Search Results for "reasoning" - Page 3
Sort By:
Showing 271 open source projects for "reasoning"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
HRM-Text
1B text generation model based on the HRM architecture
HRM-Text is a one-billion-parameter text generation model and pretraining framework based on the Hierarchical Reasoning Model architecture. It is designed to make foundation model pretraining more accessible by reducing compute and data requirements compared with traditional scaling-heavy approaches. The system combines hierarchical recurrent design, task-completion strengthening, and latent-space reasoning. Its training stack includes PrefixLM sequence packing, FlashAttention 3 kernels, PyTorch FSDP2, evaluation scripts, and checkpoint conversion tools. ... -
2
RAPTOR
The official implementation of RAPTOR
...During inference, the system can navigate this hierarchical representation to retrieve information that best matches the user’s query while preserving broader contextual understanding. This approach improves question-answering performance on complex tasks that require reasoning across long documents or multiple sources. -
3
Antigravity Awesome Skills
The Ultimate Collection of 700+ Agentic Skills for Claude Code
...The project includes skill definitions, example prompts, and usage patterns that highlight how modular abilities can be assembled into functioning assistants. Because it aims to reduce cognitive overhead, many skills show how to structure intents, handle context, and orchestrate multi-step reasoning without deep technical complexity. It also serves as inspiration for users looking to prototype new use cases — from conversational helpers that answer questions to workflow automators that trigger actions. -
4
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
DeepSeek-VL2 is DeepSeek’s vision + language multimodal model—essentially the next-gen successor to their first vision-language models. It combines image and text inputs into a unified embedding / reasoning space so that you can query with text and image jointly (e.g. “What’s going on in this scene?” or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. ... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
OpenClaw Medical Skills
The largest open-source medical AI skills library for OpenClaw
...The project organizes domain-specific “skills” that enable autonomous agents to perform tasks related to biomedical research, healthcare analysis, and clinical data interpretation. Each skill is packaged as a modular component that can be integrated into an OpenClaw-based AI assistant, allowing the agent to perform expert-level reasoning and workflows in medical contexts. Instead of relying on general-purpose language model responses, the repository equips AI agents with structured instructions and tools tailored to medical knowledge and datasets. This modular design allows developers and researchers to build AI systems that can access specialized medical reasoning processes, retrieve relevant biomedical information, and generate structured outputs suitable for analysis or downstream processing. -
6
ARC-AGI-1 Task Generator
Generates original ARC-AGI-1-style tasks distribution-matched
ARC-AGI-1 Task Generator creates new ARC-style reasoning tasks whose distribution is designed to resemble the public ARC-AGI-1 evaluation set. It provides fresh problems that models are less likely to have encountered during training or previous evaluation. The project is intended to complement public benchmark scores by testing whether reasoning abilities transfer to newly generated examples. -
7
Hello-Agents
Building an Intelligent Agent from Scratch
Hello Agents is an open educational project designed to teach developers how to understand, design, and build AI-native agents from the ground up through structured tutorials and practical examples. The project focuses on guiding learners beyond superficial framework usage toward deeper comprehension of agent architecture, reasoning loops, and real-world implementation patterns. It walks users through core concepts such as ReAct-style reasoning, tool usage, memory handling, and multi-step task execution, enabling hands-on experimentation with modern LLM-powered agent systems. The repository is structured as a progressive learning path, combining theory, exercises, and runnable code so users can incrementally build more capable agents. ... -
8
R1-V
Witness the aha moment of VLM with less than $3
R1-V is an initiative aimed at enhancing the generalization capabilities of Vision-Language Models (VLMs) through Reinforcement Learning in Visual Reasoning (RLVR). The project focuses on building a comprehensive framework that emphasizes algorithm enhancement, efficiency optimization, and task diversity to achieve general vision-language intelligence and visual/GUI agents. The team's long-term goal is to contribute impactful open-source research in this domain. -
9
Tianji
Evaluation suite designed to assess the performance of LLMs
Tianji is a comprehensive evaluation suite designed to assess the performance of large language models (LLMs) across multiple dimensions. It focuses on measuring general capabilities such as reasoning, knowledge, commonsense, and language understanding. Tianji provides a curated set of benchmarks and a unified framework for systematically comparing LLMs, making it useful for research and model selection. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Rapid LaTeX OCR
Formula recognition based on LaTeX-OCR and ONNXRuntime
Formula recognition based on LaTeX-OCR and ONNXRuntime. rapid_latex_ocr is a tool to convert formula images to latex format. The reasoning code in the repo is modified from LaTeX-OCR, the model has all been converted to ONNX format, and the reasoning code has been simplified, Inference is faster and easier to deploy. The repo only has codes based on ONNXRuntime or OpenVINO inference in onnx format and does not contain training model codes. If you want to train your own model, please move to LaTeX-OCR. ... -
11
MiniCPM4
Ultra-Efficient LLMs on End Device
MiniCPM4 is part of the MiniCPM family of ultra-efficient large language models designed specifically for high performance on edge devices and resource-constrained environments. Unlike traditional large-scale models that require extensive computational resources, MiniCPM4 focuses on delivering competitive reasoning and language capabilities while maintaining significantly lower latency and higher efficiency. It achieves this through optimized architectures, scalable training strategies, and techniques such as long-context pretraining and YaRN-based length extension, allowing it to handle sequences up to 128K tokens effectively. The model demonstrates strong performance across tasks such as long-text comprehension, reasoning, and general language generation, often outperforming similar-sized models in both speed and accuracy. ... -
12
verl-agent
Designed for training LLM/VLM agents via RL
...Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
13
LongBench
LongBench v2 and LongBench (ACL 25'&24')
...LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. The benchmark includes multiple categories such as single-document question answering, multi-document reasoning, summarization, long dialogue understanding, and code analysis. It supports bilingual evaluation in English and Chinese to assess multilingual capabilities across extended contexts. Newer versions of the benchmark introduce extremely long context windows ranging from thousands to millions of tokens, enabling researchers to test the limits of modern long-context models. -
14
ControlFlow
Take control of your AI agents
...The framework provides a structured approach for building AI systems by breaking complex tasks into smaller units called tasks that can be assigned to specialized AI agents. Developers can combine these tasks into flows that define how work is executed, enabling the creation of multi-step reasoning pipelines and collaborative agent systems. ControlFlow focuses on maintaining transparency and control in AI applications by providing explicit workflow structures instead of opaque chains of prompts. The system integrates with common LLM providers and allows developers to create workflows that blend traditional software logic with AI-driven reasoning. -
15
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
...By testing models across diverse scenarios, the benchmark highlights strengths and weaknesses in reasoning, long-term planning, and tool usage. -
16
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. -
17
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
...It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
18
Code World Model (CWM)
Research code artifacts for Code World Model (CWM)
...Inference scripts and utilities for code generation tasks. Evaluation benchmarks on code, mathematics, and reasoning tasks. Demos, serving code, and evaluation pipelines. -
19
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
20
HunyuanImage-3.0
A Powerful Native Multimodal Model for Image Generation
...The model is intended to be competitive with closed-source image generation systems, aiming for high fidelity, prompt adherence, fine detail, and even “world knowledge” reasoning (i.e. leveraging context, semantics, or common sense in generation). The GitHub repo includes code, scripts, model loading instructions, inference utilities, prompt handling, and integration with standard ML tooling (e.g. Hugging Face / Transformers). -
21
Qwen3
Qwen3 is the large language model series developed by Qwen team
Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions, tools/pipelines provided for inference using quantized formats (e.g. GGUF, etc.). ... -
22
Semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
Semantica is an open-source graph-native infrastructure layer for building explainable and auditable AI systems. It ingests fragmented data, extracts meaningful entities and relationships, and transforms them into context and knowledge graphs. Deterministic reasoning, ontology management, provenance tracking, and decision records help explain how conclusions were reached. The platform can complement existing LLMs, vector databases, and agent frameworks rather than replacing them. It supports RDF and labeled-property graphs along with standards-oriented interoperable storage. A browser-based Knowledge Explorer provides graph visualization, temporal inspection, and causal-chain tracing. ... -
23
Agentic RAG for Dummies
A modular Agentic RAG built with LangGraph
...The project explains the principles behind agentic retrieval pipelines where language models can dynamically decide when to retrieve information, analyze results, and plan further actions. Instead of relying on static retrieval pipelines, the system shows how agents can orchestrate retrieval, reasoning, and tool usage in a more flexible decision loop. The repository provides practical examples and tutorials that guide developers through building agentic RAG systems using modern AI frameworks. These examples illustrate how agents can access knowledge bases, retrieve documents, analyze them, and refine their queries during multi-step reasoning processes. ... -
24
openbench
Provider-agnostic, open-source evaluation infrastructure
openbench is an open-source, provider-agnostic evaluation infrastructure designed to run standardized, reproducible benchmarks on large language models (LLMs), enabling fair comparison across different model providers. It bundles dozens of evaluation suites — covering knowledge, reasoning, math, code, science, reading comprehension, long-context recall, graph reasoning, and more — so users don’t need to assemble disparate datasets themselves. With a simple CLI interface (e.g. bench eval <benchmark> --model <model-id>), you can quickly evaluate any model supported by Groq or other providers (OpenAI, Anthropic, HuggingFace, local models, etc.). openbench also supports private/local evaluations: you can integrate your own custom benchmarks or data (e.g. internal test suites, domain-specific tasks) to evaluate models in a privacy-preserving way. -
25
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. ...