Top Picks

Colyap is an AI phone friend you can call or text. The page shows voice-call and SMS access, memory, reminders, and task help like booking dinner, researching flights, and sending follow-up texts.

Open-source codebase for building, deploying, and scaling AI agents across L1–L5 levels. The README shows a quick start, SDK installation, local dev setup, and a developer UI for running agents.

A Noma Security research post detailing a prompt-injection flaw in GitHub Agentic Workflows, with attack flow, proof-of-concept evidence, and security recommendations.

Browser-local tool for removing supported visible Gemini watermarks from single images or batches, with before/after review and ZIP export.

Android app for chatting with PDFs and Word documents entirely on-device, with an offline/private positioning and no cloud dependency.

A vLLM blog post explaining Semantic Router as an open serving-layer runtime for bounded micro-agents, with routing patterns like Confidence, Ratings, ReMoM, Fusion, and Workflows behind a single model API.

AirPosture is an open-source iOS app that turns AirPods sensor data into a real-time posture coach, with features like background tracking, posture streaks, activity switching, stretching prompts, and Live Activity syncing.

Michii is an AI product team for online businesses that claims to plan, build, launch, market, support customers, and fix issues for founders who do not want to hire a tech team.

Saymade is an AI app builder that turns a plain-language idea into a working app, lets you refine it with feedback, and deploy it with one click.

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.

Gravity AI is a Go-based multi-agent consensus harness that coordinates AI agents through Raft-backed task state, proposal voting, and reputation updates.

A detailed technical article describing PTCRunner’s approach to building a Clojure-like language, runtime, and preludes designed for LLM agents, with emphasis on security, feedback, introspection, and scaling.

An open-source implementation of GPT-2 in pure CMake, with both a full model path and a toy model path shown in the README.