Complete toolkit for developers building LLM applications.

A toolbox with the goal of speeding up research on bargaining in MARL (cooperation problems in MARL).

A python sdk for LLM finetuning and inference on runpod infrastructure

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

[deprecated] AI Gateway - core infrastructure stack for building production-ready AI Applications

Inspect: A framework for large language model evaluations

A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Persistent, stale-free, local and cross-machine caching for Python functions.

Repo for the paper on Escalation Risks of AI systems

Experiments with representation engineering

Implementation of Google's SELF-DISCOVER

Representation Engineering: A Top-Down Approach to AI Transparency

(Model-written) LLM evals library

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

A curated list of awesome resources for Artificial Intelligence Alignment research

Awesome papers involving LLMs in Social Science.

Zotero plugin for auto-fetching citation counts from various sources

Algorithms for explaining machine learning models