Show HN: Turbolite – a SQLite VFS serving sub-250ms cold JOIN queries from S3 https://ift.tt/eOsH6KB

Show HN: Turbolite – a SQLite VFS serving sub-250ms cold JOIN queries from S3 I built a SQLite VFS in Rust that serves cold queries directly from S3 with sub-second performance, and often much faster. It’s called turbolite. It is experimental, buggy, and may corrupt data. I would not trust it with anything important yet. I wanted to explore whether object storage has gotten fast enough to support embedded databases over cloud storage. Filesystems reward tiny random reads and in-place mutation. S3 rewards fewer requests, bigger transfers, immutable objects, and aggressively parallel operations where bandwidth is often the real constraint. This was explicitly inspired by turbopuffer’s ground-up S3-native design. https://ift.tt/lP2DbjX The use case I had in mind is lots of mostly-cold SQLite databases (database-per-tenant, database-per-session, or database-per-user architectures) where keeping a separate attached volume for inactive database feels wasteful. turbolite assumes a single write source and is aimed much more at “many databases with bursty cold reads” than “one hot database.” Instead of doing naive page-at-a-time reads from a raw SQLite file, turbolite introspects SQLite B-trees, stores related pages together in compressed page groups, and keeps a manifest that is the source of truth for where every page lives. Cache misses use seekable zstd frames and S3 range GETs for search queries, so fetching one needed page does not require downloading an entire object. At query time, turbolite can also pass storage operations from the query plan down to the VFS to frontrun downloads for indexes and large scans in the order they will be accessed. You can tune how aggressively turbolite prefetches. For point queries and small joins, it can stay conservative and avoid prefetching whole tables. For scans, it can get much more aggressive. It also groups pages by page type in S3. Interior B-tree pages are bundled separately and loaded eagerly. Index pages prefetch aggressively. Data pages are stored by table. The goal is to make cold point queries and joins decent, while making scans less awful than naive remote paging would. On a 1M-row / 1.5GB benchmark on EC2 + S3 Express, I’m seeing results like sub-100ms cold point lookups, sub-200ms cold 5-join profile queries, and sub-600ms scans from an empty cache with a 1.5GB database. It’s somewhat slower on normal S3/Tigris. Current limitations are pretty straightforward: it’s single-writer only, and it is still very much a systems experiment rather than production infrastructure. I’d love feedback from people who’ve worked on SQLite-over-network, storage engines, VFSes, or object-storage-backed databases. I’m especially interested in whether the B-tree-aware grouping / manifest / seekable-range-GET direction feels like the right one to keep pushing. https://ift.tt/v14ASUL March 27, 2026 at 12:28AM

Show HN: Orloj – agent infrastructure as code (YAML and GitOps) https://ift.tt/KnbrZjV

Show HN: Orloj – agent infrastructure as code (YAML and GitOps) Hey HN, we're Jon and Kristiane, and we're building Orloj ( https://orloj.dev ), an open-source (Apache 2.0) orchestration runtime for multi-agent AI systems. You define agents, tools, policies, and workflows in declarative YAML manifests, and Orloj handles scheduling, execution, governance, and reliability. We built this because running AI agents in production today looks a lot like running containers before Kubernetes: ad-hoc scripts, no governance, no observability, no standard way to manage the lifecycle of an agent fleet. Everyone we talked to was writing the same messy glue code to wire agents together, and nobody had a good answer for "which agent called which tool, and was it supposed to?" Orloj treats agents the way infrastructure-as-code treats cloud resources. You write a manifest that declares an agent's model, tools, permissions, and execution limits. You compose agents into directed graphs — pipelines, hierarchies, or swarm loops. The part we're most excited about is governance. AgentPolicy, AgentRole, and ToolPermission are evaluated inline during execution, before every agent turn and tool call. Instead of prompt instructions that the model might ignore, these policies are a runtime gate. Unauthorized actions fail closed with structured errors and full audit trails. You can set token budgets per run, whitelist models, block specific tools, and scope policies to individual agent systems. For reliability, we built lease-based task ownership (so crashed workers don't leave orphan tasks), capped exponential retry with jitter, idempotent replay, and dead-letter handling. The scheduler supports cron triggers and webhook-driven task creation. The architecture is a server/worker split. orlojd hosts the API, resource store (in-memory for dev, Postgres for production), and task scheduler. orlojworker instances claim and execute tasks, route model requests through a gateway (OpenAI, Anthropic, Ollama, etc.), and run tools in configurable isolation — direct, sandboxed, container, or WASM. For local development, you can run everything in a single process with orlojd --embedded-worker --storage-backend=memory. Tool isolation was important to us. A web search tool probably doesn't need sandboxing, but a code execution tool should run in a container with no network, a read-only filesystem, and a memory cap. You configure this per tool based on risk level, and the runtime enforces it. We also added native MCP support. You register an MCP server (stdio or HTTP), Orloj auto-discovers its tools, and they become first-class resources with governance applied. So you can connect something like the GitHub MCP server and still have policy enforcement over what agents are allowed to do with it. Three starter blueprints are included (pipeline, hierarchical, swarm-loop). Docs: https://docs.orloj.dev We're also building out starter templates for operational workflows where governance really matters. First on the roadmap: 1. Incident response triage, 2. Compliance evidence collector, 3. CVE investigation pipeline, and 4. Secret rotation auditor. We have 20 templates in mind and community contributions are welcome. We're a small team and this is v0.1.0, so there's a lot still on the roadmap — hosted cloud, compliance packaging, and more. But the full runtime is open source today and we'd love feedback on what we've built so far. What would you use this for? What's missing? https://ift.tt/z7vpGBV March 26, 2026 at 10:37AM

Show HN: I built a voice AI that responds like a real woman https://ift.tt/ZyFYoXK

Show HN: I built a voice AI that responds like a real woman Most men rehearse hard conversations in their head. Asking someone out, navigating tension, recovering when things get awkward. The rehearsal never works because you're just talking to yourself. I built vibeCoach — a voice AI where you actually practice these conversations out loud, and the AI responds like a real woman would. She starts guarded. One-word answers, a little skeptical. If you escalate too fast or try something cheesy, she gets MORE guarded. If you're genuine and read the moment right, she opens up. Just like real life. Under the hood it's a multi-agent system — multiple AI agents per conversation that hand off to each other as her emotional state shifts. The transitions are seamless. You just hear her tone change. Voice AI roleplay is a proven B2B category — sales teams use it for call training. I took the same approach and pointed it at the conversation most men actually struggle with. There's a hard conversation scenario too — she's angry about something you did, she's not hearing logic, and you have to navigate her emotions before you can resolve anything. That one's humbling. Live at tryvibecoach.com. Built solo. Happy to answer questions. March 26, 2026 at 12:38AM

Show HN: Τ³-Bench is out – can agents handle complex docs and live calls? https://ift.tt/oGVtFEi

Show HN: Τ³-Bench is out – can agents handle complex docs and live calls? τ-Bench is an open benchmark for evaluating AI agents on grounded, multi-turn customer service tasks with verifiable outcomes. It's been great to see the community adopt it since launch — this is now the third iteration. With τ³-Bench, we're extending it to two new settings: knowledge-intensive retrieval and full-duplex voice. τ-Knowledge: agents must navigate ~700 interconnected policy documents to complete multi-step tasks. Best frontier model (GPT-5.2, high reasoning) hits ~25%. The surprising part: even when you hand the model the exact documents it needs, performance only reaches ~40%. We found that the bottleneck isn't retrieval — it's reasoning over complex, interlinked policies and executing the right actions in the right order. τ-Voice: same grounded tasks, but over live full-duplex voice with realistic audio — accents, background noise, interruptions, compressed phone lines. Voice agents score 31–51% in clean audio conditions and 26–38% in realistic ones. A consistent failure pattern across providers (OpenAI, Gemini, xAI): agent mishears a name or email during authentication, and everything downstream fails. We also incorporated 75+ task fixes to the original airline, retail, and telecom domains — many based on community audits and PRs (including contributions from Amazon and Anthropic). We believe a benchmark is only as good as its maintenance, and we're grateful for the community's help improving it. Code and leaderboard are open — we'd welcome community submissions and feedback. Blog post (papers, code, leaderboard): https://ift.tt/FQZ0Wkm... March 25, 2026 at 10:56PM

Show HN: Gridland: make terminal apps that also run in the browser https://ift.tt/6ie1RTQ

Show HN: Gridland: make terminal apps that also run in the browser Hi everyone, Gridland is a runtime + ShadCN UI registry that makes it possible to build terminal apps that run in the browser as well as the native terminal. This is useful for demoing TUIs so that users know what they're getting before they are invested enough to install them. And, tbh, it's also just super fun! Gridland is the successor to Ink Web (ink-web.dev) which is the same concept, but using Ink + xterm.js. After building Ink Web, we continued experimenting and found that using OpenTUI and a canvas renderer performed better with less flickering and nearly instant load times. We're excited to continue iterating on this. I expect a lot of criticism from the "why does this need to exist" angle, and tbh, it probably doesn't - it's really mostly just for fun, but we still think the demo use case mentioned previously has potential. - Chris + Jess https://ift.tt/rSxBjGT March 24, 2026 at 10:27PM

Show HN: I built a party game that makes fun of corporate culture https://ift.tt/wbjpnc2

Show HN: I built a party game that makes fun of corporate culture Made the first party game that makes fun of corporate culture! Would love for you to try it out. https://ift.tt/ZFvM82t March 25, 2026 at 12:09AM

Show HN: Littlebird – Screenreading is the missing link in AI https://ift.tt/3Q79Kr5

Show HN: Littlebird – Screenreading is the missing link in AI https://littlebird.ai/ March 23, 2026 at 11:09PM