🤖 AI Agents - saeedesmaili · Scour

nauta-ai/holster-scan: Local-first scanner for AI-hallucinated / typosquatted (slopsquat) packages + agent boundary preflight — catches what generic SAST misses, before an agent runs or a repo is shared.

🧠LLMs Code

github.com··Hacker News

How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope

🤖Automation Academic

Tejas-TA/predikit: The missing bridge between your ML models and your AI agents.

🤖Data science Code

github.com··Hacker News

MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning

💬Natural Language Processing Academic

Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents

🧠Transformers Academic

itsthestranger/strangeClaw: strangeClaw is a minimal, self-hosted autonomous AI agent with full Firecracker sandbox isolation support.

🏠Self-hosting Code

github.com··Hacker News

Entropy-Based Evaluation of AI Agents: A Lightweight Framework for Measuring Behavioral Patterns

🧠LLMs Academic

Benchmarking Large Language Models for Safety Data Extraction

🪟Context Windows Academic

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

🧠LLMs Code

github.com··Hacker News, Hacker News

Tight Sample Complexity of Transformers

🧠Transformers Academic

N8n-style tool chains for AI agents – custom design, or reinforced by what works

🧠LLMs Code

github.com··Hacker News

acunningham-ship-it/veilbrowser: Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.

🧠LLMs Code

github.com··Hacker News

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

🎮Reinforcement Learning Academic

RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

🎮Reinforcement Learning Academic

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

🧠LLMs Academic

Moai-Team-LLC/agentic-product-standard: The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 7-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

🧠LLMs Code

github.com··DEV, Hacker News

Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries

🔥PyTorch Academic

MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action

🧠LLM Inference Academic

3SPO: State-Score-Supervised Policy Optimization for LLM Agents

🎮Reinforcement Learning Academic

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

🎯Fine-tuning Academic

Log in to enable infinite scrolling