Top Picks

A GitHub-hosted technical guide for running a multi-tier agent system on Termux, with SQLite used for messaging, scheduling, and audit logs, plus thermal-aware admission control for Android devices.

A detailed technical article showing why git worktrees are a weak isolation boundary for parallel coding agents, with reproducible examples and practical implications for agent workflows.

A primer for non-coders to design and implement software through structured dialogue with an AI. It explains the CGP method, its goals, how it differs from orchestrator/worker patterns, and how to use the matching primer version.

A web-based multi-model comparison of procedural medieval castle worlds made with three.js. It showcases the same castle brief across eight models and three art directions, with static gallery previews and full-page worlds you can open.

A step-by-step guide for turning a spare Mac into an always-on machine Claude Code can control over SSH or from the Claude app.

VAIBot is an AI governance product focused on agent security. This page explains its prompt-injection threat model and positions the product as a circuit breaker that gates tool calls and other egress actions before they execute.

Clusy is an agent-native notebook platform for ML and data science work in the cloud. The page says it can source data, inspect it, choose architecture and compute, and run end-to-end workflows, with a demo showing a finetuning task and follow-up work queued while the notebook runs.

Katra is an open-source, self-hosted cognitive memory system for AI agents with MCP support. The repo describes episodic recall, semantic search, knowledge graphs, temporal analysis, and Docker-based deployment for MCP-compatible agents.

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.