Top Picks

An open-source multi-agent coding framework that uses a commit-bound project graph to scope worker tasks, replay failed runs, and merge accepted diffs through ordered Git reconciliation.

A research preprint describing ADHD, a parallel divergent ideation method for LLM coding agents that isolates branches, uses cognitive frames, and then prunes with a separate critic pass.

A bilingual satirical idle simulation where you run an AI startup from toy classifiers to near-AGI, managing data, compute, launches, crises, and rivals.

A Claude Code plugin that plays background lounge or elevator music while the agent is thinking, with track rotation, stop/start controls, and status-line integration.

A blog post from Augment Code comparing its coding agent, Auggie, against Claude Code on Opus 4.7. It presents benchmark results, token usage, cost comparisons, and an explanation of the Context Engine and Prism router.

A drop-in memory plugin for Hermes Agent that uses a pull-model episodic memory approach with real deletes and audit traces. It supports synchronous writes, trace logging, and Claude-backed summarization for on-demand recall.

A public visualization that tracks flagship AI models’ Elo history over time using the Arena AI Leaderboard dataset, with notes on caveats and methodology.

A macOS menu bar app that keeps a MacBook awake with the lid closed while the display sleeps normally, so long-running coding agents can continue running.

A guide for exporting ChatGPT, Claude, and Gemini history into XTrace MemHub, then downloading Markdown for an Obsidian-style wiki and graph view. It explains the export flow, supported platforms, and the Markdown ZIP output.

A GitHub repo for evaluating agentic AI pipeline systems, with guidance for defining metrics, building eval cases, running repeatable tests, and tracking regressions.

An AI tools directory with hand-reviewed comparisons, popular tool rankings, and a set of free developer utilities plus SEO tools.

A notes app for Mac, iPhone, and iPad that syncs through iCloud and mirrors notes to local Markdown files for editing, backup, and workflow integration.

A VS Code extension that turns code editor cursors into a real-time music visualizer using microphone or system audio input.

An open-source simulator that studies how GPT inference behaves under space radiation and cosmic-ray fault conditions, with CLI runs, comparisons, and self-contained HTML reports.

AI agent that transpiles Python projects into native C binaries, with support for static builds, web app conversion, and automatic verification steps like compilation retries and valgrind checks.

A Steel blog post that dissects Claude Code’s deep-research workflow and contrasts it with other research systems. It also positions Steel as an open-source browser API for AI agents, making the page relevant for AI builders.

A MotherDuck blog interview with Wes McKinney on practical AI coding workflows, including spec-driven development, continuous AI code review, and how to keep agent-generated code maintainable.

AI-powered PDF to Markdown converter focused on preserving structure like headings, tables, images, and reading order for research, docs, and knowledge workflows.

Pure Effect is a small JavaScript library for building testable business logic as data-driven commands instead of relying on mocks. It includes primitives like Success, Failure, Command, Ask, Retry, and Parallel, plus helpers like effectPipe and runEffect for composing and executing flows.

Naiou is an OpenTUI terminal app and yes/no oracle that answers every query with a definitive Yes or No. It includes install steps, build instructions, platform support, and OpenAI-compatible API key requirements.

Agenvoy is a Go-native multi-model AI agent framework that routes tasks to the best model, shares a common daemon and session across interfaces, and can generate scripts or APIs to extend its toolset.

Research paper introducing hyperagents, a self-referential agent framework that combines a task agent and a meta agent into one editable program. The abstract describes a DGM-based system that improves both task performance and its own improvement process across domains.

Browser-based tool for cleaning NotebookLM PDF exports before sharing, with preview, region selection, and download of a repaired file.

A research repository and local web app for testing quantum gravity theory-space exclusions against encoded consistency constraints. It includes a CLI, a localhost interface, test coverage, and an LLM-powered research agent for running searches and report generation.