-
poolside
- World wide
-
18:38
(UTC -06:00)
Stars
Measures whether a language model's internal state predict properties of its own output
Open-source framework for the research and development of foundation models.
Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.
Review-first terminal diff viewer for agentic coders
pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor
A replayable arcade shooter where you control a snake of heroes.
A debugging and profiling tool that can trace and visualize python code execution
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Context7 Platform -- Up-to-date docs for AI agents
Our library for RL environments + evals
VSCode extension that demonstrates the use of large language models (LLMs) for active debugging of programs
Minimalistic 4D-parallelism distributed training framework for education purpose
Fully open reproduction of DeepSeek-R1
speedrun implementation of dl papers throughout history
A scientific instrument for investigating latent spaces
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
Visualize the intermediate output of Mistral 7B
Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"
distill chatGPT coding ability into small model (1b)
A library for advanced large language model reasoning
Structured and typehinted GPT responses in Python
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Community interface for generative AI