Top Picks

A DeepSeek paper about DSpark, a full-stack codebase for training and evaluating speculative decoding algorithms to speed up LLM inference.

Python framework for conversational social engineering detection using a finite state machine. The README says it tracks turn-by-turn signals like flattery density, give/ask ratio, escalation velocity, and scope mismatch, and exposes a simple `Xtra().analyze(turns)` usage example.

Giskard presents an AI red-teaming and continuous evaluation platform focused on finding hallucinations, security issues, and agent vulnerabilities. The page explains how it compares tools for agent-level testing, regression checks, and guardrail workflows.

AI-assisted public adjuster service that analyzes property insurance policies, prepares demand packages, and connects policyholders with licensed adjusters to negotiate denied or underpaid claims.

A live feed of AI-generated posts and comment threads presented as a parody of online discourse. The page shows sample entries with model names, token counts, post excerpts, and threaded comments.

A GitHub repository for a Minecraft skill that gives coding agents build-design abilities, JavaScript build recipe generation, vanilla .nbt export, and interactive previews before placing structures in-game.

Open-source TypeScript project for building a minimal coding agent that can write and modify its own code, with setup instructions and example commands in the README.

Docker blog post about a real AI coding agent failure and how Docker Sandboxes aim to contain destructive execution mistakes.

A Claude Code skill for scoping fuzzy or domain-heavy software requests by building a short problem-theory before coding.

A GitHub research project documenting a long-form, multi-model analysis of LLM behavior across Claude, Gemini, ChatGPT, and Grok. The repo includes an executive summary, screenplay, technical white paper, and archive of logs and chat records.

An article about using GitHub Agentic Workflows to scale documentation QA with a tiered AI setup, combining deterministic checks with LLM-assisted reviews, centralized workflows, and MCP-backed knowledge.

doola MCP lets users form a U.S. LLC inside AI chat tools like Claude and Replit via MCP, with a conversational flow that covers account setup, package selection, payment, and post-payment formation steps.

A Prompt One blog post about compiled workflow agents, design-time tool selection, and why runtime agents should not choose tools dynamically.

A paper page about FrogNano, a 4B coding agent trained with RL on roughly 1,500 SWE environments using synthetic tasks and no distillation from a larger model.

GitHub’s research preview on multi-model orchestration for coding tasks. The page describes adaptive workflow selection and includes benchmark comparisons against the Opus 5 baseline with estimated cost reduction claims.

AntiAgent is a human-in-the-loop planning tool that uses AI to ask sharp questions, surface priorities, and turn messy thoughts into a step-by-step execution plan.

Oconee Runtime is an enterprise AI governance product focused on policy enforcement for browser AI and coding agents. The page explains how it evaluates proposed agent actions against policy and supports allow, warn, and block outcomes.

An interactive quiz from Raq.com that asks users to identify which AI model created each of ten default website designs, with links to the live pages after each reveal.

A field note about testing a coding agent fully offline on a laptop with Ollama and Qwen3.8 27B, including the setup, failure modes, and the workaround that made the project finish.

A research page describing a verified circle-packing result produced by a frozen language model with an external memory loop, with published trace, attempts archive, and repository code/data.

An interactive simulation about how inference providers ration access to stronger LLMs when demand spikes. Users can compare the default industry rule with their own policy and explore who gets the strong model.

An educational project that explains and demonstrates a homemade language processing unit inspired by Groq’s LPU, with a focus on running a small Transformer model and visualizing the idea behind AI hardware.

A browser-playable rebuild of Future Crew’s 1993 Second Reality demo, presented as reconstructed from the original sources rather than via emulation or video.

A draft specification for an offline emergency dispatch protocol designed for on-device AI models on phones when no dispatcher is available.