Stars
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
Inference Preference Optimization enhances reasoning in LLMs by integrating retrieved memory from user or agent context into Group Relative Policy Optimization (GRPO).
Transform memory traces into calendar events for agents and users to plan, reflect, and act over time. We develop a conversational interface for temporal reasoning, context-aware scheduling, and ed…
Inference Preference Optimization (IPO) builds on GRPO by integrating memory retrieval into chain-of-thought reasoning for personalized inference.
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
React app for inspecting, building and debugging with the Realtime API
Uncomplicated Observability for Python and beyond! 🪵🔥
Examples and guides for using the OpenAI API
Fast and memory-efficient exact attention
An extremely fast Python package and project manager, written in Rust.
A Datacenter Scale Distributed Inference Serving Framework
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Minimal reproduction of DeepSeek R1-Zero
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
Biological foundation modeling from molecular to genome scale
Framework enabling modular interchange of language agents, environments, and optimizers
A language agent gym with challenging scientific tasks
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (…
Lbster: Language models for Biological Sequence Transformation and Evolutionary Representation
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
Python and MATLAB code for linear algebra textbook.