Profiles & Limits#
Rustbox offers two execution profiles, each tuned for different workloads.
Availability: Judge profile is live in the open beta. Agent profile is on the waitlist - and we will invite you when the infrastructure is ready.
Quick comparison#
| Judge | Agent | |
|---|---|---|
| Memory | 256-512 MB | 1 GB |
| Wall time | 7-15s | 30s |
| CPU time | 4-8s | 15s |
| Max PIDs | 10-1024 | 32-512 |
| Network | disabled | filtered |
| Best for | Interviews, contests, test runners | LLM agents, code interpreters, REPLs |
| Status | live | waitlist |
Judge mode#
Use case: Competitive programming, coding assessments, interview platforms.
Code runs in a bare sandbox with just the language runtime. No network access, tight memory limits, fast time limits. Designed for evaluating short, deterministic programs against known test cases.
| Language | Memory | CPU Time | Wall Time | Max PIDs |
|---|---|---|---|---|
| Python | 256 MB | 4s | 7s | 10 |
| C | 256 MB | 8s | 10s | 8 |
| C++ | 256 MB | 8s | 10s | 8 |
| Java | 512 MB | 8s | 10s | 1024 |
| JavaScript | 512 MB | 8s | 12s | 16 |
| TypeScript | 512 MB | 8s | 12s | 16 |
| Go | 256 MB | 8s | 10s | 1024 |
| Rust | 256 MB | 8s | 15s | 64 |
All languages: network disabled, max code size 64 KB, max stdin size 256 KB.
Typical use: submit a candidate's solution with test case input, compare stdout against expected output. Verdicts (AC, RE, TLE, MLE, PLE, FSE) are determined by kernel evidence, not exit code guessing.
Agent mode · waitlist#
Use case: LLM agent tools, code interpreters, short-lived Python REPLs, notebook cells.
Agent profile is not live yet. - we are opening invites as the Agent infrastructure rolls out.
Higher-memory tier above Judge. Filtered network allows package imports and outbound HTTPS while blocking private IPs and cloud metadata. Sized for typical agent tool-call workloads with room for short-lived Python/JS runs.
| Resource | Limit |
|---|---|
| Memory | 1 GB |
| Wall time | 30 seconds |
| CPU time | 15 seconds |
| Max PIDs | 32-512 (per language) |
| Network | Filtered |
| Code size | 64 KB |
| Stdin size | 256 KB |
Typical use: an LLM agent generates a short Python snippet to parse JSON, call a public API, and return structured output. Round-trip completes well under 30 seconds.
Security#
Both profiles run with identical isolation: 8 kernel layers, seccomp filtering, capability drop, credential isolation, NO_NEW_PRIVS. The only differences are resource limits and network policy.
There is no way to escalate from one profile to the other via the API. Your profile is determined by your API key, not by the request.
Verdicts#
Both profiles return the same verdict set:
| Verdict | Meaning |
|---|---|
AC | Accepted - clean exit, code 0 |
RE | Runtime Error - non-zero exit or crash |
TLE | Time Limit Exceeded - wall time exceeded |
MLE | Memory Limit Exceeded - OOM killed by cgroup |
PLE | Process Limit Exceeded - fork/thread bomb hit cgroup PID limit |
FSE | File Size Exceeded - SIGXFSZ from RLIMIT_FSIZE |
SIG | Signaled - killed by signal |
IE | Internal Error - platform infrastructure failure |
Every verdict is backed by kernel evidence (cgroup OOM events, signal delivery records, CPU accounting). The platform does not guess verdicts from exit codes.