Top Picks

A reference implementation for intent-execution separation in LLM agents. The project uses a typed intent layer (SIF) over domain vocabularies, with a deterministic execution layer and demo domains for legal and veterinary workflows.

A GitHub repository of agent skills for reviewing conversational AI product UX from a codebase, including discovery, review, and recommendation workflows.

taste-ai is a command-line tool that compresses project context for AI agents and learns coding patterns from session logs, git history, and prompts. The README shows install steps, a quick start, command examples, and a workflow for generating compact session context and updating pattern files.

Ferrix AI is an agentic product management platform that pulls in customer feedback, usage data, revenue signals, and market research, then recommends what to build next and generates specs, tickets, release plans, and stakeholder communications after approval.

AI Home Architect is a browser-based AI design generator for interiors, exteriors, floor plans, and elevations, with a Vastu floor planner and instant image downloads.

A detailed walkthrough for running a local coding agent on macOS with llama.cpp, Gemma 4, MTP speculative decoding, image support, and Pi as the agent interface.

Nodea is a live branching AI chat canvas for working through complex projects. The demo shows forkable replies that turn conversations into trees, with example prompts for naming a coffee shop and shaping branding ideas.

A font project and keyboard firmware concept that turns typed text into a noise-like character stream while rendering readable output only through the font itself.

A CLI tool that keeps Claude Code, Codex, and GLM 5-hour rate-limit windows continuous by auto-pinging providers when a window resets.

Aquifer is a self-hosted MCP gateway runtime for buffering spiky agent and API traffic. It queues requests durably in SQLite, dispatches them at a configurable rate, and supports both MCP and HTTP adapters with webhook delivery.

AI sales agent for cold outreach that finds prospects, personalizes messages, and follows up across email, text, LinkedIn, and X until someone replies.

Public GitHub repository describing how to access a large Powerset Research GitHub dataset through an MCP server or DuckDB. Includes no-auth access, schema-aware SQL use, and example queries for agents and analysts.

kLex is the reference runtime for FROG, a typed language built for native tooling, browser apps, pipelines, and concurrent utilities. The repo shows install steps, language examples, a browser playground, GUI support, and a security-scanner demo.

StackNudge is an open-source notification tool for AI coding agents. It adds banners and sounds when supported agents finish a task or pause for approval, with macOS support for a native panel and click-to-focus behavior.

A Python-based coordination protocol and daemon for running multiple LLM sessions in parallel with shared awareness, aimed at Claude Code and other Anthropic-compatible models.

A bootable Linux-based OS prototype with a React desktop, Rust daemons, Electron shell, and a local AI assistant. The page describes the boot flow, architecture layers, built-in apps, persistence, and hardware boot timing.

A GitHub release for Engram, an AI coding tool that acts as a universal context layer across multiple IDEs and assistants. The v3.4.0 release highlights support for Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, and Zed, plus npm, OpenVSX, and Anthropic plugin distribution.

A local AI coding harness that turns business-rule specs into a constrained JSON AST, validates it, and compiles it into Clojure code while logging generation and repair artifacts.

CtxVault is an open-source receipt layer for governed AI context. It shows what evidence was selected, caveated, blocked, omitted, and how a context packet can be audited or rolled back.

Rauno is a multi-AI chat interface that sends one prompt to ChatGPT, Gemini, and Claude and presents them as a roundtable discussion. It’s aimed at comparing model responses and using cross-verification to help users judge which answer is right.

Community edition of Merlin, a local-first deduplication tool for LLM context and RAG pipelines. The repo includes quick-start install steps, MCP and editor integrations, savings claims, and rollback guidance.

A Chrome extension that uses AI to score YouTube videos against your interests and fade irrelevant content. It also adds Focus Mode controls to hide Shorts, autoplay, comments, recommendations, and other attention-heavy parts of YouTube.

A GitHub repository of system-prompt overrides for Claude Code, aimed at shrinking the always-on prompt and adjusting behavior for Opus 4.7. It includes a detailed rationale, measured prompt-size reductions, and install steps using tweakcc-fixed.

A printable quick-reference page for Codex CLI, covering commands, flags, TUI shortcuts, approvals, config, models, MCP, skills, and subagents.