Your prompts need tests too. Run prompts against real datasets, score outputs with LLM judges, version everything, and compare runs to see what got better.
Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.
Local Go daemon that gives AI tools persistent shared workspace state. Context assembly, multi-provider inference routing, hash-chained ledger, MCP server.
TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.
MCP server + CLI giving AI agents 50 spreadsheet tools for .xlsx — live-recalc formulas (~390 Excel functions), repair broken references & external links, read/write, diff, and audit. Works in Claude Code, Cursor, Codex, and any MCP client.
High-performance financial charting library with Canvas/WebGL hybrid rendering, delivering crisp multi-DPR visuals at 1-3ms GPU time per frame. Features plugin-based rendering and visual signal annotation. Exposes JSON semantic configuration for Agent-driven quantitative visualization. Works seamlessly across React, Vue, and Angular (soon).
MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.
Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.
Laravel-native client for Model Context Protocol (MCP) servers. Built by Redberry (Diamond-tier Laravel partner). Used by LarAgent and other frameworks to enable AI agent functionality.
Universal control system for coding agents: shared memory, cross-project handoffs, research management, & MCP + Obsidian dashboards across products/repos.