ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
- autonomous-agents
- language-model
- llm
- mathematical-reasoning
142,273 visible repositories in the index
745–768 of 1,816 · Most stars
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
Evaluate your LLM's response with Prometheus and GPT4 💯
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Tools to train a generative model on arbitrary audio samples
AI model square and chat with AI.
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
AI Group is a powerful mobile intelligent assistant application that integrates multiple large language models (LLMs) and AI services, providing you with a convenient intelligent interaction experience.
Evaluation tool for LLM QA chains
LLM-based ontological extraction tools, including SPIRES
T3Bench: Benchmarking Current Progress in Text-to-3D Generation
WHartTest 是一款AI驱动的测试自动化平台,实现从需求到可执行测试用例的自动化生成与管理,帮助测试团队提升效率与覆盖率。 (WHartTest is an AI-driven test automation platform that automates the generation and management of executable test cases from requirements, helping testing teams improve efficiency and coverage.)
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
An Open Source Toolkit For LLM Distillation
🎉 全新下一代高颜值、高性能、高扩展的智能AI大模型API聚合分发系统 | A new next-generation high-value, high-performance, and highly scalable intelligent AI large-model API aggregation and distribution
Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
Codebase for Aria - an Open Multimodal Native MoE
Arena-Hard-Auto: An automatic LLM benchmark.
AIConfig is a config-based framework to build generative AI applications.
AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.
A series of math-specific large language models of our Qwen2 series.