artie.com
Show HN: Artie – Real-time data replication to your data warehouse, self-serveHey HN, cofounder of Artie here. I’ve been working on real-time database replication using CDC (Postgres/MongoDB into Snowflake, BigQuery, Redshift) with my wife for the last three...news.ycombinator.com
Ask HN: ZealPHP – Dangers Isolating Request-State in Coroutines?I built ZealPHP (https://php.zeal.ninja), a runtime experiment with OpenSwoole - to isolate what leaks between coroutines. The idea is to bring back the good old PHP coding style, ...legato.gg
Show HN: Legato – a Rust audio graph framework with a minimal DSLI've been building Legato, a realtime audio graph framework for Rust. The idea is to sit somewhere between PureData/MaxMSP (graph-based, visual routing) and something like JUCE.The...Advertisement
github.com
Show HN: PrismCat – Local transparent proxy and debugging console for LLM APIsHi HN,I built PrismCat because I got tired of not knowing what LLM SDKs (like LangChain or various OpenAI/Anthropic wrappers) were silently injecting into my prompts behind the sce...recursant.ai
Show HN: Recursant – service mesh for governing AI agentsHello,I have just released Recursant to the public. I have been working on it for a while. It is a control plane for governing AI agents across stacks. It provides full observabili...appdevforall.org
Show HN: Code on the Go, an IDE for Android with On-Device Debugging (GPLv3)Hi HN, I’m Hal, the CTO at App Dev for All. I wanted to share a technical problem we worked on over the past year and how we approached it.We’ve been building Code on the Go, a ful...github.com
Show HN: Routiium – self-hosted LLM gateway with a tool-result guardRoutiium is a self-hosted, OpenAI-compatible LLM gateway I built. It does the table-stakes things you'd expect — managed keys, routing, rate limits, analytics — but the part I want...Advertisement
fittohire.com
Show HN: We replaced 5 ML models with 1 shared encoder on an $11/month VPSWe were running 5 fine-tuned MiniLM models for a resume-to-job matching pipeline — 455MB on an $11/month VPS, one per task. I consolidated them into a single shared encoder with 5 ...whereismyip.info
Show HN: WhereIsMyIP, A no-nonsense, one-second public location checkerHey HN,I originally built this tiny project a few years ago but ended up abandoning it. I recently revived and finished it to solve a very specific, recurring annoyance I had with ...news.ycombinator.com
Show HN: Compile English specs into 22 MB neural functions that run locallyWe built ProgramAsWeights (PAW) — https://programasweights.comYou describe a function in English — like "classify if this message is urgent" — and PAW compiles it into a tiny neura...news.ycombinator.com
Show HN: Bloomberg Terminal for LLM ops – free and open sourceBloomberg Terminal exists because financial traders needed one place to see everything: prices, risk, routing, counterparty health. You can't trade blind.LLM engineers are trading ...Advertisement
jointherevolution.today
Show HN: I visualized how AI agent systems accidentally become org chartsMost companies deploying AI agents are accidentally building organizations.You start with one agent. It gets overwhelmed. You add more. They start routing to each other based on wh...splice-cad.com
Show HN: Splice CAD – Wiring and cable assembly CAD with an agentic assistStill working on Splice CAD. The two most significant updates focus on handling design complexity and automating using agentic workflows. Previous Show HN here:https://news.ycombin...news.ycombinator.com
ARCHE3-7B – Sparse Moe with SmartRouter and Foundation Curriculum TrainingThis is my first post on HN — a bit nervous, but excited to share what I've been building.I’ve been working on a 7B sparse Mixture-of-Experts prototype that can actually run on con...docs.google.com
Show HN: Cross Domain Intelligence – The Translation Problem in American R&DThe U.S. spends $28 billion a year on preclinical research that cannot be reproduced. Pharmaceutical R&D productivity has declined 80-fold since 1950.It takes 17 years on average f...Advertisement
zero-human-labs.com
Show HN: Deploy a full autonomous AI org from a single YAML fileShow HN: Deploy a full autonomous AI org from a single YAML fileI built Zero Human Labs after spending too much time babysitting AI agent pipelines — manually routing tasks, watchi...news.ycombinator.com
Show HN: GitDB – GPU-accelerated vector database with Git-style version controlGitDB is a version-controlled vector database. Branch, merge, diff, and time-travel your embeddings the same way git handles source code. No server, no Docker — pip install gitdb-v...news.ycombinator.com
Analyzing OpenClaw's 3-layer defense against prompt injectionI’ve been analyzing how open-source AI execution engines (like OpenClaw) handle prompt injection. The conclusion is concerning: when an Agent has tool access (shell, DB, web), Prom...news.ycombinator.com
Proton's Swiss Myth: US Jurisdiction via Cloudflare and FAA Arbitration ClausesThe "Swiss Sanctuary" is a Network and Legal MirageAs a Business customer, I performed a technical and legal audit of Proton AG’s current infrastructure. The results show a systemi...Advertisement
github.com
Show HN: HDC-based function caller ranks #2 on BFCL V4 – $2.08 vs. Opus at $87I've been building Glyphh, a hyperdimensional computing runtime, for two years. This is the first HDC-based entry on the Berkeley Function Calling Leaderboard (BFCL V4), to my know...
