marimohub – self-hostable marimo notebooks
The marimo team released marimohub, a self-hostable platform for storing, managing, and running marimo notebooks on a team's own infrastructure. The hub keeps notebook metadata, versions, snapshots, a…
The marimo team released marimohub, a self-hostable platform for storing, managing, and running marimo notebooks on a team's own infrastructure. The hub keeps notebook metadata, versions, snapshots, a…
Agent37, a cloud platform founded by Vishnu Krishnaprasad, runs AI agent harnesses including Claude Code, OpenAI Codex, Hermes and OpenClaw in persistent cloud sandboxes starting at under $5 a month f…
BoxLite ranked first of ten projects in HVTracker's Sandboxes & Runtimes category on October 3, 2026, with an HVTrust score of 85.6 — the only A grade in the category, ahead of E2B (78.2) and NVIDIA's…
DigitalOcean and Uber both shipped production-grade isolation for autonomous agents on October 1, with DigitalOcean's Agent Droplets built on Firecracker microVMs and Uber's gateway scoping permission…
A developer's comparison of OpenAI's managed ChatGPT dots agents against the self-hosted, Apache-2.0-licensed Rakazo framework argues that the two differ fundamentally in cost mechanics and control: C…
Engrams, a self-hosted orchestrator for AI coding agents, launched as an open source alternative to Devin, running each agent in its own Firecracker microVM and snapshotting idle VMs so sessions cost …
A developer compared seven cloud sandbox and VM providers for hosting AI agents — machine0, OpenComputer, E2B, Daytona, Modal, Fly.io Sprites, and Vercel Sandbox — testing each SDK up to the API-key c…
A new tutorial demonstrates building an AI agent that processes receipts and invoices inside an E2B Firecracker microVM sandbox, mounting a lakeFS branch as an ordinary filesystem so every change is v…
UFO released ufo-core, an open source runtime for AI agents that lets teams run agents on their own infrastructure, with the same runtime powering UFO's hosted service at ufo.ai. The runtime runs as a…
Rails published a landing page and benchmark suite pitching the framework as a good fit for coding agents, arguing that convention over configuration, Ruby's token density, and decades of public Rails…
Zuse released an open-source, chat-first desktop app that wraps Claude Code, Codex, Grok, Gemini, Cursor, OpenCode, and Pi coding-agent CLIs in a persistent, project-aware interface with locally store…
OpenAI released its Agents API into public beta on September 10, exposing the same harness that runs Codex — built-in context compaction, session persistence, and multi-step tool coordination — at no …
E2B sandboxes can be monitored and traced with OpenTelemetry by instrumenting the application that creates them, according to a technical guide from SigNoz. The guide details five telemetry paths — ap…
Tensorlake redesigned its sandbox proxy to collapse a second Layer 7 hop down to Layer 4, publishing before-and-after numbers for the change, according to a comparison of sandbox networking across Ten…
A developer documented a custom integration that runs OpenAI's first-party Computer Use and Browser Use runtimes inside an E2B sandbox, pairing the Codex CLI with a virtual Linux desktop built from Xv…
Vercel announced on Sept 3, 2026 that Cursor's Cloud Agents can now execute inside Vercel Sandbox, making Vercel one of eight infrastructure vendors—including AWS Lambda, Cloudflare, Coder, Daytona, E…
Trail of Bits released Coop, an open-source Rust CLI that runs AI coding agents like Claude Code and Codex inside disposable Firecracker and Lima virtual machines, isolating them from the host system …
Anthropic's Claude Code mobile agent runs inside a Firecracker microVM with a custom Rust init (process_api) as PID 1, a 324 MB Bun harness on a read-only disk, and host-driven lifecycle management, a…
OpenAI shipped GPT-6 Astra, a model designed to operate computers and complete multi-step tasks rather than just chat. The developer behind Aantraa and Scrapefast notes the real opportunity lies in th…
A new analysis of 16,893 coding-agent runs found that Claude, Codex, and Cursor show distinct preferences for third-party tools, with the study retaining 5,292 valid sessions across 51 codebases and 1…