Search Results for "reasoning" - Page 5
Sort By:
Showing 606 open source projects for "reasoning"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
$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
Computational Thinking
Introduction to computational thinking with Julia
...It emphasizes learning how to translate problems into computational terms and developing algorithms and models to analyze them effectively. Using Julia, the course highlights both mathematical reasoning and practical coding, bridging the gap between theory and application. The materials include lectures, notebooks, exercises, and projects that encourage experimentation and discovery. By combining programming with conceptual depth, the repository aims to build skills that are transferable across disciplines and essential for modern scientific inquiry. -
2
Fulcro
A library for development of single-page full-stack web applications
Fulcro is a batteries-included, full-stack library for building data-driven web applications in Clojure and ClojureScript. It integrates seamlessly with React, supports web, native, and desktop (Electron) targets, and enables strong local reasoning while facilitating rapid development and scalable production-level UIs. The rewrite of Fulcro Inspect is available via the releases page of Fulcro Inspect. And there are preliminary instructions for using it with the latest Fulcro. The alpha versions of Fulcro 3.8 are alpha purely because of this development-time change and its potential issues, and are otherwise production-ready. -
3
DeepSeek V2
Strong, Economical, and Efficient Mixture-of-Experts Language Model
...This version likely includes architectural improvements, training enhancements, and expanded dataset coverage compared to V1. The repository includes model weight artifacts, evaluation benchmarks across a broad suite (e.g. reasoning, math, multilingual), configuration files, and possibly tokenization / inference scripts. The V2 model is expected to support more advanced features like better context window handling, more efficient inference, better performance on challenging tasks, and stronger alignment with human feedback. Because DeepSeek is pushing open-weight competition, this V2 iteration is meant to solidify its position in benchmark rankings and in developer adoption. ... -
4
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. ... -
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.
-
5
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. -
6
DeepSeek Prover V2
Advancing Formal Mathematical Reasoning via Reinforcement Learning
...The repository describes how they use recursive proof decomposition by prompting DeepSeek-V3 to break complex theorems into subgoals, synthesize proof sketches, and then combine them to bootstrap training data. They then fine-tune via reinforcement learning with binary correct/incorrect feedback to integrate informal reasoning with formal proof behavior. The repo releases two model sizes (7B and 671B) and provides evaluation performance (e.g. pass rates on MiniF2F, results on ProverBench) as well as prompt / usage examples for proof generation in Lean 4. It also includes a PDF of the paper or project overview and sample formalization datasets. Because theorem proving is a cutting-edge area in LLM research, Prover-V2 is positioned as a pushing-forward effort in formal reasoning for LLMs. -
7
DeepSeek GUI
AI agent workspace for DeepSeek models, with Code and Claw modes
...The project includes Code and Claw modes, which are intended to support software development and agent-style task handling inside the application. It targets users who want a dedicated desktop-like workspace for DeepSeek-based coding, reasoning, and productivity. The project is released under the MIT license and has builds for major desktop platforms, including macOS and Windows. Its main value is making DeepSeek agent workflows easier to access through a focused visual interface. -
8
Qwen3.6
Qwen3.6 is the large language model series developed by Qwen team
The Qwen3.6 project is an open-source large language model series developed by Alibaba’s Qwen team, designed to deliver high-performance AI capabilities with a strong emphasis on real-world usability and developer productivity. It builds upon the advancements introduced in Qwen3.5, focusing on improving stability, responsiveness, and practical application in coding and agent-based workflows. The repository serves as a central hub for documentation, community discussion, and access to the... -
9
Google Agent Skills
Agent Skills for Google products and technologies
...It is designed to integrate with agent platforms through a standardized installation system. The project emphasizes reusable, composable knowledge units that can enhance agent reasoning and execution. It is actively developed and intended to support modern AI-driven development workflows. The system helps bridge the gap between documentation and actionable agent behavior. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
LeetCode Master
About "Code Thoughts" LeetCode Practice Guide: 200 classic questions
leetcode-master is a comprehensive collection of LeetCode solutions written in C++ and organized as a structured learning path for coding interview preparation. The repository contains detailed explanations, categorized problem sets, and step-by-step reasoning behind solutions, making it an effective study companion for developers preparing for technical interviews. Problems are grouped by topic—such as arrays, linked lists, dynamic programming, greedy algorithms, and graph theory—so learners can focus on specific areas systematically. Each solution is accompanied by clear commentary to explain the thought process, algorithm design, and complexity analysis. ... -
11
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. It then iteratively refines its search until it produces a comprehensive, well-cited answer synthesized by the Gemini model. The repository provides both a browser-based chat interface and a command-line script (cli_research.py) for executing research queries directly. ... -
12
Kimi-K3
Open Frontier Intelligence
Kimi K3 is an open-weight, native multimodal agentic model from Moonshot AI for advanced reasoning, coding, and knowledge work. It uses a 2.8-trillion-parameter mixture-of-experts architecture while activating 104 billion parameters per token. Its design combines Kimi Delta Attention, gated multihead latent attention, Attention Residuals, and Stable LatentMoE routing. The model can process text and images and supports a context window of more than one million tokens. -
13
LLM Colosseum
Benchmark LLMs by fighting in Street Fighter 3
...The system places language models inside the environment of the classic video game Street Fighter III, where they must interpret the game state and decide which actions to perform during combat. This setup creates a dynamic environment that tests reasoning, situational awareness, and decision-making abilities in real time. Instead of relying purely on reward signals as in reinforcement learning agents, the models analyze contextual information and generate strategic actions based on the game environment. Performance is evaluated using a competitive ranking system that assigns models an ELO rating based on their results across matches against other models. -
14
claurst
Your favorite Terminal Coding Agent, now in Rust
claurst is an experimental AI agent framework that appears to focus on structured reasoning and task execution within coding or automation environments. The project likely explores how agents can be designed to handle complex workflows through modular components and clearly defined execution steps. It may include abstractions for managing context, decision-making, and interaction with external tools, enabling agents to perform multi-step tasks efficiently. -
15
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
...Given its open-source availability under the same project repository, it provides an accessible entry point for testing multimodal reasoning and building proof-of-concept applications. -
16
Sa2VA
Official Repo For "Sa2VA: Marrying SAM2 with LLaVA
Sa2VA is a cutting-edge open-source multi-modal large language model (MLLM) developed by ByteDance that unifies dense segmentation, visual understanding, and language-based reasoning across both images and videos. It merges the segmentation power of a state-of-the-art video segmentation model (based on SAM‑2) with the vision-language reasoning capabilities of a strong LLM backbone (derived from models like InternVL2.5 / Qwen-VL series), yielding a system that can answer questions about visual content, perform referring segmentation, and maintain temporal consistency across frames in video. ... -
17
Deep Research
Use any LLMs (Large Language Models) for Deep Research
...It offers MCP server support and SSE APIs, so IDEs and agent clients can drive the same workflow programmatically. The result is a repeatable process for scoping questions, collecting evidence, and producing a concise report with citations and reasoning steps. -
18
BeeAI Framework
Build production-ready AI agents in both Python and Typescript
...It goes beyond simple prompt-based interactions by introducing rule-based governance and constraint enforcement, enabling developers to create agents with predictable and controllable behavior while still preserving advanced reasoning capabilities. The framework supports both Python and TypeScript with full feature parity, making it accessible to a wide range of developers and teams. It includes a unified backend layer that connects seamlessly to multiple large language model providers, allowing flexible deployment across different AI infrastructures without vendor lock-in. ... -
19
Agents 2.0
An Open-source Framework for Data-centric Language Agents
...The project introduces a concept known as agent symbolic learning, which treats an agent pipeline similarly to a neural network computational graph. In this framework, each node in the pipeline represents a step in the reasoning or action process, while prompts and tools act as adjustable parameters analogous to neural network weights. During training, the system performs a forward execution where the agent completes a task and records the trajectory of prompts, outputs, and tool usage. A prompt-based loss function is then applied to evaluate the quality of the outcome, generating language-based gradients that guide improvements to the agent pipeline. -
20
TraceRoot
Find the Root Cause in Your Code's Trace
...Lightweight SDKs for Python and TypeScript enable seamless instrumentation using OpenTelemetry, with support for both self-hosted and cloud deployment. Human-in-the-loop interaction is central: developers can guide reasoning by selecting relevant spans or logs, then verify agent reasoning through traceable context. -
21
HY-World 1.5
A Systematic Framework for Interactive World Modeling
...The platform targets use cases in digital entertainment, game worlds, training simulators, and interactive storytelling, where AI agents need to adapt to real-time user inputs and changes in environment state. It blends advanced reasoning with multimodal synthesis, enabling agents to describe scenes, generate context-appropriate responses, and contribute to narrative or gameplay flows. The underlying framework typically supports large-context state tracking across extended interactions, blending temporal and spatial multimodal signals. -
22
OpenAI Agents (Python)
A lightweight, powerful framework for multi-agent workflows
openai-agents-python is a library developed by OpenAI to simplify the process of creating and running agents that interact with tools and APIs using OpenAI models. It provides abstractions for tool usage, memory management, and agent workflows, enabling developers to define function-calling agents that reason through multi-step tasks. Ideal for building custom AI workflows, the library supports dynamic tool definitions and contextual memory handling. -
23
ZeroGPU Router
Cut inference costs without dumbing down your agent
...Its main value is letting agents reserve expensive frontier models for complex reasoning while offloading routine language tasks to cheaper specialized routes. -
24
pytudes
Python programs, usually short, of considerable difficulty
...The repository includes readable solutions, experiments, notebooks, and scripts that cover algorithms, puzzles, probability, search, language processing, simulation, and mathematical reasoning. It is useful for programmers who want to study elegant Python code while learning how experienced developers approach problem solving. Many examples emphasize clarity and compactness rather than framework-heavy engineering. pytudes is best understood as a learning library, a coding style reference, and a set of practical programming studies. -
25
MetaClaw
Just talk to your agent
MetaClaw is an AI or agent-oriented system that appears to focus on advanced control, coordination, or training of autonomous agents, potentially within reinforcement learning or tool-using environments. The project likely emphasizes meta-level reasoning, where agents are not only executing tasks but also adapting their strategies based on feedback and performance signals. It may incorporate mechanisms for learning from interactions, improving decision-making over time, and generalizing across different domains. The architecture suggests scalability, allowing the system to handle multiple agents or complex workflows simultaneously. ...