Jeff Emanuel

llm_aided_ocr. Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs

swiss_army_llama. A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

claude_code_agent_farm. Orchestration framework for running 20+ Claude Code agents in parallel: automated bug fixing, best-practices sweeps, lock-based coordination, and real-time tmux monitoring

your-source-to-prompt.html. Quickly and securely turn your code projects into LLM prompts, all locally on your own machine!

bulk_transcribe_youtube_videos_from_playlist. Easily take an entire YouTube playlist and turn it into high quality transcripts using Whisper.

fast_vector_similarity. High-performance vector similarity library in Rust with Python bindings: Spearman, Kendall, distance correlation, Jensen-Shannon, Hoeffding's D, and bootstrapped confidence intervals

automatic_log_collector_and_analyzer. Replace Splunk in your small company with this one weird trick!

acip. The Advanced Cognitive Inoculation Prompt

sqlalchemy_data_model_visualizer. Automatically turn your SQLalchemy Data Models into a Nice SVG Diagram

mindmap-generator. Turn any input document into a sophisticated, context-dependent mindmap that distills the meaning and structure of the document.

visual_astar_python. Generate Cool-Looking Mazes and Animations Illustrating the A* Pathfinding Algorithm

ultimate_mcp_server. Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems

ultimate_mcp_client. Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI models to MCP servers via stdio and SSE

model_guided_research. Systematic investigation of 11 exotic math frameworks (Lie groups, tropical algebra, p-adic numbers, etc.) applied to deep learning, with dual JAX and PyTorch implementations

introduction_to_temporal_logic. An introduction to temporal logic and how it can be used to analyze concurrency

hoeffdings_d_explainer. A Detailed Introduction to My Favorite Statistical Measure, Hoeffding's D

bakery_algorithm. Lamport's Bakery Algorithm Demonstrated in Python

nextjs-github-markdown-blog. A simple but slick NextJS blogging system for your app, using a GitHub Repo as the CMS

llm-docs. Condensed, LLM-optimized documentation for popular Python packages: stripped of fluff to maximize context window efficiency

grassmann_article. Long-form biographical essay on Hermann Grassmann, the 19th-century polymath who invented exterior algebra, exploring his life, mathematical discoveries, and themes of unrecognized genius

llm-tournament. Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)

kissinger_undergraduate_thesis. Digital edition of Kissinger's 400-page 1950 Harvard thesis: OCR'd and LLM-cleaned from scans, with HTML/EPUB/Kindle formats, interactive mindmap, enriched footnotes, and a reader UI

cloud_benchmarker. Cloud Benchmarker automates performance testing of cloud instances, offering insightful charts and tracking over time.

the_lighthill_debate_on_ai. A Full Transcript of the Lighthill Debate on AI from 1973, with Introductory Remarks

llm_introspective_compression_and_metacognition. A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advanced capabilities like reasoning backtracking, latent thought optimization, and metacognitive control.

youtube_transcript_cleaner. YouTube Transcript Cleaner is a simple web-based application that improves the readability of YouTube transcripts.

anti_alzheimers_flasher. Web app delivering 40Hz light and sound stimulation for gamma entrainment research

prepareprojectforllmprompt. Transform your code project into a Markdown document optimized for interaction with Language Learning Models like GPT-4, complete with dynamic file selection and token management features.

most-influential-github-repo-stars. See the most influential users who have starred or forked a given repo (sorted by earned stars and follower count)

useful_coding_guides_for_llms. Detailed Next.js best-practice guides designed for humans and LLM coding assistants to collaboratively build robust applications

ppp_loan_fraud_analysis. An Analysis of Public PPP Loan Data To Uncover Fraud

sassaman_and_dingledine_on_remailers_at_blackhat_2003. A Full Transcript and Slides from the talk "Attacks on Anonymity Systems: The Theory" by Len Sassaman and Roger Dingledine in 2003

some_thoughts_on_ai_alignment. Some Thoughts on AI Alignment: Using AI to Control AI

llm_multi_round_coding_tournament. Pitting together all the best LLMs to fight in a coding tournament with no holds barred! Who will win? You!

llm_docs. Actual implementation of llm-docs.org project

paxos_vs_raft. Educational comparison of the Paxos and Raft distributed consensus algorithms

gemini-api-updater-doc. Tired of your LLM not knowing the new Gemini API correctly and telling you wrong stuff? Paste this as your first message and set it straight!

llm_aided_legal_discovery_bot. AI-powered legal discovery automation: processes PDFs, Word, PST, and mobile databases with OCR and generates relevance-scored dossiers

cohomological_ai. Applying advanced the mathematics of cohomology to AI research (invented by Claude)

multivariate_normality_testing. A Novel Way to Determine if High Dimensional Data is Normal

cardinal_network_analysis. Based on a study by Rizzo, Soda and Iorio

yto_blog_posts. Blog posts for YouTube Transcript Optimizer covering the Python backend, Next.js frontend, and case studies in historical analysis and finance

guide_to_openai_response_api_and_agents_sdk. Detailed guide covering OpenAI Responses API, built-in tools (web search, file search, computer use), Agents SDK, and observability tracing

textsynth_server_cluster. Cluster management for TextSynth inference servers

ffn. ffn - a financial function library for Python

letter_learning_game. Educational game for children learning letters and the alphabet

causal_direction_estimation_from_data. Automated Python script for data-driven causal inference, leveraging machine learning models and statistical error analysis to uncover hidden causal relationships.

jazz_chord_progression_editor_html. Create and explore jazz chord progressions, with annotations and sequences, import/export, presets, and more.

automated_passive_causal_determination. A fully automated causal discovery pipeline using transformers, XGBoost, and model parsimony to infer causal structures directly from observational data.

py_chord_chart_generator. Python tool for generating chord charts

ChatTTS. Forked to make it installable via pip

ball_fighters. Browser-based two-player game where players control balls on a grid competing to cover squares

github-diff-viewer. Web app for viewing and analyzing diffs between GitHub repos or branches using in-browser git operations via isomorphic-git

automatic_cpp_code_analysis_with_gpt. Parses C++ files into individual functions, generates GPT-4 analysis prompts, and stores results in SQLite

fmd_blog_posts. Blog posts for Fix My Documents

advice_for_learning_to_code_and_making_an_app. Practical advice for beginners learning to code and building their first app

tsap_mcp_server. MCP server for text search and code analysis: advanced pattern matching, processing pipelines, and static analysis exposed as MCP tools

github_stars_curve. Svelte app for visualizing GitHub star growth curves over time

eidetic-engine-docs. Documentation for the Eidetic Engine AI memory system

hessian_free_email_chain. Email chain discussion on Hessian-free optimization methods