Anthropic just released Managed Agents

We ship the layer underneath.
Claude Code today. GPT-5 tomorrow. On our metal or yours.

Firecracker microVMs on bare metal. Not owned by any foundation-model vendor. Priced like electricity. Click below -- you're in a live Claude Code session in under ten seconds. No signup, no API key, no waitlist.

Agent sandboxes are stateless.
Your agents shouldn't be.

Every sandbox provider gives your agent an isolated environment to run code. When the session ends, everything disappears.

For a 4-minute task, that's fine.

For a 14-hour research pipeline, a week-long code migration, or a multi-agent system that builds on previous results -- you need execution that remembers.

upstream is a turn executor. Each turn produces structured output. Context accumulates. The next turn starts where the last one ended.

# Turn 1: Research $ upstream run research.md Step 1: Search papers .............. done (14 results) Step 2: Summarize findings ......... done Context: 2 artifacts saved # Turn 2: Analysis (receives Turn 1 context) $ upstream run analysis.md Context loaded: 2 artifacts from previous turn Step 1: Cross-reference findings ... done Step 2: Generate report ............ done

Three API calls. No setup.

Create a sandbox. Run code. Get results. The SDK handles everything else.

01

Create a sandbox

One API call. A Firecracker VM boots from a pre-warmed snapshot in 200ms. Claude Code, git, and your toolchain are ready.

--- image: python:3.12 --- # Data Analysis ```bash pip install pandas python analyze.py ```
02

Run it

upstream pulls the image, executes each bash block in an isolated VM, and captures the output.

$ upstream run pipeline.md Pulling python:3.12 ... done Step 1: pip install ..... done (3.1s) Step 2: python analyze .. done (1.4s)
03

Read the results

Results are written back into the markdown. Exit codes, stdout, timing -- all inline. The document is now a complete execution report.

**Result:** exit 0 (1.4s) ``` Found 847 records Mean: 42.3, Median: 38.1 Report saved to output.csv ```

How upstream compares

Honest numbers. We win on cost, context, and self-hosting. Others win on SDK breadth and enterprise traction.

E2B Daytona upstream
Self-hosted Enterprise only No Free + open source
Context store No No Built-in
Interface Python/JS SDK Python/JS SDK Markdown
Cold start ~150ms ~90ms ~5ms (warm pool)
Cost per session ~$0.01 ~$0.01 ~$0.0002 (self-hosted)
Isolation Firecracker microVM Firecracker microVM Firecracker microVM
Max session 24 hours Unlimited Unlimited

Self-hosted is free. Forever.

Run on your own metal for $0. Or let us host it -- still 2-5x cheaper than alternatives.

Free
$0
Self-hosted, unlimited
  • Single Rust binary
  • All core features
  • Context accumulation
  • Unlimited pipelines
  • Unlimited agents
  • Community support
Install from source
Enterprise
Custom
Dedicated metal, volume discounts
  • Dedicated bare metal
  • All Pro features
  • Volume discounts
  • Custom SLA
  • SSO / SAML
  • Dedicated support
Contact us

Try it in 60 seconds.

$ cargo install upstream click to copy

Or download a prebuilt binary from GitHub Releases