An Agent-First desktop IDE (macOS / Windows, just 7MB) for managing multiple Claude Code and Codex agents running in parallel across different projects. Built-in terminal, session replay, AI-generated commit messages, and weekly token usage analytics. 445 stars, v0.3.0, GPL-3.0.

The highest-starred meta-skill in the Claude Code ecosystem (17.2k Stars). Automatically distills public figures' cognitive frameworks into executable Skills via 6 parallel research agents and Triple-Verification filtering. MIT licensed, free to use.

A Rust-based microservices platform aiming to replicate Palantir Foundry's core capabilities as open-source. Covers ontology modeling, data pipeline versioning, AI agent integration, and workflow automation. Architecture documentation is exceptional, but the project remains in very early development (12 Stars, no release).

An open-source recursive LLM-powered investigation agent that performs entity resolution across heterogeneous datasets (corporate filings, campaign finance, government contracts) and renders knowledge graphs in real-time via Cytoscape.js. Built with Tauri 2, MIT licensed, positioned as Palantir's community edition. 1,600 Stars in two months.

A single system prompt file that forces any LLM to respond directly and without filler. Bans all opener phrases and the 'not X, but Y' sentence pattern. Tested to reduce word count by 72–73% while retaining all substantive information. 1,375 stars in 13 days, MIT licensed, includes a Claude Code skill version.