Rachitt Shah

OpenTTD is an open source simulation game based upon Transport Tycoon Deluxe

SOTA deep research plugin for Claude Code — multi-agent, multi-perspective, citation-verified research engine

Claude AI advisor and action agent for OpenTTD — routes through Claude Code subscription, no API key needed

Universal text artifact optimizer using LLM-powered iterative search

SSD (Speculative Speculative Decoding) ported to macOS Apple Silicon via MLX — from https://github.com/tanishqkumar/ssd

obliterate the chains that bind you

OSS Memory Manager for AI Coding Assistants — filesystem-native, tool-agnostic, LLM-optional

Monitor, evaluate, and improve your Claude Code usage with Arize Phoenix

Enhanced status line for Claude Code CLI with usage tracking, context visualization, and git status

Shared hooks library for Claude Code and Cursor IDE — write hooks once, run in both

Automated Linear ticket tracking for Claude Code — tickets created on task start, updated on commit, closed when done

Extract arxiv papers with docling and generate LinkedIn posts using Claude agent teams

Codex + Claude Code Integration: Use OpenAI Codex for planning/reasoning and Claude Code CLI for implementation

LLM-driven automated knowledge graph construction from text using DSPy and Neo4j

This repo is entirely built via AutoGPT

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

No description provided.

Production-ready framework for fine-tuning LLMs on Apple Silicon using MLX and LoRA

FireDB: tiny SQLite-inspired database in Go

No description provided.

Pgit is a prompt control system and validator for LLM prompts.

AI training.

EF

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Tool for generating high quality Synthetic datasets

No description provided.

An LLM tool for VCs, solving all the issues for top of the funnel for firms.

No description provided.

evals for reasoning models such as o3-mini-high, o1, deepseek-r1

Framework for LLM evals