Search Results for "reasoning models" - Page 3
Sort By:
Showing 188 open source projects for "reasoning models"
View related business solutions-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
1
Mathematics Dataset
This dataset code generates mathematical question and answer pairs
...The dataset enables models to learn mathematical problem-solving through examples that involve both numeric and symbolic reasoning. Version 1.0 includes over 2 million examples per category, with training splits labeled as “easy,” “medium,” and “hard,” supporting curriculum-based learning strategies. The data can be accessed via PyPI or generated locally using provided Python scripts, with outputs formatted for direct use in training or evaluation pipelines. -
2
Ling
Ling is a MoE LLM provided and open-sourced by InclusionAI
...The project offers different sizes (Ling-lite, Ling-plus) and emphasizes flexibility and efficiency: being able to scale, adapt expert activation, and perform across a range of natural language/reasoning tasks. Example scripts, inference pipelines, and documentation. The codebase includes inference, examples, models, documentation, and model download infrastructure. As more developers and researchers engage with the platform, we can expect rapid advancements and improvements, leading to even more sophisticated applications. Model inference and API code (e.g. integration with Transformers). ... -
3
GLM-4-Voice
GLM-4-Voice | End-to-End Chinese-English Conversational Model
GLM-4-Voice is an open-source speech-enabled model from ZhipuAI, extending the GLM-4 family into the audio domain. It integrates advanced voice recognition and generation with the multimodal reasoning capabilities of GLM-4, enabling smooth natural interaction via spoken input and output. The model supports real-time speech-to-text transcription, spoken dialogue understanding, and text-to-speech synthesis, making it suitable for conversational AI, virtual assistants, and accessibility... -
4
InternGPT
Open source demo platform where you can easily showcase your AI models
InternGPT is an open-source multimodal AI framework designed to extend large language models beyond text interactions into visual reasoning and image manipulation tasks. The system integrates conversational AI with computer vision models so users can interact with images, videos, and visual environments through natural language instructions. Unlike traditional chat systems that rely solely on text prompts, InternGPT allows users to interact with visual content using both language and nonverbal signals such as pointing or highlighting objects within images. ... -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
TTRL
Test-Time Reinforcement Learning
TTRL is an open-source framework for test-time reinforcement learning in large language models, with a particular focus on reasoning tasks where ground-truth labels are not available during inference. The project addresses the problem of how to generate useful reward signals from unlabeled test-time data, and its central insight is that common test-time scaling practices such as majority voting can be repurposed into reward estimates for online reinforcement learning. ... -
6
DATAGEN
AI-driven multi-agent research assistant automating hypothesis
...Instead of requiring users to manually orchestrate each stage of a research process, the platform allows these agents to coordinate automatically and handle the workflow end-to-end. The project integrates several modern AI frameworks including LangChain, LangGraph, and large language models to manage reasoning and data processing tasks. Through this architecture, the system can combine structured data analysis with natural language reasoning to generate insights and research outputs. The platform is designed for researchers, analysts, and developers who want to accelerate data exploration and automate parts of the research lifecycle. -
7
Synthetic Data Kit
Tool for generating high quality Synthetic datasets
Synthetic Data Kit is a CLI-centric toolkit for generating high-quality synthetic datasets to fine-tune Llama models, with an emphasis on producing reasoning traces and QA pairs that line up with modern instruction-tuning formats. It ships an opinionated, modular workflow that covers ingesting heterogeneous sources (documents, transcripts), prompting models to create labeled examples, and exporting to fine-tuning schemas with minimal glue code. -
8
Gemini Fullstack LangGraph Quickstart
Get started w/ building Fullstack Agents using Gemini 2.5 & LangGraph
gemini-fullstack-langgraph-quickstart is a fullstack reference application from Google DeepMind’s Gemini team that demonstrates how to build a research-augmented conversational AI system using LangGraph and Google Gemini models. The project features a React (Vite) frontend and a LangGraph/FastAPI backend designed to work together seamlessly for real-time research and reasoning tasks. The backend agent dynamically generates search queries based on user input, retrieves information via the Google Search API, and performs reflective reasoning to identify knowledge gaps. ... -
9
OM1
Modular AI runtime for robots
OM1 is an open-source AI platform designed to build autonomous agents capable of interacting with digital environments and completing complex tasks. The project focuses on creating a modular architecture where language models can coordinate with external tools, APIs, and knowledge sources to accomplish multi-step objectives. Instead of operating as simple conversational systems, OM1 agents can plan actions, retrieve information, and execute tasks across different services. The framework integrates reasoning modules, planning strategies, and tool interfaces that allow agents to operate in dynamic environments. ... -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
RecursiveMAS
Offical Implementation for "Recursive Multi-Agent Systems"
...The system uses a lightweight module called RecursiveLink to transfer and transform latent representations between agents, enabling seamless interaction even across heterogeneous models. It also incorporates an inner–outer loop training approach that optimizes the entire system collectively rather than tuning each agent separately. This design improves efficiency, reduces token usage, and stabilizes learning during iterative reasoning. -
11
DeepSearcher
Open Source Deep Research Alternative to Reason and Search
...It also supports flexible embeddings, making it easier to choose different embedding models depending on domain requirements, latency targets, or accuracy goals. The overall workflow aims to minimize hallucinations by grounding outputs in retrieved material and then applying structured reasoning over that evidence before generating a final report. -
12
TAME LLM
Traditional Mandarin LLMs for Taiwan
TAME LLM is an open-source initiative focused on building and releasing large language models optimized for Traditional Mandarin and the linguistic context of Taiwan. The project includes models such as Llama-3-Taiwan-70B, which are fine-tuned versions of large transformer architectures trained on extensive corpora containing both Traditional Mandarin and English text. These models are designed to support applications such as conversational AI, knowledge retrieval, and domain-specific reasoning in fields like manufacturing, law, healthcare, and electronics. ... -
13
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
...It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds state-of-the-art performance in many multimodal benchmarks, particularly spoken language understanding, audio reasoning, image/video understanding, etc. Very strong benchmark performance across modalities (audio understanding, speech recognition, image/video reasoning) and often outperforming or matching single-modality models at a similar scale. Real-time streaming responses, including natural speech synthesis (text-to-speech) and chunked inputs for low latency interaction. -
14
GenericAgent
Self-evolving autonomous agent framework
The GenericAgent project is a flexible framework for building autonomous AI agents that can operate across diverse tasks and environments. It is designed around modularity, allowing developers to define agents with interchangeable components such as tools, memory systems, and reasoning strategies. The architecture emphasizes generality, enabling the same agent framework to be adapted for different domains including coding, research, and task automation. It integrates with modern language models to provide planning, execution, and iterative reasoning capabilities, making it suitable for complex workflows. The project also focuses on extensibility, allowing developers to plug in custom tools or APIs and tailor agent behavior to specific use cases. ... -
15
LOTUS
AI-Powered Data Processing: Use LOTUS to process all of your datasets
...The core concept of the framework is the use of semantic operators, which extend traditional relational database operations to support reasoning over text and other unstructured data. These operators allow tasks such as semantic filtering, ranking, clustering, and summarization to be expressed directly within data processing pipelines. The LOTUS engine automatically optimizes how language models are used during execution, which can significantly improve performance and reduce computational cost. -
16
DeepSeek Math
Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeek-Math is DeepSeek’s specialized model (or dataset + evaluation) focusing on mathematical reasoning, symbolic manipulation, proof steps, and advanced quantitative problem solving. The repository is likely to include fine-tuning routines or task datasets (e.g. MATH, GSM8K, ARB), demonstration notebooks, prompt templates, and evaluation results on math benchmarks. The goal is to push DeepSeek’s performance in domains that require rigorous symbolic steps, calculus, linear algebra, number... -
17
QwenPaw
A personal AI assistant, easy to install
QwenPaw is an AI agent framework developed by the AgentScope ecosystem to provide a desktop-style intelligent assistant powered by Qwen language models and modular agent orchestration. The project combines conversational AI, memory systems, tool usage, workflow automation, and multimodal interaction into a unified assistant environment designed for daily productivity and experimentation. It supports structured reasoning, autonomous task execution, and integration with external tools and APIs, allowing the assistant to perform actions beyond standard chatbot conversations. ... -
18
mini SWE-agent
The 100 line AI agent that solves GitHub issues
mini SWE-agent is a lightweight, minimalist AI-powered software engineering agent designed to autonomously solve GitHub issues and assist developers directly from the command line using large language models. Unlike more complex frameworks, it emphasizes simplicity and efficiency, consisting of roughly 100 lines of code while still achieving strong performance on benchmarks such as SWE-bench Verified, where it demonstrates competitive problem-solving capabilities. The agent operates by interpreting software issues, analyzing repository context, and executing actions such as editing code, running commands, and validating fixes through iterative reasoning loops. ... -
19
nano-graphrag
A simple, easy-to-hack GraphRAG implementation
nano-graphrag is a lightweight implementation of the GraphRAG approach designed to simplify experimentation with graph-based retrieval-augmented generation systems. GraphRAG expands traditional RAG pipelines by constructing knowledge graphs from documents and using relationships between entities to improve the quality and reasoning of AI responses. The nano-GraphRAG project focuses on reducing complexity by providing a compact and readable codebase that preserves the core functionality of graph-based retrieval systems while remaining easy to modify and extend. The system extracts entities and relationships from documents using language models and organizes them into graph structures that can be queried during generation. ... -
20
Qwen
The official repo of Qwen chat & pretrained large language model
Qwen is a series of large language models developed by Alibaba Cloud, consisting of various pretrained versions like Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B. These models, which range from smaller to larger configurations, are designed for a wide range of natural language processing tasks. They are openly available for research and commercial use, with Qwen's code and model weights shared on GitHub. Qwen's capabilities include text generation, comprehension, and conversation, making it a... -
21
NExT-GPT
Code and models for ICML 2024 paper, NExT-GPT
...This architecture allows the model to convert between modalities, such as generating images from text descriptions or producing audio or video outputs based on textual prompts. The project also introduces instruction-tuning strategies that enable the model to perform complex multimodal reasoning and generation tasks with minimal additional parameters. -
22
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.1V — often referred to as a smaller / lighter version of the GLM-V family — offers a more resource-efficient option for users who want multimodal capabilities without requiring large compute resources. Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. ... -
23
Sapiens
High-resolution models for human tasks
Sapiens is a research framework from Meta AI focused on embodied intelligence and human-like multimodal learning, aiming to train agents that can perceive, reason, and act in complex environments. It integrates sensory inputs such as vision, audio, and proprioception into a unified learning architecture that allows agents to understand and adapt to their surroundings dynamically. The project emphasizes long-horizon reasoning and cross-modal grounding—connecting language, perception, and... -
24
Controllable-RAG-Agent
This repository provides an advanced RAG
Controllable-RAG-Agent is an advanced Retrieval-Augmented Generation (RAG) system designed specifically for complex, multi-step question answering over your own documents. Instead of relying solely on simple semantic search, it builds a deterministic control graph that acts as the “brain” of the agent, orchestrating planning, retrieval, reasoning, and verification across many steps. The pipeline ingests PDFs, splits them into chapters, cleans and preprocesses text, then constructs vector... -
25
LLM Council
LLM Council works together to answer your hardest questions
LLM Council is a creative open-source web application by Andrej Karpathy that lets you consult multiple large language models together to answer questions more reliably than querying a single model. Instead of relying on one provider, this application sends your query simultaneously to several LLMs supported via OpenRouter, collects each model’s independent response, and then orchestrates a multi-stage evaluation where the models critique and rank each other’s outputs anonymously. ...
