Renderer for the harmony response format to be used with gpt-oss
☆4,343Apr 8, 2026Updated 3 weeks ago
Alternatives and similar repositories for harmony
Users that are interested in harmony are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI☆20,047Mar 27, 2026Updated last month
- SGLang is a high-performance serving framework for large language models and multimodal models.☆26,832Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆78,385Updated this week
- Minimalistic large language model 3D-parallelism training☆2,674Apr 7, 2026Updated 3 weeks ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,046Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Fully open reproduction of DeepSeek-R1☆26,013Apr 2, 2026Updated last month
- Train transformer language models with reinforcement learning.☆18,193Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,462Updated this week
- Lightweight coding agent that runs in your terminal☆78,375Updated this week
- Minimal reproduction of DeepSeek R1-Zero☆13,079Feb 27, 2026Updated 2 months ago
- Our library for RL environments + evals☆4,057Updated this week
- Fast and memory-efficient exact attention☆23,563Updated this week
- ☆4,471Apr 22, 2026Updated last week
- AllenAI's post-training codebase☆3,702Apr 25, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.☆63,070Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,544Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆3,015Apr 20, 2026Updated last week
- PyTorch native post-training library☆5,750Updated this week
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆21,407Apr 15, 2026Updated 2 weeks ago
- A framework for few-shot evaluation of language models.☆12,331Apr 22, 2026Updated last week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,199Updated this week
- DSPy: The framework for programming—not prompting—language models☆34,016Apr 24, 2026Updated last week
- Efficient Triton Kernels for LLM Training☆6,315Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Development repository for the Triton language and compiler☆19,087Updated this week
- slime is an LLM post-training framework for RL Scaling.☆5,490Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆18,037Mar 27, 2026Updated last month
- Kimi K2 is the large language model series developed by Moonshot AI team☆10,717Jan 21, 2026Updated 3 months ago
- A lightweight, powerful framework for multi-agent workflows☆25,587Updated this week
- Tools for merging pretrained large language models.☆7,023Mar 15, 2026Updated last month
- A PyTorch native platform for training generative AI models☆5,286Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,417Updated this week
- Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing a…☆45,153Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A Datacenter Scale Distributed Inference Serving Framework☆6,701Updated this week
- s1: Simple test-time scaling☆6,650Jun 25, 2025Updated 10 months ago
- Ongoing research training transformer models at scale☆16,203Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,762Jul 18, 2025Updated 9 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,248Aug 27, 2025Updated 8 months ago
- ☆1,135Jan 10, 2026Updated 3 months ago
- Simple RL training for reasoning☆3,851Dec 23, 2025Updated 4 months ago