Endo Familiar, an O-cap based JavaScript agent sandbox
AI agents today run with full access to your credentials and systems. Endo's object-capability model grants only what's needed, nothing more.
Endo Familiar, an O-cap based JavaScript agent sandbox launched on April 23, 2026 with 13 votes, #1,135 of 21,248 launches that month and more than 90% of that year's launches.
In plain words
Endo Familiar is a JavaScript agent sandbox built on O-cap, a security model. It allows developers to run JavaScript agents in an isolated environment with capability-based access controls. The sandbox restricts what agents can access and do based on explicit permissions rather than broad system access. It is designed for developers who need to execute untrusted or third-party JavaScript code safely. The capability-based security model stands out as an alternative to traditional permission systems.
written from the facts on this page · September 2026
From the sources
In the video above, Agoric/DCF software engineer Kris Kowal walks through a live demo of the Endo Familiar, a working prototype of the architecture discussed below. Watch him spawn an AI agent named “lal” with nothing but the ability to read an instruction primer, then extend it just enough capability to write a file, count letters in a sandboxed program, and produce a read-only view of a directory by having the agent itself write the program that narrows the capability. The demo ends with a colleague joining over a WebSocket relay and sharing a directory from their machine, which the agent summarizes without ever knowing the files are remote. The ideas that follow are easier to…from dcfoundation.io
Does a similar job
all alternatives →
EphoAug 2026 · epho.io · ▲156Hey folks, Burak here. Epho is an API that allows running Claude Code, Codex or Opencode in a sandbox in the cloud. It abstracts away sandboxes, and allows running coding agents with a single HTTP request. Epho came out of our own struggles with building our own AI analyst: - Sandboxes give you bare machines; you need to configure them for agentic workloads. - Each agent behaves differently, and you need to build integrations with each of them. - Sandbox providers are not very reliable, which means you need to figure out a multi-provider strategy to avoid failures. - Logging, artifacts,…
- OOoso – Open-Source Policy Engine for Authorization2020 · osohq.com · ▲44
Oso helps companies run agents in production with confidence using monitoring, access controls, and automated least privilege.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app