"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)
Streamlit IndexError Bug Fix Guide ➔ SAVE (The Hidden Gem)
📊 The Dawn Execution Report
Noise Kill Rate: 75%
Generated Justification (for Saved Item): "Critical match: This guide outlines exactly why state sync delays cause index mismatches in Streamlit arrays."
Generated Actionable Patch (Output):
Python
Hermes Agent generated patch to kill the blocker immediately:
safe_idx = min(
st.session_state.current_index,
len(st.session_state.dialogue_list) - 1
)
current_dialogue = st.session_state.dialogue_list[safe_idx]
🛠️ Technical Implementation & The Sandbox Fallback
Frontend: Streamlit (Features a high-contrast agent dashboard and real-time reasoning visualization via st.status)
LLM Core: gemma4:e4b running locally via Ollama.
Key Metric: "Noise Kill Rate"—A prominent dashboard metric showing the exact percentage of data the agent successfully terminated, instantly communicating the saved cognitive load.
💡 Note for Judges (Demo Reliability)
To ensure a deterministic and reliable demo experience during judging, the current prototype includes fallback context boundaries for selected URLs within the scraping tool. This architecture is designed to transition directly into a dynamic vector-embedding pipeline (RAG) mapped against the agent’s core prompt structures.
🚀 The Core Philosophy
Most AI systems help people consume more information. Tsundoku Slayer focuses on a different question: "What information deserves your attention right now?"
Instead of generating another tedious report, Hermes Agent acts as an intelligent decision-making layer. It protects developer focus by filtering, prioritizing, and surfacing only immediately actionable knowledge.