/pricing/): Free tier (1,000 credits/month), Pro ($97/month), and Enterprise plans.
- [Enterprise](https://baponi.ai/enterprise/): Self-hosted deployment, VPC isolation, BYOB storage, and custom SLAs.
- [Trust Center](https://baponi.ai/trust/): Six independent isolation layers, zero-credential storage mounts, immutable audit logging on every tier.

## Comparisons

- [Baponi vs E2B](https://baponi.ai/compare/vs-e2b/): Hardened nsjail (sub-20ms) vs Firecracker microVMs (self-reported 80-200ms), lifecycle model, zero-credential bucket mounts, pricing, self-hosting. Verified June 2026.
- [Baponi vs Daytona](https://baponi.ai/compare/vs-daytona/): Hardened nsjail vs Sysbox containers, internet access tiers, BYOB storage, credit pricing vs per-second metering, AGPL licensing. Verified June 2026.
- [Baponi vs Modal](https://baponi.ai/compare/vs-modal/): Worked idle math from published rates: 150 daily 8-hour agent sessions cost about $898/month on Modal vs $97/month flat on Baponi (inside Pro's included credits), because Modal sandboxes bill per second while idle and Baponi bills nothing between calls. One flat credit price vs 3x sandbox rates with multipliers, REST + MCP, Kubernetes self-hosting. Verified June 2026.
- [Baponi vs Vercel Sandbox](https://baponi.ai/compare/vs-vercel/): Worked tuning math from published rates: the same 150-session agent workload spans $16 to $1,536/month on Vercel Sandbox depending on timeout and lifecycle tuning (five meters), $97/month flat on Baponi (one meter, inside Pro's included credits). Managed read-only bucket mounts vs DIY FUSE with credentials in the VM, sub-20ms overhead vs 0.84s measured median, self-hosting in any region vs US East only. Verified June 2026.