tokenbender

agent-guides. one page guides that i let my subscribed/customised agents consume to perform actions

avataRL. rl from zero pretrain, can it be done? yes.

infinite. a rubric driven prioritized replay rl algo to maximise continual learning

autoInstruct. Handles everything related to working with instruction datasets

chatbot-ui-react. ChatMaxx Furiousa - So that I don't have to buy subscription from everyone like it is OTT wars

deepseekv3-minimal. Creating the DeepSeek V3 model from scratch

fpo. Implementation of Flow Policy Optimization (FPO)

DeepSeek-Coder-local-UI. DeepSeek Coder: Let the Code Write Itself

Surgical-Theatre. Python

research_assistant. research assistant to analyse papers

seamless_communication. Foundational Models for State-of-the-Art Speech and Text Translation

simplebpe. needs clean up, incomplete

komorebi. LM/VLM implementations

context. Python

kautuhal. experimental log, fun and random shenanigans

wikivec2text. Simple embedding -> text model trained on a small subset of Wikipedia sentences.

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no crazy configs, no giant monorepo—but scores 65% on SWE-bench verified!

kotaemon. An open-source RAG-based tool for chatting with your documents.

opencode. AI coding agent, built for the terminal.

llama3-recipes. Jupyter Notebook

pdf_to_image. convert any pdf to images per page