August-murr/Interregnum
A public notebook. Working drafts, half-formed ideas, and thoughts I'm too much of a perfectionist to just post.
Repositories
August-murr/Ouroboros
Ouroboros is a self-referential AI experimentation framework where an agent evolves the very codebase that defines its own behavior.
August-murr/APART
The repo for my submission for APARTs Secret Loyalties Hackathon
August-murr/Bluedot
The repo for all files and reports for the Bluedot Impact AI safety project
August-murr/August-murr
August-murr/sandboxed-ml-agent
Code and data for "Sandboxed AI Agents with GPU Access" blog post. An OpenHands agent with GPU access that completes ML tasks. Part of the Ouroboros research project.
August-murr/verl
verl: Volcano Engine Reinforcement Learning for LLMs
August-murr/OpenHands-CLI
Lightweight OpenHands CLI in a binary executable
August-murr/TRLReport
August-murr/auto-labeler
August-murr/Resource_Aware_Agentic_RL
train agents to maximize productivity per dollar, learning to optimize tool-use, exploration,and verification under strict budgets.
August-murr/verl_vllm_image
August-murr/trl
Train transformer language models with reinforcement learning.
August-murr/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
August-murr/smolagents
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
August-murr/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
August-murr/rllm
Democratizing Reinforcement Learning for LLMs
August-murr/leetgpu-challenges
LeetGPU Challenges
August-murr/vastai_configs
August-murr/Harmlessness_Self_Evaluator
August-murr/basic_data_science
August-murr/ScalableGen
August-murr/Lab
My AI Lab
August-murr/open-r1
Fully open reproduction of DeepSeek-R1
August-murr/search-and-learn
scale inference-time compute of open models