Ai Research Python Packages

scitex

Umbrella package for SciTeX — reproducible science from raw data to manuscript

research-hub-pipeline

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

scitex-dataset

Multi-domain scientific dataset fetcher (neuroscience, biology, medical)

rlm-code

The Research Playground for the RLMSs and Coding Agents

autocrucible

Autonomous experiment platform — let LLM agents optimize anything through iterative edit-evaluate loops

hn-tech-signal-mcp

MCP server for global tech & AI signal intelligence via HackerNews, arXiv, Lobste.rs and GitHub

inflion

Observability and influence tracing infrastructure for multi-agent AI systems.

notebooklm-skill

NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.

llm-tokens-atlas

Open benchmark of LLM tokenization calibration across providers.

swarms-cloud

Swarms Cloud - Pytorch

nouse

A persistent epistemic substrate for AI. Nous treats language models as larynx, not mind, and benchmarks epistemic structure instead of output fluency.

traceiq

Observability and influence tracing infrastructure for multi-agent AI systems.

halftrace

Diagnose how your agent's compliance with rules varies across trajectory length.

autoevolve

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

cogitator

A Python toolkit for chain-of-thought prompting

autojudge

Smarter experiment evaluation for autoresearch — replaces eyeballing val_bpb with statistical verdicts

autosteer

Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

zotero-keeper

AI-powered research toolkit integrating PubMed search, Zotero management, and VS Code extension with OpenURL institutional access

cortex-research-suite

AI Research Operating System — skill testing, synthetic data, evaluation, multi-agent orchestration

vortex-fusion

Transformers + Mambas + LSTMS All in One Model

iris-gate

Multi-architecture AI convergence system with epistemic humility for scientific discovery

theorist

Prediction-error optimization. The agent guesses before each experiment. Wrong predictions are the learning signal. One file, zero dependencies. pip install theorist