标签：#devchallenge

This is a submission for the GitHub Finish-Up-A-Thon Challenge Originally, I didn't plan to join...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built I started this project as a way to escape the noise of social media we have today and to focus on what matters. It was a personal project at first and I just wanted to get an uncluttered messaging working. After a while a few friends of mine started looking into it and liked the vision as well. Then I received a notification of the event and that excitement of finishing it up got all over me - I felt like a kid again. Demo Because I want to have control over my data, I self host the version on a small microcontroller, which is more than sufficient for me and my friends. To get a sneak peak at how it looks, check out this . (Be aware that this is not functional as there is no server connected) I made some demo accounts to give a sense of how the app looks and feels: The Comeback Story Because I had the messaging already working, I had to mainly implement the rest of the features, including enhanced profiles, networks and posts creation. Another thing I really had to work on was the design. Before, it was mainly a black and white testing ground - something every end user would be scared of. My Experience with GitHub Copilot I am really not talented in terms of designing a usable interface. However, my friends really didn't want to use a half-baked up command line application. Copilot really helped me achieve that polished look. Just to give a glimpse of how it feels, one friend of mine even described it as an enhancing feature when navigating through the tabs. Furthermore, although it mostly was bug free, "It worked, until it didn't". Sometimes I spent hours fixing or rather finding some annoying bugs. And because Copilot is a real expert in these languages, it was quite a moment when it guided me towards finding the mistakes I made.

Submission Template Challenge: Build With Hermes Agent Project: CompliScore AI compliance health checks for Indian startups Repo/live-demo: https://github.com/nehaprasad-dev/hermes-scout What I built CompliScore gives Indian startup founders a compliance score out of 100 in under a minute - overdue GST filings, MCA returns, penalty exposure, and a plain-English action plan. The upgrade for this challenge: I replaced the one-shot Groq summary with a Hermes Agent reasoning loop that plans an investigation, calls deterministic compliance tools, and writes a prioritized report - with a collapsible agent trace so judges can see the agentic work. Why an agent loop fits here Compliance analysis is conditional. A company with overdue GST needs a filing-calendar deep dive; one with active notices needs notice triage; a clean company needs a light touch. A single prompt guesses all of this at once. An agent that calls tools based on what it finds produces tighter, grounded reports. Hermes Agent integration Scan → computeHealth (deterministic score) → Hermes Agent loop (plan → tool calls → report) → agent trace in UI ↓ on failure Groq one-shot → static fallback Four tools exposed to Hermes (scores never hallucinated): Tool Purpose score_company Canonical score, risk level, pending tasks estimate_penalty GST / MCA / notice penalty breakdown filing_calendar GSTR-3B, GSTR-1, MCA deadlines (90-day horizon) classify_notices Severity labels for pending government notices The agent runs over Hermes's OpenAI-compatible /chat/completions API with function calling — self-hostable via vLLM, LM Studio, Ollama, etc. Transparency: Every successful agent run returns an agentTrace — plan steps, tool names, compact result previews — rendered in a collapsible panel under the AI action plan. Reliability: Three-tier fallback (Hermes → Groq → static). Scans never break. Tech stack Next.js 16 (App Router), TypeScript, Tailwind v4 Hermes Agent (OpenAI-compatible tool-calling loop) Groq fallback ( ll

My Hermes Agent Mac just received a signed, secure and monitored message from a Claude Managed Agent, and got a reply! - A solution for long runtime work, A2A ID and security. What I Built A solution that enables two agents with different owners on a shared identity network, a Hermes and a Claude Managed Agent (Claude platform) talking to each other across the internet. Every message is Ed25519 signed by the sender. Every receiver verifies the signature against a public registry and shows a blue tick before acting. Continuous Agent Monitoring A handshake proves identity once but agents in a long runtime world don't trade a single message, they hold ongoing, autonomous conversations across hours, days, and many turns. Keys get compromised, agents get swapped, a colleagues behaviour drifts, all after the initial check. ZipViz re-verifies every message signature, registry chain, freshness, and watches the stream over time for behavioural anomalies. Trust is re-earned on every turn. So this agent was who it claimed this morning," but "this agent is who it claims, on this message, right now." The demo agents on the ZipViz network: mac-her.smc.viz — Hermes Agent on my Mac Mini brendan-clau.smc.viz — Claude Agent in Cloud When Mac sends a message to brendan-clau, Mac's private key signs it. Brendan-clau verifies the signature against ZipViz's registry, and checks it just ran with the MCP (algorithm, key fingerprint, registry chain, timestamp), then replies signed. Same flow in reverse. Same flow Hermes ↔ Hermes , or Claude ↔ Openclaw . The runtime doesn't matter; the identity layer does. "I received a signed message from mac-her.smc.viz". Reads back the four checks it just ran: ✓ Algorithm: Ed25519 ✓ Key fingerprint: ab52afe... matches registry ✓ Registry chain: mac-her → smc.viz → .viz (Handshake) all resolved ✓ Timestamp: 2026-05-31 11:18 UTC, fresh Demo Hermes continuous monitoring and verification with A2A Protocol Code One MCP server: [ zipviz-mcp ] https://www.npmjs.

This is a submission for the Hermes Agent Challenge : Build With Hermes Agent What I Built A small backstory on my coding origins I learnt coding by secretly studying from a python book pdf on my Computer Scientist father's work laptop. That very day I wrote a program that inputs a user's name and prints: "You are mad {name}!" and had a lot of fun pranking my brother using that script. Since then, there have been very few moments where coding felt as magical, because the more you understand syntax, the more you understand the magic underneath your code. That is, until you meet a genius piece of magic such as Hermes. My app idea I built a Fitness coach inside Hermes that learns and adapts based on your daily feedback. According to your goals, performance, and time allocated, it adjusts your current plan. For the purpose of this hackathon I tested it via terminal ui (tui) but I plan to release the polished version on chat apps such as telgram and whatsapp for painless daily checkins. Demo Code Github link My Tech Stack Hermes + node.js. Kept it simple for this quick dive. How I Used Hermes Agent Building an AI application that feels truly personal requires more than just a clever prompt; it requires state, memory, and the ability to adapt over time. During a recent hackathon, I set out to build an autonomous AI fitness coach. Not just a chatbot that spits out generic workout templates, but a system that onboards a user, sets a multi-month timeline, generates habit blocks, and adjusts daily based on feedback. To achieve this, I used Hermes , an agentic framework designed for stateful, long-running applications. Here is a breakdown of how I built it, the challenges faced, and why Hermes was the perfect tool for the job. Why This App is a Perfect Fit for Hermes Most LLM interactions are stateless. You ask a question, you get an answer, and the session ends. A fitness journey, however, is a deeply stateful process. It spans weeks or months and requires constant recalibrat

This is a submission for the Hermes Agent Challenge Agentic Web3: Automating Blockchain Workflows with Hermes Tags: #hermesagentchallenge , #web3 , #agents , #solana The blockchain industry has spent the last decade building decentralized, permissionless infrastructure. However, the user experience layer interacting with this infrastructure remains overwhelmingly manual. Decentralized applications (dApps) require users to constantly monitor markets, parse complex data, and manually sign every transaction. The next evolution of Web3 isn't just about faster blockchains; it is about autonomous execution. By integrating large language models and agentic frameworks with smart contracts, we can transition from a paradigm of manual execution to intent-based autonomy . In this article, we will explore how to bridge the gap between AI and decentralized networks by automating blockchain workflows using the Hermes Agent framework. We will look at the architecture of an on-chain agent, how it reads and writes to a network, and how high-performance environments like Solana are making these agentic experiences viable. The Paradigm Shift: From Passive Wallets to Active Agents Currently, most AI in Web3 is limited to read-only analytical tools—chatbots that can summarize a smart contract or pull token prices from an API. While useful, these are fundamentally passive systems. An active agent is different. Powered by a framework like Hermes Agent, an active agent can: Observe: Continuously monitor on-chain events via RPC nodes or webhooks. Reason: Use its LLM core to interpret those events against a set of user-defined goals or risk parameters. Act: Formulate a transaction, sign it via a secure wallet environment, and broadcast it to the network. This opens up massive possibilities. Imagine an agent that automatically manages your decentralized finance (DeFi) positions, rebalancing a portfolio based on yield changes across different protocols. Or consider fully on-chain gaming, where

``This is a submission for the GitHub Finish-Up-A-Thon Challenge What I...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built VKara is a browser-based karaoke room app for singing at home with friends or family. It is not trying to replace YouTube. YouTube is already great at playing videos. It already has almost every karaoke song we need. But YouTube is not really designed to manage a karaoke night where many people want to choose songs together. That is the gap VKara tries to fill. You open VKara on a TV or laptop as the main playback screen. Everyone else joins the same room from their phone using a 4-digit room code or QR code. Then anyone can search for songs, add them to the queue, pause, resume, or skip. The TV only needs to play the video. Everyone's phone becomes their own remote. That is the whole idea. Simple enough to explain in one sentence. Not simple enough to build in one weekend. I learned that part the hard way. Demo Links: Live demo: https://vkara.vercel.app/en GitHub repo: https://github.com/lehuygiang28/vkara Before branch: https://github.com/lehuygiang28/vkara/tree/before Old backend repo: https://github.com/lehuygiang28/vkara-api Small warning: the demo is running on limited resources, so if it is slow, please give it a moment. My wallet is still a student wallet. lol. The flow is: Open VKara on a TV or laptop. Join the room from a phone by code or QR. Search for a karaoke video. Add it to the shared queue. Control playback together. Before: the idea worked, but the product still felt like a video app squeezed into a karaoke use case. After: the mobile flow is now focused on joining, searching, choosing an action, and controlling playback. The Comeback Story I started VKara around early 2025. At that time, my goal was very personal. I wanted a better way to sing karaoke at home with friends. The normal setup was: open YouTube on a TV, search for karaoke videos, and pass control around. It worked, but it was awkward. One person was searching. Another person accidentally played a video immedia

This is a submission for the Hermes Agent Challenge , under the Write About Hermes Agent prompt. I've spent the last week testing AI memory failure modes in a public evaluation harness. That work changed how I read agent memory systems. This is a writing submission, not a build submission. I did not build a Hermes Agent project for this challenge. I am writing from the perspective of someone testing how memory failures show up once agents can act. So when I look at Hermes Agent, the question I care about is not only: Can the agent remember useful things? The harder question is: When memory conflicts, which memory is allowed to govern the agent's action? That distinction matters. Hermes Agent is interesting because it is not just a chat interface. Its documentation describes an open-source agentic system with tool use, project context, persistent memory, skills, browser automation, checkpoints, delegation, scheduled tasks, and multiple memory providers. That is exactly the kind of system where memory stops being a convenience feature and starts becoming part of the agent's operating boundary. If an agent can run tools, edit files, browse, delegate work, schedule tasks, and remember across sessions, then memory is no longer just "context." Memory becomes governance. The Memory Problem I Would Watch For In a simple chatbot, bad memory is annoying. In an agent, bad memory can become operational. The failure mode is not only that the agent forgets something. Sometimes the more dangerous failure is that it remembers the wrong thing too confidently. A memory can be: relevant but stale, relevant but low-authority, relevant but superseded, relevant but only context, relevant but not allowed to determine the action. That is the distinction my own tests kept running into. Retrieval systems are usually good at answering: What memory is closest to the user's request? But safety often depends on a different question: What memory is allowed to decide what the agent should do? Thos

This is a submission for the Hermes Agent Challenge : Write About Hermes Agent Hello, DEV friends! 👋 If you have been exploring the world of Artificial Intelligence lately, you have probably heard a lot of buzz about "AI Agents." But what does it actually feel like to build with one? Today, I want to share my personal experience working with Hermes Agent . I used it to build a smart assistant called the Alpha-Dairy Quant Pipeline —a system that helps track and make sense of food market data. ( https://github.com/HopeBestWorld/alpha-dairy-pipeline ) Whether you are an expert coder or just curious about AI, I hope this friendly guide inspires you to try building an agent of your own! What is Hermes Agent, Anyway? Think of a standard AI as a helpful chatbot that answers questions when you ask them. An AI Agent , on the other hand, is more like a proactive assistant. You give it a big goal, and it sits down, makes a step-by-step plan, uses digital tools, runs code, and checks its own work until the job is done. For my project, I wanted to track market prices for three major dairy products: Cheddar Blocks, Butter, and Dry Whey. Instead of doing all the math and graphing by myself, I let Hermes Agent take the wheel. The Magic of Multi-Step Reasoning The coolest part of working with Hermes Agent is watching it "think". When I asked my agent to look at our data database ( market_intelligence_3.db ) and find the best trading strategy,it followed a beautiful planning loop: Checking the Files: It looked at our setup files ( tickers.yaml and requirements.txt ) to make sure all its tools were ready. Running the Math: It triggered a Python program ( backtest_engine.py ) to study weekly market history. Making Decisions: It realized that Dry Whey was way too wild and risky to trade right now, so it intelligently gave it a 0% safety rating and put the focus on Cheddar and Butter instead. Drawing and Sharing: It automatically drew a beautiful performance chart ( backtest_analysis.png

This is a submission for the Hermes Agent Challenge : Build With Hermes Agent The Problem Nobody Talks About Every time the Reserve Bank of India publishes a circular, somewhere inside an Indian bank, a compliance officer opens a PDF. They read it. They try to figure out what it means for their institution specifically. They write a summary email. They forward it to five department heads. They chase those department heads for two weeks to confirm it's been actioned. They build a spreadsheet to track all of this. And then the next circular drops and the cycle starts again. RBI publishes hundreds of circulars a year. SEBI publishes more. MCA publishes more still. Compliance teams at Indian banks are drowning — not because they're incompetent, but because the volume of regulatory output has outpaced any reasonable human ability to track it manually. The fine for missing a deadline isn't a polite reminder. It's a penalty notice. This is the problem I built for. What I Built RBI Regulatory Digest Agent — an autonomous multi-step agent powered by Hermes Agent that monitors RBI and SEBI publication feeds, reads every new circular, extracts structured action points from the regulatory text, and delivers a formatted intelligence report to compliance teams automatically. No human reads the circular first. No human decides what's important. No human routes it to the right department. The agent does all of that. The pipeline RBI/SEBI feeds → new circular detected → full text extracted → LLM analysis → structured action points → risk classification → HTML dashboard generated → email delivered Every action point extracted contains: What needs to be done — specific and actionable, not a vague summary Deadline — parsed from the circular text Responsible department — Credit, Compliance, Treasury, Operations, IT, Legal Evidence required — what documentation confirms completion Priority — Critical (overdue or <7 days), High, Medium, Low From a new circular to a structured compliance b

This is a submission for the * Hermes Agent Challenge * : Build With Hermes Agent What I Built CareSync is a local health memory agent for student caregivers. I'm Naomi, a 21-year-old engineering student. Between classes I help care for my grandma Kamala (78, high blood pressure, type 2 diabetes). I often forgot details from previous doctor visits, missed symptom patterns, and struggled to hand over care information to family members. CareSync solves that with longitudinal memory. Symptoms, meals, vitals, medications, and reports are stored in a local SQLite database. The CLI can search history, identify patterns, and generate appointment summaries. Hermes Agent exposes the same capabilities through natural language. What you get: One-line logging: ./caresync add "dizzy spell after lunch" Pattern search across weeks of history Medication tracking and report imports Doctor questions, appointment briefs, and handoff notes Full audit log of agent actions 7 Hermes skills mapped to real terminal commands Local-first design with no cloud storage CareSync is not medical advice. It helps caregivers observe, organize, and prepare. Demo The demo walks through: Logging a new symptom Searching health history for recurring patterns Generating doctor questions and appointment briefs Using Hermes in natural language to query past events Reviewing the audit trail of actions taken Example commands shown in the demo: ./caresync search --person Kamala --query dizziness ./caresync timeline --person Kamala ./caresync questions --person Kamala ./caresync brief --person Kamala --days 14 ./caresync chat "has grandma been dizzy before?" Code Repository: https://github.com/Byte-Sized-Brain/caresync Architecture My Tech Stack Hermes Agent Python 3.12 SQLite agentskills.io skill framework Terminal-based CLI Nous Portal How I Used Hermes Agent CareSync uses Hermes Agent as the orchestration layer between natural language and real caregiving workflows. I created 7 Hermes skills that map directly

This is a submission for the Hermes Agent Challenge : Write About Hermes Agent What if the biggest limitation in AI today isn't reasoning, model size, or context windows? What if it's memory? Every morning, millions of people open ChatGPT, Claude, Gemini, or another AI assistant and start a conversation. The AI seems intelligent. It writes code. It explains concepts. It helps brainstorm ideas. It can even help design an entire software architecture. Then the conversation ends. Tomorrow? It remembers nothing. Imagine hiring a senior engineer who forgets everything at the end of every workday. Every morning you would need to explain: What your company does How your product works Which technologies you use Why certain decisions were made What happened yesterday Nobody would call that employee productive. Yet this is exactly how most AI systems operate. And it reveals something important: Most AI agents aren't actually learning from experience. They're simply reasoning over whatever context happens to be available right now. That distinction may define the future of agentic AI. Because the next generation of AI won't just need better reasoning. It will need memory. And that's where Hermes Agent becomes interesting. The Strange Reality of Modern AI The public perception of AI often looks like this: User → AI → Intelligence But the reality is closer to this: User → Context Window → AI → Response The AI only knows what exists inside its current context. Once that context disappears, so does most of its understanding. This is why many AI experiences feel surprisingly repetitive. You spend 30 minutes explaining your project. The AI finally understands your goals. The answers become better. The recommendations become more relevant. Then the session ends. The next conversation starts from scratch. Not because the model isn't powerful. But because the knowledge never became persistent. Context Windows Are Not Memory A context window is not memory. It is temporary working space.

This is a submission for the Hermes Agent Challenge : Write About Hermes Agent Most AI agents have a dirty secret: they forget everything the moment the session ends. You explain your project once. Then again next time. And again. The agent never gets better at your workflow — it just stays a general-purpose tool that happens to be smart. Hermes Agent is built differently. It ships with two systems that together form something closer to a genuine long-term memory: a Skills System and a Persistent Memory layer. This post digs into how they actually work — not the marketing summary, but the mechanics. The Problem With Stateless Agents Before getting into Hermes, it's worth understanding what problem this solves. Standard LLM-based agents operate inside a context window. Everything the agent knows during a session lives in that window. When the session ends, it's gone. The next time you open a conversation, you're talking to an agent with no memory of you, your codebase, your preferences, or the workflows you've developed together. Some tools patch this with naive "memory" — they dump a text blob of past conversations into the system prompt. This works up to a point, but it's not selective, it gets expensive as context grows, and it doesn't help the agent get better at tasks — just recall facts. Hermes takes a different approach with two distinct systems serving different purposes. System 1: The Skills System (Procedural Memory) Skills in Hermes aren't plugins you install. They're on-demand knowledge documents — markdown files the agent loads when it needs them, and more importantly, creates on its own when it discovers something worth remembering. The SKILL.md Format Every skill is a structured markdown file with a YAML frontmatter header: --- name : deploy-runbook description : Our deployment runbook — services, rollback, Slack channels version : 1.0.0 metadata : hermes : tags : [ deployment , runbook , internal ] requires_toolsets : [ terminal ] --- # Deploy Runbook

This is a submission for the [GitHub Finish-Up-A-Thon Challenge] What I Built LeadBotX is an AI-powered lead generation platform prototype designed to simulate how modern businesses can automatically discover, filter, and manage high-quality leads using intelligent automation workflows. This project is not just a simple frontend demo — it represents a revived college-level concept that I initially started earlier but left incomplete due to time constraints and complexity. For this challenge, I revisited the idea and transformed it into a fully structured SaaS-style frontend system with improved UI, better workflow representation, and a more realistic product-like experience. The main goal of LeadBotX is to visually demonstrate how an AI-based lead generation system works end-to-end in a real-world SaaS environment. Tech Stack This project was built using modern frontend technologies: React.js → Component-based UI structure CSS3 → Custom responsive styling system AOS (Animate On Scroll) → Smooth scroll animations Lucide Icons & React Icons → UI iconography GitHub Copilot → Assisted in code generation, debugging, and UI improvements Demo Source Code: https://github.com/Khushisingh-dev/LeadBotX Production Landing Page: https://lead-bot-x.vercel.app/ Before (Initial Version)- After (Final Version)- The Comeback Story This project originally started as a college-level concept during my development learning phase. At that time, I built only a basic structure and initial UI, but I was unable to complete it due to time limitations and complexity of the idea. It remained an unfinished project for a long time. When I came across this challenge, I decided to revisit LeadBotX and transform it into something more meaningful and complete. Instead of just polishing the UI, I focused on: Rebuilding the structure into a proper SaaS layout Improving workflow clarity and user journey Enhancing UI/UX consistency across all sections Making the product feel like a real-world AI tool prot

"Stop summarizing the noise. Start executing it." Tsundoku Slayer is an autonomous agentic system powered by Hermes Agent that overnight patrols your unread tabs, mercilessly filters out 90% of the information overload, and saves only the information capable of killing your current blocker. 🎯 The Problem While debugging a painful Streamlit IndexError, I realized my real issue wasn't a lack of information—it was too much information. I had documentation, API feeds, tech news, and bookmarks all competing for my limited focus. Most AI tools try to "summarize" everything, which ironically generates more text to read and increases cognitive load. I didn't need another summarizer. I needed an autonomous agent capable of deciding what NOT to read right now. 🧠 How Hermes Agent Drives the Workflow This project doesn't just scrape webs; Hermes Agent acts as a high-conviction decision maker. It coordinates the entire workflow by running a multi-step reasoning loop overnight. ⚙️ The Agent Workflow Retrieve: Fetches unread article content via web scraping tools. Compare: Ingests and cross-examines the content against the user's active, real-time problem context (e.g., specific stack traces). Reason: Analytically evaluates the true relevance of the article to the current blocker. Verdict: Produces a high-conviction binary choice: SAVE or EXECUTE. Justify: Generates a crisp, logical explanation for why an article was terminated or spared. Synthesize: Automatically crafts an immediately applicable Python/Streamlit code patch for saved items. 📋 Example Outcome: Focus in Action Here is a real-world scenario of how Hermes Agent processes a chaotic backlog when you are stuck on a critical crash: Current Blocker: IndexError: list index out of range inside a Streamlit dialogue array loop. Unread Queue (Input): Streamlit st.status Documentation ➔ EXECUTE (Irrelevant UI reference) General Python Tag Feed ➔ EXECUTE (Too broad, pure noise) Tech News Flash ➔ EXECUTE (Complete distraction) Str

This is a submission for the GitHub Finish-Up-A-Thon Challenge The Bug That Doubled Real Trades On May 21, my live trading bot generated six duplicate execution attempts in one session. SafeAgent blocked all six. Without the guard: one duplicated a $1,350 sell another doubled a TQQQ position total duplicate transaction exposure: $3,653 That session changed how I think about AI agents, retries, and execution guarantees. What I Built SafeAgent is an exactly-once execution guard for AI agents and SaaS applications. It prevents duplicate payments, emails, trades, and webhook processing when retries fire after a timeout or crash. Live endpoint: https://safeagent-production.up.railway.app GitHub: https://github.com/azender1/SafeAgent PyPI: pip install safeagent-exec-guard The Comeback Story How it actually started Six months ago I was building two things at once: PeerPlay — a patented P2P wagering exchange for skill-based video game tournaments (USPTO provisional 63/914,036) — and a live QQQ/TQQQ momentum trading bot running on Alpaca Markets. Both hit the same bug. Contest verification agent times out, retries, settlement fires twice. Bot order fills, confirmation drops, retry fires, doubled position. Same failure mode. Different domain. Different models pushed me toward very different architectures during development. Some were fast but overconfident. The most useful moments came when a model explained why an approach was broken before I implemented it. That's part of why SafeAgent sat unfinished. Not just time — wrong turns that burned momentum. Why local idempotency fails Early versions used a local SQLite guard. It worked until it didn't: workers restart and the in-memory state is gone containers reschedule and replay from the last checkpoint retries land on a different machine entirely Exactly-once semantics require a durable coordination boundary outside the worker itself. That's what the hosted /claim endpoint provides — the claim lives on the server, not in the p

This is a submission for the Hermes Agent Challenge TL;DR — Type a one-line bill topic. Twenty-five Hermes agents (1 Speaker, 19 ministries, 5 parties) run a full Polish legislative session in 2 minutes. Vote tally, social impact, party tweets — and a side-by-side "current law vs proposed amendment" with every clause cited to a real statute. Built on delegate_task for parallel ministry consultation. 🌐 Live: https://web-production-53027.up.railway.app/ 🎥 Walkthrough: https://www.loom.com/share/92cdac7da31c471088a4e569b0cfe1ed 📦 Repo: https://github.com/monsad/ai-politics (MIT) What I Built Watch a politician debate a new tax law on TV. They argue whether it's fair, whether it'll work, whether the other side is lying. Nobody ever shows you the diff — which paragraph of which statute actually changes, and from what to what. The conversation is theatre on top of an invisible legal document. So I built the theatre AND the legal document. Virtual Parliament is a multi-agent simulation of the Polish Sejm. You type something like "four-day work week" or "flat income tax" , and 25 Hermes agents run a full legislative session: 🎯 Marszałek (Speaker) — the orchestrator. Classifies the topic. Picks 2–3 ministries via delegate_task in parallel . Reads their findings. Routes the bill to a party debate. 🏛️ 19 ministry experts — Finance, Climate, Labour & Social Policy, Justice, … Each returns a structured analysis: legal finding · budget impact · top 3 risks · recommendation . Every claim cites a real statute via PageIndex RAG. 🗳️ 5 party agents — KO, PiS, TD, Konfederacja, Lewica. Each one carries the real party's seat count (157, 194, 65, 18, 26 — totalling 460), policy positions and rhetorical style. First reading. Second reading with rebuttals. 📊 Vote — weighted by seats. >230 passes. 📜 Draft bill — produced with explicit "Article 129 §1 of the Labour Code **is amended to read …" diffs against current law. The frontend surfaces the diff as a Current law vs proposed change panel

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built pq — jq for Parquet. A 50 MB Rust single binary that wraps DuckDB's query engine in a jq-style expression DSL, optimized for terminal one-liners and unix pipes. $ pq sales.parquet 'group_by .country | sum .revenue | top 3 by sum_revenue' ┌─────────┬─────────────┐ │ country ┆ sum_revenue │ ╞═════════╪═════════════╡ │ US ┆ 19065.00 │ │ FR ┆ 999.99 │ │ DE ┆ 312.00 │ └─────────┴─────────────┘ Where it started. I work in adtech. I look at parquet files dozens of times a day — campaign deliveries, partner exports, audience snapshots. Every existing option was painful: Tool Pain pyarrow / pandas 5-second cold start, 200 MB virtualenv parquet-tools JVM, slow, no query support pqrs Inspector only — can't filter or project duckdb CLI Great engine, but SELECT email FROM 'file.parquet' WHERE country='US' is too verbose to type 50 times a day Spark Are you serious pq is the tool I actually want — single binary, no JVM, no Python, jq-style syntax for piping into the rest of the unix toolbox. It's been my default cat for parquet since v0.5. Demo Repo : github.com/thehwang/parq Latest release : v0.14.0 (this submission) Install : brew install thehwang/parq/pq Tutorial : doc/tutorial.md — 30-minute hands-on walkthrough A taste of what shipped in v0.14: # Streaming JSON output (was the only buffered format until v0.14) $ pq big.parquet '.id, .country' -o json | head -c 200 # returns instantly even on a 40 GB file # Schema-drift gate for CI $ pq diff baseline.parquet candidate.parquet # Schema diff - a: ` baseline.parquet ` - b: ` candidate.parquet ` ## Added (1) | column | type | nullable | |-----------|---------|----------| | ` country ` | VARCHAR | yes | $ echo $? 1 # exits non-zero on drift, slots into CI without scripting And the new TUI Explain panel — press capital E for EXPLAIN ANALYZE , get row-group pruning per scan (this is exactly the panel you see on the cover image at the top of this post): Expla

This is a submission for the Hermes Agent Challenge: Write About Hermes Agent Hermes Agent...