First screen, captured 8 days ago. Open the video.

Launch HN: Rivet (YC W23) – Scale and Orchestrate Agents on S3

What HN thinks

Impressive storage engineering, slightly lost in translation: even the PhDs and their coding agents want to know what an actor is.

Messaging is confusing
Several experienced developers say they can't tell what Rivet does or how actors differ from agents, and want the site to lead with the problem and use cases.
Storage design is compelling
The SSD tier with 2-of-3 AZ acknowledgement and background batching to S3 drew praise, with comparisons to celld and interest in a POSIX filesystem built on it.
Decouple agent loop from sandbox
Commenters discussed running the agent harness outside heavy sandboxes and using lightweight emulated environments, while some questioned whether orchestration speed matters when model latency dominates.

Consensus: Users who have tried Rivet, self-hosted or as a Durable Objects replacement, like it, but many think the pitch and UX need clearer explanation.

Recommended in the comments

Sprites (service): Pairing it with an external agent loop means you pay only for execution time, not for time spent waiting on inference.
just-bash (tool): It gives agents a familiar environment without needing a real Linux sandbox.
Cloudflare Durable Objects (service): Mentioned as the existing alternative some commenters use for agent state.

Summarised by Claude from the comment thread 7 days ago.

Points: 111
Comments: 58
Best rank: #4
Posted: 2026-11-05 by NathanFlurry
Category: DevOps & infra

rivet actor-model ai-agents s3 durable-objects rust sqlite self-hosted

All captures:

Full page

Captured 8 days ago. Click for the whole screenshot.

Looks similar

Screenshot of github.com: Show HN: Ramasite, a Self-Contained Laravel/Filament/SQLite CMS

Show HN: Ramasite, a Self-Contained Laravel/Filament/SQLite CMS (github.com)

3 points by DaleFranks 1 day ago | 0 comments

GitHub repository for RamaSite, a self-contained MIT-licensed CMS built with Laravel, Filament and SQLite, largely written with Claude Code.

cms laravel filament sqlite

Screenshot of github.com: 6-11X speedup running Qwen3.6 on my RTX 4090, full repo.

6-11X speedup running Qwen3.6 on my RTX 4090, full repo.(github.com)

10 points by AI4Science 6 hours ago | 0 comments

GitHub repository for Lightreason, a Python/CUDA project claiming LLM token-generation speedups for Qwen models on consumer GPUs, with benchmarks and a demo chat.

llm-inference speculative-decoding qwen rtx-4090

Screenshot of github.com: A general purpose Apple Silicon layer for x86-64 PCs

A general purpose Apple Silicon layer for x86-64 PCs (github.com)

125 points by iceboundrock 2 days ago | 52 comments

GitHub repository for Stela, a GPL-licensed UEFI boot program with an arm64-to-x86-64 translator and NVIDIA Metal driver to run macOS on x86-64 PCs.

apple-silicon binary-translation macos x86-64

Screenshot of github.com: Exact – a new cross platform UI framework

Exact – a new cross platform UI framework (github.com)

119 points by vmg12 4 days ago | 89 comments

GitHub repository for Exact, an MIT-licensed cross-platform UI framework from the Expo team, written mainly in Rust with Swift and JavaScript hosts.

expo ui-framework cross-platform rust

Screenshot of github.com: Show HN: Write GitHub Actions in any language: Loopt

Show HN: Write GitHub Actions in any language: Loopt (github.com)

7 points by Bnjoroge 4 days ago | 0 comments

GitHub repository for Loopt, a Rust tool that lets you write GitHub Actions workflows in languages like Rust, Python, TypeScript, and Go and compiles them to YAML.

github-actions ci-cd yaml rust

Screenshot of github.com: Show HN: Log every LLM call with tokens, cost, latency, and time to first token

Show HN: Log every LLM call with tokens, cost, latency, and time to first token (github.com)

3 points by garritfra 2 days ago | 0 comments

GitHub repository for llmtee, a self-hosted single-binary Go proxy that logs LLM API calls with tokens, cost, latency and time to first token to SQLite or Postgres.

llm-proxy llm-observability go sqlite

Full page

Looks similar

Show HN: Ramasite, a Self-Contained Laravel/Filament/SQLite CMS (github.com)

6-11X speedup running Qwen3.6 on my RTX 4090, full repo.(github.com)

A general purpose Apple Silicon layer for x86-64 PCs (github.com)

Exact – a new cross platform UI framework (github.com)

Show HN: Write GitHub Actions in any language: Loopt (github.com)

Show HN: Log every LLM call with tokens, cost, latency, and time to first token (github.com)

Related stories

Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents (github.com)

Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents

Launch HN: Respan (YC W24) – Open-source Rust AI gateway built around plugins

Launch HN: Alter (YC S25) – Access control for multi-user agents (alterauth.com)

Launch HN: Simantic (YC F26) – Firmware Simulation for AI Agents

Launch HN: Twenty.com (YC S23) – Open-source CRM