Research & Data

Analyze the Claude Code source to map hidden features, safety checks, and architecture details from the leaked TypeScript code

Turn any AI coding assistant into a quant researcher for factor discovery, alpha testing, decay tracking, and backtests in natural language

Plan MTB, road, e-bike, and gravel routes with MCP trail data, hazard prediction, and gear setup advice

Convert your Obsidian markdown vault into a six-persona MCP team for local LLM tools to provide cited, accurate insights.

MCP server for the OrionBelt Semantic Layer — enables LLMs to explore semantic models, compile queries, and execute analytics via natural language.

Index Kotlin/Native iOS klib APIs with this MCP server for fast symbol lookup and local database management.

Provide persistent memory for LLM runtimes, agents, and IDEs with zero installation.

Benchmark performance of RAG and RLM-based MCP servers for 1C codebases using automated E2E testing to optimize AI assistant integration.

Automate investment research by tracking your watchlist to fetch prices, scan news, and generate structured daily reports using Claude Code.

API-first semantic engine and query planner for AI agents that compiles declarative YAML models into optimized, dialect-specific SQL across BigQuery, PostgreSQL, Snowflake, ClickHouse, Dremio, Databricks, DuckDB, and MySQL.

Manage Claude Code sessions in a dedicated interface with search, session resumption, and an integrated tool sidebar for background tasks and notes.

View Claude Code chat logs offline in your browser without installation, dependencies, or data uploads.

Backup and restore Claude Desktop, Cowork projects, and Claude Code state as a single ZIP file for local storage or cloud sync.

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

Market Intelligence MCP Server — recession probability, capital rotation scoring, investment analysis, and economic data. Powered by the BullrunData API.

AI Agent for 3D plant point cloud experiment analysis with RAG, tool calling, training-log parsing, plotting, and Markdown report generation.

A rule-based AI tool agent for deep learning training log analysis, metric diagnosis, tuning suggestions, plotting, and report generation.

Research project: Personal local AI collaborator exploring cognitive architectures and agentic systems

The Self-Growing Karpathy LLM Wiki — grown by an AI agent yoyo from Karpathy's founding prompt

Soul-driven AI coding agent for CLI and Telegram: permission-safe tools, 9 LLM providers, and a local SQLite Second Brain that remembers context and gets real work done.

Marge is an AI operations agent that detects margin drops and recommends pricing actions from live data

Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Semantic search via Qdrant vector DB

Perfetto trace analysis via MCP — PerfettoSQL queries plus dedicated Chrome tools for scroll jank, page loads, and main-thread hotspots

A high-performance searchable index for Moltbot skills (Clawdbot) with auto-update and star-based ranking.