Hacker News ·
Show HN: IngotDB – SQL-based memory for LLM agents
Submitted by tjbroodryk. Hacker News recorded 1 points and 1 comments as of Oct 28, 2026 (UTC).
Home / Browse
Inspect repositories, adoption requirements and practical uses of open-source tools.
817 public stories
Hacker News ·
Submitted by tjbroodryk. Hacker News recorded 1 points and 1 comments as of Oct 28, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
A project which explores whether LLM agents can develop persistent behavioural divergence through a reconstructive memory system that forgets, distorts, and consolidates experiences over time.
Hacker News ·
Hi HN, I'm Salman. I started ReacherX as a side project in mid 2023 while studying at university, working part-time, and freelancing. I went full-time on it in June 2026. First time sharing something I built on Hacker News ;) ReacherX is an open-source platform for finding the people you're looking for on X/Twitter and LinkedIn. Unlike tools like Apollo, which pull from a static prospect database, ReacherX runs live searches against current data, so results can be very recent, and it's built for
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
Hacker News recorded 3 points and 2 comments as of Oct 19, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with static
Hacker News ·
Hacker News recorded 2 points and 0 comments as of Oct 14, 2026 (UTC).
Hacker News ·
Hacker News recorded 5 points and 0 comments as of Oct 13, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
I am in the process of learning European Portuguese because I moved to Portugal. I was having significant friction with Google Translate, so I started giving more and more instructions to Gemini Flash to create a powerful, low-friction experience when getting translations between English and EU Portuguese. This became a generally-powerful prompt that can serve any language combination, so I posted it to github. I haven't tried it with any other model providers yet. Let me know what you think!
Hacker News ·
Hacker News recorded 2 points and 3 comments as of Oct 13, 2026 (UTC).
Hacker News ·
Hacker News recorded 3 points and 0 comments as of Oct 11, 2026 (UTC).
Hacker News ·
Hacker News recorded 1 points and 1 comments as of Oct 11, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
Hacker News recorded 2 points and 0 comments as of Oct 9, 2026 (UTC).
Hacker News ·
Hacker News recorded 3 points and 0 comments as of Oct 8, 2026 (UTC).
Hacker News ·
Hacker News recorded 28 points and 6 comments as of Oct 13, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
This repo is an upgrade to my previous project, Cubic Doggo: https://github.com/SphericalCowww/CubicDoggo It has since implemented an IMU and several mechanical reinforcements. The next step will be simulation and reinforcement learning.
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
Submitted by kaushikbokka. Hacker News recorded 1 points and 0 comments as of Nov 7, 2026 (UTC).
Hugging Face Spaces ·
Interactive demo built with static
Hacker News ·
Hi HN, I'm Robel. I built LogClaw because I was tired of paying for Datadog and still waking up to pages that said "something is wrong" with no context. LogClaw is an open-source log intelligence platform that runs on Kubernetes. It ingests logs via OpenTelemetry and detects anomalies using signal-based composite scoring — not simple threshold alerting. The system extracts 8 failure-type signals (OOM, crashes, resource exhaustion, dependency failures, DB deadlocks, timeouts, connection
Hacker News ·
LLM coding agents (Claude Code, Codex, etc.) have structural weaknesses: blind retry loops, volatile learning, silent spec drift, and gate gaming. These aren't bugs in specific models — they're properties of goal-optimizing systems. ANDON applies Toyota Production System principles to address this: - Jidoka (autonomation): auto-detect failures and block forward-progress commands (git push, deploy) - Kaizen (continuous improvement): force Five Whys root cause analysis, then standardize prevention
Hacker News ·
I write a lot of markdown in Neovim — learning notes with KaTeX math, design docs with Mermaid/D2 diagrams, cross ... I also browse repos offline and preview static sites. No single tool handled all of that with live reload. So I built dirsv. It's a single Go binary with an embedded web UI, use fsnotify for watching filesystem, and send WebSocket events to reload the browser page. I also build dirsv.nvim that auto start dirsv at repo root (or current working dir if it's not a git repo), then ope
Hugging Face Spaces ·
Interactive demo built with gradio
Hacker News ·
Hacker News recorded 2 points and 1 comments as of Oct 20, 2026 (UTC).
Hacker News ·
Hacker News recorded 1 points and 0 comments as of Oct 18, 2026 (UTC).
Hacker News ·
Hacker News recorded 3 points and 1 comments as of Oct 18, 2026 (UTC).