Rivet launches agentOS using V8 isolates and WebAssembly

// 2h agoINFRASTRUCTURE

Rivet launches agentOS using V8 isolates and WebAssembly

Rivet released agentOS, a virtual operating system runtime engineered specifically to execute AI agents with minimal footprint and low latency. Rather than spinning up resource-heavy virtual machines or traditional Docker containers for each agent, agentOS assigns each agent instance a lightweight V8 isolate coupled with a WebAssembly system call interface to achieve ~6ms cold starts.

// ANALYSIS

Moving away from traditional containerization toward V8 isolates and WebAssembly sandboxing is a game-changing architectural decision for high-density AI agent execution.

–Sub-10ms cold starts eliminate execution bottlenecks in dynamic, multi-step agent workflows.
–V8 isolation paired with WebAssembly syscall sandboxing offers security without the high memory footprint of container-based isolation.
–Dramatically improves hardware utilization and reduces compute costs when scaling thousands of concurrent autonomous agents.

// TAGS

agentosrivetv8-isolateswebassemblyagentinfrastructurecomputeruntime

DISCOVERED

2h ago

2026-07-27

PUBLISHED

2d ago

2026-07-24

RELEVANCE

8/ 10

AUTHOR

stretchcloud

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE22m ago

OpenCode 1.18.6 fixes MCP refresh and branch caches

OpenCode version 1.18.6 introduces key stability fixes and performance improvements across its desktop application and underlying client interfaces. This update resolves provider and Model Context Protocol (MCP) refresh issues in App v1, stabilizes v2 client compatibility by pinning the UI to a versioned `@opencode-ai/client` snapshot, and isolates remote reference caches by git branch to prevent cross-branch state collisions.

OPEN SOURCE1h ago

ESP32 AI Runs 28.9M Model at 9.5 Tokens/Sec

ESP32 AI is an architectural experiment by slvDev that runs a 28.9-million-parameter TinyStories language model locally on an $8 ESP32-S3 microchip without relying on external cloud servers. By keeping a 25-million-parameter embedding table in memory-mapped SPI flash to fetch token rows on demand, the project successfully circumvents tight microcontroller RAM limitations while maintaining a generation throughput of approximately 9.5 tokens per second.

OPEN SOURCE1h ago

Open Science v0.7.2 boosts research workflow transparency

AIPOCH has released Open Science v0.7.2, an update to its open-source, model-agnostic AI workbench for scientific discovery. The new release prioritizes making AI research workflows more transparent, controllable, and easier to manage as researchers increasingly rely on autonomous agents for complex scientific tasks.