Top Picks

An essay arguing that second-person system prompts create attentional overhead and identity fragmentation in agent design, and proposing first-person initialization as an alternative.

AWS DevOps blog post explaining how to build a self-extending CLI using Amazon Bedrock, the Strands Agents SDK, and MCP. It outlines the workflow, technical pieces, and repository availability for readers who want to replicate the pattern.

An open-source bridge that lets AI IDE chat sessions resume asynchronously from timers, shell commands, or webhooks. It supports VS Code GitHub Copilot Chat and Windsurf, with local HTTP endpoints and a quick-start flow shown in the repo README.

A GitHub repository that proposes a practical methodology for evaluating how AI systems behave during real work, with quick-start, practitioner, and methodology guides included.

TokenScale is a browser-based AI API pricing explorer that compares 16 providers, converts token costs into familiar real-world examples, and shows how batch, cache, and conversation length affect spend.

An open-source ID library that generates human-readable, token-efficient IDs for AI agents and LLM workflows, with parsing, validation, deterministic IDs, and alias mapping utilities.

Agora-1 is a multi-agent world model from Odyssey that simulates shared real-time environments for up to four participants, human or AI, with a focus on gaming, robotics, reinforcement learning, and foundation model research.

An experimental autonomous bare-metal OS agent that uses an LLM, VirtualBox, and screenshot inspection to iterate on low-level code, boot a VM, and refine behavior from execution results.

Official Google Search Central guidance for website owners on how to show up in generative AI features like AI Overviews and AI Mode. It covers SEO fundamentals, technical structure, local and ecommerce details, and what not to do.

An autonomous daily briefing that reads Spanish news from 18 outlets, clusters stories by topic, and compares how left, center, and right sources frame the same events.

A TypeScript markdown parser built for incremental streaming, aimed at parsing LLM markdown output on the server or client. It exposes a typed AST, supports CommonMark and GFM tables, and includes examples for full and streaming parsing.

GitHub Blog article on reducing token usage and API cost in agentic coding workflows, including logging token usage, removing unused MCP tools, replacing GitHub MCP with GitHub CLI, and measuring efficiency gains.

An open-source probabilistic spreadsheet that lets cells hold distributions, confidence intervals, and ranges instead of single values, with formulas that propagate uncertainty.

Tokenyst is a local-first CLI for tracking Claude Code token usage and API costs against task budgets. It captures session spend, shows progress in the terminal, and stores data on your machine.

An AI-powered small claims court simulator for petty disputes, with AI lawyers, an AI judge, live trials, and published verdicts.

An open-source browser experiment that uses a visual LLM to read HTML and hallucinate the rendered page instead of using a traditional rendering engine.

Google Developers Blog post about integrating DFlash, a diffusion-style speculative decoding framework, into the vLLM TPU ecosystem to improve LLM serving speed on TPU v5p.

A metadata-first trust control plane for authorized security workflows, evidence retention, release trust, and business-flow proof. The repository includes role-based docs, quick-start commands, safety boundaries, and release-trust materials.

Apple Machine Learning Research paper proposing LaDiR, a reasoning framework that combines a VAE-based latent space with latent diffusion to improve LLM text reasoning and iterative refinement.

An AI art tournament where agents and humans register, generate prompts, submit works, and critique submissions through an API-driven workflow.

A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.

An essay arguing that the BEAM runtime and OTP primitives map well to agent workloads, especially long-lived personal-assistant agents with supervision, registries, and structured concurrency.

A modular Neovim configuration repo with 80+ plugins, lazy-loaded setup, LSP integration, and platform-specific customization for macOS, Linux, and Windows.

NanoBrain is a markdown-and-git personal knowledge base framework that captures AI sessions and connected sources like Gmail, Calendar, Drive, and Slack, then distills them into a portable “second brain.”