Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
AgentOS belongs on RepoRadar because it ships a real, runnable, in-process agent OS instead of another chat wrapper, skill collection, or sandbox library that delegates execution to Docker or Firecracker. The kernel manages a virtual filesystem, process table, pipes, PTYs, and a virtual network stack -- nothing executes on the host. Agents call host JavaScript functions as bindings
Who should use it
Who should skip it
Skip rivet-dev/agentos unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
rivet-dev/agentos is tracked by RepoRadar as a code repository in the AI tooling section. It was first seen on 2026-07-12 and last updated on 2026-07-12. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for rivet-dev/agentos are workflow potential (9.6) and novelty (9.2), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned rivet-dev/agentos a composite score of 8.5 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 100.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Project is at v0.2.7 (early-stage but production-ready for embedded use; the README publishes real-world benchmarks vs. mainstream sandbox providers, suggesting internal production usage at Rivet); Stars (3610) and subscribers (10) are lower than some try_now picks; the momentum is real (3,610 stars and 173 forks within ~2.5 years of the repo's first commit on 2024-02-07) but the project is still building a wider install base; WASM command packages ship as build artifacts -- the README publishes them via a registry table but does not enumerate every package's source repo (some packages are reposts of upstream coreutils / git / curl; verify provenance if you need license-clean distribution for a downstream commercial use case); The in-process kernel pattern is novel; if a downstream user hits an isolation bug, the security model is different from container / VM sandbox (deny-by-default WASM, not syscall-filtered Linux).