Search Results for "thinking" - Page 2
Sort By:
Showing 53 open source projects for "thinking"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
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.
-
1
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text, images, audio, and video and delivers real-time streaming responses in text and natural speech. It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. The model supports 119 text languages, 19 speech input languages, and... -
2
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... -
3
GLM-4.5V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.5V is the preceding iteration in the GLM-V series that laid much of the groundwork for general multimodal reasoning and vision-language understanding. It embodies the design philosophy of mixing visual and textual modalities into a unified model capable of general-purpose reasoning, content understanding, and generation, while already supporting a wide variety of tasks: from image captioning and visual question answering to content recognition, GUI-based agents, video understanding,... -
4
opc-methodology
The second edition of "One-person Enterprise Methodology"
...It is particularly useful for building consistent workflows in areas such as content generation, automation, and decision support. The framework promotes modular thinking, allowing users to reuse and refine components across different tasks. It also encourages iterative refinement, helping users improve prompt performance through systematic adjustments. Overall, OPC Methodology provides a practical approach to prompt engineering that prioritizes clarity, structure, and repeatability. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
Matrix ChatGPT Bot
Talk to ChatGPT via any Matrix client
Matrix ChatGPT Bot allows you to talk to ChatGPT via any Matrix client. OpenAI released the official API for ChatGPT. Thus, we no longer have to use any older models or any models which kept on being turned off by OpenAI. This means the bot is now way more stable and way faster. However, please note: The usage of the API is no longer free. If you use this bot, your OpenAI account will be charged! You might want to limit your budget in your account using the OpenAI website. You need to remove... -
6
AI System & AI Infra
Tutorial repository focused on the full-stack design of AI systems
...The repository is particularly useful for engineers who want to move beyond model usage and understand the systems engineering layer that enables large-scale machine learning. Its content emphasizes architectural thinking, performance considerations, and the relationship between hardware acceleration and deep learning frameworks. -
7
Feishu ChatGPT
Voice dialogue, role-playing, multi-topic discussion, picture creation
...Familiar with the SDKs of DingTalk, Feishu, Qiwei and other platforms, and be able to develop and integrate a series of amazing functions! Proficient in platform-based detail thinking, let the efficient server-side hot update script you develop amaze the audience! Easily control Docker containerization technology and deploy code as you like! With some experience in payment function development, it really makes money fly! Understand some Linux scripting and socket programming. -
8
AgentGPT
🤖 Assemble, configure & deploy autonomous AI Agents in your browser
.... 🤖 AgentGPT allows you to configure and deploy Autonomous AI agents. Name your own custom AI and have it embark on any goal imaginable. It will attempt to reach the goal by thinking of tasks to do, executing them, and learning from the results 🚀. By sponsoring this free, open-source project, you not only have the opportunity to have your avatar/logo featured below, but also get the exclusive chance to chat with the founders!🗣️ 👉 Click here to support the project: https://github.com/sponsors/reworkd-admin -
9
The Algorithms - C #
Collection of various algorithms in mathematics, machine learning
...Each algorithm implementation is written to be readable and well documented so that students and developers can understand how the algorithm works internally. The repository is designed primarily as an educational resource that helps programmers study algorithm design and computational thinking. Contributors from around the world continually add new implementations and improvements, making the repository a collaborative learning project. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
10
igel
Machine learning tool that allows you to train and test models
...I sometimes needed a tool sometimes, which I could use to fast create a machine learning prototype. Whether to build some proof of concept, create a fast draft model to prove a point or use auto ML. I find myself often stuck writing boilerplate code and thinking too much about where to start. Therefore, I decided to create this tool. igel is built on top of other ML frameworks. It provides a simple way to use machine learning without writing a single line of code. Igel is highly customizable, but only if you want to. Igel does not force you to customize anything. Besides default values, igel can use auto-ml features to figure out a model that can work great with your data. -
11
JConstraints
Java Framework to implement solutions to solve constraints problems
JConstraints is a Java Framework that enables implementations of advanced solutions for combinatorial problems as constraints satisfaction problems. The architecture was built thinking in the constraints satisfaction paradigm. The Framework is easy to use. Therefore, with few interfaces implementations you can already run advanced combinatory solutions. Just to name a few algorithms, the Framework can solve any constraints problems using: - Regular Backtracking; - A variety of Backjumping algorithms; - A variety of arc-consistency algorithms; - Local search algorithm; - Tabu search algorithm; - Maximize solutions: comming soon; - Minimize solutions: comming soon; The Framework also enables heuristic injections so that the developers can achieve greater performance of algorithms using their own heuristics. ... -
12
Identification
A tiny "guess what I'm thinking about" game, or an identifier.
This is a tiny game : think about something and answer the questions the software asks. The goal is to have a "identifier" which is able, for instance, to find which mushroom you have in your hands. -
13
-
14
Elysia is an attempt to study the complex process behind decision making in neural systems. An evolved entity approach is used to converge on an 'intelligence' solution through genetic algorithms as well as adaptable models of distributed 'thinking'.
-
15
SPADES (System for Parallel Agent Discrete Event Simulation) is a middleware system for the creation of artificial intelligence agent-based simulations. SPADES supports robust distribution across machines and tracks the thinking time of agents.
-
16
Project Cogito is a artificial intelligence infrastructure to aid the development of thinking machines. It will provide the ability to create virtual worlds with loadable objects that brains can interact with. Administrative interfaces will be provided.
-
17
NuMarkdown-8B-Thinking
Reasoning-powered OCR VLM for converting complex documents to Markdown
NuMarkdown-8B-Thinking is the first reasoning OCR vision-language model (VLM) designed to convert documents into clean Markdown optimized for retrieval-augmented generation (RAG). Built on Qwen 2.5-VL-7B and fine-tuned with synthetic Doc → Reasoning → Markdown examples, it generates thinking tokens before producing the final Markdown to better handle complex layouts and tables. -
18
GLM-4.5-Air
Compact hybrid reasoning language model for intelligent responses
GLM-4.5-Air is a multilingual large language model with 106 billion total parameters and 12 billion active parameters, designed for conversational AI and intelligent agents. It is part of the GLM-4.5 family developed by Zhipu AI, offering hybrid reasoning capabilities via two modes: a thinking mode for complex reasoning and tool use, and a non-thinking mode for immediate responses. The model is optimized for efficiency and deployment, delivering strong results across 12 industry benchmarks, with a composite score of 59.8. GLM-4.5-Air supports both English and Chinese, and is suitable for tasks involving text generation, coding, reasoning, and tool calling. ... -
19
QwQ-32B
QwQ-32B is a reasoning-focused language model for complex tasks
...It supports an extended context length of up to 131,072 tokens and incorporates supervised fine-tuning and reinforcement learning for enhanced instruction-following capabilities. The model is capable of structured thinking and delivers competitive performance against top models like DeepSeek-R1 and o1-mini. Recommended usage involves prompts starting with <think>\n, non-greedy sampling strategies, and support for standardized outputs on math and multiple-choice tasks. For long input handling, it supports YaRN (Yet another RoPE Namer) for context scaling. -
20
Qwen3.6-27B
Dense multimodal Qwen model for coding, agents, and long context
...The model emphasizes stability and practical developer utility, with major improvements in agentic coding, frontend generation, and repository-level reasoning. It also introduces thinking preservation, allowing it to retain reasoning traces from earlier turns to improve consistency, reduce repeated computation, and support iterative agent workflows. Qwen3.6-27B natively supports a 262K-token context window and can be extended to about 1M tokens with YaRN for ultra-long tasks. It is compatible with Transformers, vLLM, SGLang, and KTransformers, supports tool calling through Qwen-Agent. -
21
Qwen3.6-35B-A3B
Open multimodal model for coding, agents, and long-context tasks
...The model emphasizes stability, responsiveness, and practical developer productivity, with major improvements in agentic coding, frontend generation, and repository-level reasoning. A notable addition is thinking preservation, which allows the model to retain reasoning context from earlier messages, improving iterative work and reducing redundant computation. Architecturally, it uses a Mixture-of-Experts design with 35B total parameters and 3B active, supports a native 262K-token context window, and can be extended to about 1M tokens with YaRN. ... -
22
Qwen3.6-35B-A3B-FP8
FP8 Qwen model for efficient multimodal coding and agent tasks
...Built for stability and real-world developer use, it emphasizes agentic coding, repository-level reasoning, and productive long-context workflows. A key capability is thinking preservation, which allows the model to retain reasoning traces from earlier messages, helping reduce repeated computation and improving consistency in iterative tasks. The model uses a Mixture-of-Experts design with 35B total parameters and 3B active, supports a native context window of 262,144 tokens, and can be extended to about 1,010,000 tokens with YaRN. ... -
23
DeepSeek-V3.2
High-efficiency reasoning and agentic intelligence model
...DeepSeek-V3.2 also features a large-scale agentic task synthesis pipeline, which generates training data to enhance tool-use intelligence and multi-step reasoning. It introduces a new “thinking with tools” chat template, allowing it to reason and decide when to invoke specific tools during problem solving. -
24
EORS
rational agent
This project aims at creating rationally thinking agents. The agent gather information through command line or network and stores it in its memory. It uses Stanford's NLP library to understand the language statements. -
25
Kimi K2.6
Multimodal agent model for coding, orchestration, and autonomy
Kimi K2.6 is an open-source native multimodal agentic model built for advanced autonomous execution, long-horizon coding, and large-scale task orchestration. It is designed to handle complex end-to-end software workflows across multiple languages and domains, including front-end development, DevOps, performance optimization, and coding-driven design. Beyond coding, it can transform prompts and visual inputs into production-ready interfaces and lightweight full-stack outputs with structured...
