Search Results for "thinking"
Sort By:
Showing 184 open source projects for "thinking"
View related business solutions-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
1
Computational Thinking
Introduction to computational thinking with Julia
Computational Thinking is an open source MIT course repository that teaches computational problem-solving through the Julia programming language. The course integrates mathematics, computing, and real-world applications into a unified curriculum, making it suitable for students across science, engineering, and data-driven fields. It emphasizes learning how to translate problems into computational terms and developing algorithms and models to analyze them effectively. -
2
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
...The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. GLM-4.5 achieves strong performance on 12 industry-standard benchmarks, ranking 3rd overall, while GLM-4.5-Air balances competitive results with greater efficiency. ... -
3
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
...GLM-4.5V builds on the flagship GLM-4.5-Air foundation (106B parameters, 12B active), achieving state-of-the-art results on 42 benchmarks across image, video, document, GUI, and grounding tasks. It introduces hybrid training for broad-spectrum reasoning and a Thinking Mode switch to balance speed and depth of reasoning. GLM-4.1V-9B-Thinking incorporates reinforcement learning with curriculum sampling (RLCS) and Chain-of-Thought reasoning, outperforming models much larger in scale (e.g., Qwen-2.5-VL-72B) across many benchmarks. -
4
GLM-4.7
Advanced language and coding AI model
...It delivers significant gains over GLM-4.6 in multilingual agentic coding, terminal-based workflows, and real-world developer benchmarks such as SWE-bench and Terminal Bench 2.0. The model introduces stronger “thinking before acting” behavior, improving stability and accuracy in complex agent frameworks like Claude Code, Cline, and Roo Code. GLM-4.7 also advances “vibe coding,” producing cleaner, more modern UIs, better-structured webpages, and visually improved slide layouts. Its tool-use capabilities are substantially enhanced, with notable improvements in browsing, search, and tool-integrated reasoning tasks. ... -
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
5
Weekly
Front-end intensive reading weekly
...Combining cutting-edge technology and source code interpretation with the work experience of large factories. Gradually add some back-end technical interpretations. Some business thinking. The two basic modules of compilation principle and design pattern have been completed. -
6
SocratiCode
Enterprise-grade (40m+ LOC) codebase intelligence
SocratiCode is an AI-assisted learning tool that applies the Socratic method to programming education, guiding users through problem-solving rather than directly providing answers. It encourages critical thinking by asking structured questions that lead developers toward discovering solutions on their own. The system is designed to improve understanding of programming concepts through iterative reasoning and dialogue. It can be used to practice coding challenges, debug logic, and explore design decisions in a guided manner. SocratiCode emphasizes learning through inquiry rather than passive consumption of solutions. ... -
7
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,... -
8
SuperPrompt
Experimental prompt framework exploring reasoning structures in AI
...It explores structured prompt engineering techniques that combine symbolic expressions, logical constructs, and conceptual frameworks to guide large language models toward deeper reasoning processes. Its main concept revolves around a highly structured prompt format that includes tagged sections for reasoning, analysis, conceptual expansion, and recursive thinking patterns. These sections act as a kind of meta-instruction system intended to influence how an AI model approaches problem solving and conceptual exploration. SuperPrompt also incorporates ideas from mathematics, recursion, abstract algebra, and theoretical reasoning to encourage models to perform multi-step conceptual synthesis rather than simple direct responses. -
9
Kimi K2.5
Moonshot's most powerful AI model
...Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. ... -
$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.
-
10
Ars Contexta
Claude Code plugin that generates individualized knowledge systems
...The system emphasizes long-term knowledge retention by structuring information into reusable and evolving documents rather than ephemeral chat logs. It allows users to define their thinking style and workflows, which the system uses to tailor how knowledge is captured and organized. Arscontexta integrates directly into coding workflows, making it particularly useful for developers who want to accumulate insights over time. The resulting knowledge base can be reused across sessions, improving productivity and reducing repeated explanations. -
11
Sidecar for Laravel
Deploy and execute AWS Lambda functions from your Laravel application
Sidecar packages deploy and execute AWS Lambda functions from your Laravel application. AWS Lambda is a powerful service that allows you to run code without provisioning or thinking about servers. Laravel Vapor brought that power to Laravel. Using Vapor, you can run your plain ol' Laravel apps on a serverless platform and get incredible speed, security, and reliability. Using Lambda through Vapor is a wonderful developer experience, but there are times when building your applications when you need to run just one or two Node functions for some reason. ... -
12
Flashpoint Launcher
Launcher for Flashpoint Archive
The launcher for Flashpoint Archive (the non-profit web preservation project). The Flashpoint Launcher (FPL) is a desktop application made for browsing, storing, and launching other applications (games, animations, web apps etc.). It is specifically made for Flashpoint Archive, a non-profit with the goal of furthering archival and accessibility efforts for games, animations and other digital interactive experiences on the web. -
13
DeepSeek V4
Description of the special control instructions for DeepSeek-V4
DeepSeek V4 is a documentation-focused repository that explains how to guide DeepSeek V4 roleplay behavior through special first-message instructions. Rather than providing a conventional application, it acts as a practical prompt-control reference for users who want to influence the model’s thinking-mode style during roleplay sessions. It describes three operating styles: default behavior, role immersion, and pure analysis. Role immersion encourages character-like internal framing, while pure analysis pushes the model toward structured scene planning without dramatic inner monologue. The guide explains how to apply the instructions in the web client and how developers can append the markers programmatically when calling supported DeepSeek V4 API models. ... -
14
IQuest-Coder-V1 Model Family
New family of code large language models (LLMs)
...They support native long contexts up to 128K tokens, enabling them to reason across large codebases and multi-file interactions without context fragmentation, and include “Thinking” variants optimized for complex reasoning and “Loop” variants with recurrent mechanisms to improve inference efficiency. IQuest-Coder-V1 delivers state-of-the-art performance on multiple coding benchmarks, demonstrating strong results in competitive programming, tool use, and agentic code generation. -
15
Mini Agent
A minimal yet professional single agent demo project
...It is designed both as a reference implementation and as a usable agent, demonstrating a full execution loop that includes planning, tool calls, and iterative refinement. The project exposes an Anthropic-compatible API interface and fully supports interleaved thinking, letting the agent alternate between reasoning steps and tool invocations during long, complex tasks. It includes a basic toolset for file-system operations and shell commands, plus integrations with MCP tools such as web search and knowledge graph access. Mini-Agent also comes with “Claude Skills”-style predefined skills for tasks like document processing, design work, and testing, packaged as reusable behaviors that can be invoked by the agent as needed. -
16
Dnote
A simple command line notebook
...It is designed around fast, distraction-free workflows that let users jot down notes quickly from the terminal or a web interface, ensuring that insights and solutions are captured at the moment they occur. With structured tagging and hierarchical organization, Dnote encourages users to categorize entries in ways that align with their own thinking rather than forcing a rigid notebook structure. Its search is optimized to handle large collections of notes, allowing users to find relevant information instantly, which makes it especially helpful for developers, engineers, and power users who accumulate practical knowledge over time. -
17
DoWhy
DoWhy is a Python library for causal inference
...DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks. Much like machine learning libraries have done for prediction, DoWhy is a Python library that aims to spark causal thinking and analysis. DoWhy provides a wide variety of algorithms for effect estimation, causal structure learning, diagnosis of causal structures, root cause analysis, interventions and counterfactuals. DoWhy builds on two of the most powerful frameworks for causal inference: graphical causal models and potential outcomes. For effect estimation, it uses graph-based criteria and do-calculus for modeling assumptions and identifying a non-parametric causal effect. ... -
18
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. ... -
19
gstack
Use Garry Tan's exact Claude Code setup: 15 opinionated tools
...The system includes a set of curated tools that simulate roles like CEO, engineering manager, designer, and QA engineer, allowing developers to orchestrate complex development cycles more efficiently. It emphasizes structured thinking and process discipline, encouraging users to follow consistent workflows rather than ad hoc development practices. gstack integrates browsing, planning, reviewing, and shipping functionalities into a cohesive system, making it particularly useful for teams or individuals building products with AI assistance. -
20
tw93.fun
This is Tw93's front-end technology blog
This is Tw93's front-end technology blog. Commonly used to record learning and research front-end technology. Concerned about new technology and new thinking. The blog theme named cosy-jekyll-theme is created by Tw93. -
21
AdminSet
AdminSet for DevOps
Adminset is developed based on the DevOps concept and takes the integration of all operation and maintenance scenarios as its own responsibility. Adminset is a fully automated operation and maintenance platform developed based on operation and maintenance thinking. All functions of the client need to configure the ssh password-free login from the server to the client. -
22
Draper
Decorators/view-models for Rails applications
...In the controller, you decorate the article before handing it off to the view. In the view, you can use the decorator in exactly the same way as you would have used the model. But whenever you start needing logic in the view or start thinking about a helper method, you can implement a method on the decorator instead. -
23
Meilisearch
An open-source, lightning-fast, and hyper-relevant search engine
...Send data to Meilisearch however you want, no need to match a schema or convert your dataset to a compatible format. Everyone makes mistakes! If typos break your search experience, many users will leave thinking what they were looking for just wasn't there. Start searching through your dataset in less than 5 minutes and quickly connect your codebase to Meilisearch with our official libraries. Meilisearch is designed to work out-of-the-box, no configuration needed. -
24
spleen
Monospaced bitmap fonts
...Patrick Wildt (patrick@) recently imported ssdfb(4), a driver for small OLED displays in OpenBSD and needed a 5x8 font to be able to squeeze more columns and rows on those devices. As someone spending most of his time in a terminal, I have been thinking about drawing my own font for a while, and this was the perfect opportunity. To be able to test character spacing and alignment, I started to use the font in xterm, then a zoomed version, and one thing leading to another, I started creating a 8x16 version, and then bigger versions based on it. Spleen is now available in 5 sizes: 5x8, 8x16, 12x24, 16x32, and 32x64. ... -
25
Academic Research Skills for Claude Code
Academic Research Skills for Claude Code
Academic Research Skills is a structured learning repository aimed at improving users’ ability to conduct rigorous academic research, particularly in technical and scientific domains. It compiles methodologies, frameworks, and best practices for literature review, critical analysis, and research writing. The project is designed as a self-guided resource, helping learners understand how to evaluate sources, synthesize information, and develop strong arguments. It likely integrates examples,...
