Search Results for "reasoning" - Page 7
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.
-
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.
-
1
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. The repository provides model code and inference scripts that let researchers and developers run and benchmark the system on both images and PDFs, with support for batch evaluation and optimized pipelines leveraging vLLM and transformers. -
2
macai
All-in-one native macOS AI chat application
...The app supports a wide range of providers, including OpenAI, Anthropic, Google Gemini, xAI, Perplexity, and Ollama, allowing users to switch between local and cloud-based models without changing tools. It includes advanced features such as multimodal capabilities, image generation, search integration, and reasoning workflows, making it more than just a simple chat client. The application also emphasizes privacy by avoiding telemetry and offering optional iCloud synchronization for cross-device continuity. With its combination of native performance, multi-provider flexibility, and user-friendly design, macai serves as a comprehensive AI hub for macOS users. -
3
AppAgent
Multimodal Agents as Smartphone Users, an LLM-based multimodal agent
...Instead of requiring backend access to application APIs, the framework interacts with apps the same way a human user would, making it compatible with a wide variety of mobile applications. AppAgent combines vision capabilities with language reasoning to understand interface elements and determine which actions are required to accomplish a task. The system also includes mechanisms for exploration and learning, allowing the agent to analyze user interface layouts and build structured knowledge about how different apps function. -
4
Qwen3 Embedding
Designed for text embedding and ranking tasks
...It builds upon the Qwen3 base/dense models and offers several sizes (0.6B, 4B, 8B parameters), for both embedding and reranking, with high multilingual capability, long‐context understanding, and reasoning. It achieves state-of-the-art performance on benchmarks like MTEB (Multilingual Text Embedding Benchmark) and supports instruction-aware embedding (i.e. embedding task instructions along with queries) and flexible embedding/vector dimension definitions. It is meant for tasks such as text retrieval, classification, clustering, bitext mining, and code retrieval. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
Claude BugHunter
A Claude Code skill bundle for bug hunting
...It packages a large collection of specialized skills, slash commands, and disclosed-report patterns so Claude Code can reason through common vulnerability classes more systematically. The project is meant to help authorized testers structure reconnaissance, triage, hypothesis building, exploitation reasoning, and reporting. It includes curated patterns from public vulnerability reports, making it useful as a learning and workflow reference. Because it supports security testing, it should only be used on systems where the user has permission to test. Its strongest value is turning scattered bug bounty knowledge into reusable Claude Code workflows. -
6
yourself-skill
Instead of distilling others, it is better to distil yourself
...It encourages systems to maintain awareness of user preferences, goals, and communication styles. The project emphasizes building more human-aligned interactions by incorporating memory and contextual reasoning. It can be integrated into broader AI systems to improve personalization and continuity across sessions. The design focuses on enhancing user experience through adaptive responses. It is particularly useful for conversational agents and assistants. Overall, it contributes to more context-aware and user-centered AI systems. -
7
Book4_Power-of-Matrix
Book_4_Matrix Power | The Iris Book: From Addition, Subtraction
...It combines explanatory text, diagrams, and Python examples to bridge theory and practical computation. The material emphasizes geometric interpretation and visual reasoning, which makes abstract linear algebra topics more accessible to beginners and self-learners. The repository is continuously updated and intended to accompany the broader Visualize-ML learning ecosystem. Overall, it serves as a visually driven mathematical foundation for students preparing for data science and machine learning work. -
8
Claude Code Plugins
Intelligent automation and multi-agent orchestration for Claude Code
Claude Code Plugins is a lightweight framework designed to define, manage, and execute AI agents in a modular and extensible way, typically focusing on orchestrating tasks using large language models and tool integrations. The project provides abstractions for building agents that can interpret instructions, execute commands, and interact with external systems in a structured workflow. It emphasizes simplicity and composability, allowing developers to define agent behaviors through reusable... -
9
Natural Language Toolkit
NLTK Source
...The toolkit includes implementations of many foundational NLP algorithms and utilities, enabling developers to perform tasks such as tokenization, stemming, parsing, classification, and semantic reasoning. NLTK was originally developed to support research and teaching in computational linguistics and artificial intelligence, and it has become one of the most influential educational platforms for learning NLP in Python. The project also includes access to numerous linguistic corpora and lexical resources that can be downloaded and used directly in experiments and applications. -
$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.
-
10
HuixiangDou
Overcoming Group Chat Scenarios with LLM-based Technical Assistance
...This design allows the system to participate in group discussions without flooding the chat with unnecessary messages. The assistant uses retrieval and ranking methods along with language model reasoning to produce accurate answers for technical topics such as computer vision and machine learning projects. It can be integrated into messaging platforms such as WeChat or other team collaboration tools to assist developer communities. -
11
Agent SOP
Natural language workflows for AI agents
Agent SOP is a framework that implements structured operational procedures (SOPs) for autonomous agents so that they can carry out complex multi-step tasks reliably and in a defined order. Instead of relying solely on broad language model reasoning, this project enforces explicit step sequences with checkpoints, conditional transitions, and rollback logic, making agent workflows more predictable and auditable. It defines reusable SOP templates that agents can instantiate with context-specific parameters, allowing organizations to codify best practices for customer support, data processing, document workflows, or incident response. ... -
12
AI Agents Masterclass
Follow along with my AI Agents Masterclass videos
...The project includes structured lessons, code examples, and practical exercises that cover foundational concepts like prompt engineering, chaining agents, tool usage, plan execution, evaluation, and safety considerations. It breaks down how autonomous agents interact with external systems, handle iterative reasoning, and integrate with third-party services or APIs to perform real tasks — for example, web search, browsing, scheduling, or coding assistance. Students of the masterclass can follow written modules or Jupyter notebooks that illustrate concepts step by step and progressively build more capable agents. The content is suitable for both beginners and intermediate developers because it starts with basic principles and escalates to advanced architectures like multi-agent coordination. -
13
Tencent-Hunyuan-Large
Open-source large language model family from Tencent Hunyuan
Tencent-Hunyuan-Large is the flagship open-source large language model family from Tencent Hunyuan, offering both pre-trained and instruct (fine-tuned) variants. It is designed with long-context capabilities, quantization support, and high performance on benchmarks across general reasoning, mathematics, language understanding, and Chinese / multilingual tasks. It aims to provide competitive capability with efficient deployment and inference. FP8 quantization support to reduce memory usage (~50%) while maintaining precision. High benchmarking performance on tasks like MMLU, MATH, CMMLU, C-Eval, etc. -
14
Think Bayes 2
Text and code for the second edition of Think Bayes, by Allen Downey
Think Bayes 2 is the companion repository for the second edition of Allen B. Downey’s introduction to Bayesian statistics. It teaches Bayesian reasoning through computational methods instead of relying mainly on symbolic mathematics. Each chapter is presented as a Jupyter notebook where readers can study the text, run examples, and complete exercises. Separate solution materials help learners check their work and explore alternative approaches. The lessons cover probability distributions, Bayesian updating, estimation, prediction, comparison, and decision-making. ... -
15
ThinkStats2
Text and supporting code for Think Stats, 2nd Edition
ThinkStats2 is the code and text companion for the second edition of Think Stats, an introduction to statistics and data science for Python programmers. It teaches probability and statistical reasoning through short programs, experiments, and analysis of real datasets. The material emphasizes exploratory methods that help readers ask and answer practical questions with data. Case studies draw from public sources, including health-related datasets, to connect abstract concepts with realistic analysis. Each chapter has a notebook containing examples and exercises, along with a separate version that includes solutions. ... -
16
Make It heavy
A Python framework that emulates Grok Heavy functionality
...The framework uses OpenRouter for model access and can also run in single-agent mode for simpler tasks. Overall, it is useful for users who want broader research coverage, richer reasoning diversity, and structured multi-agent responses from one command-line workflow. -
17
Clawith
OpenClaw for Teams
...It is designed to function as a control layer where agents can perform actions, manage workflows, and respond dynamically to changing conditions. The system likely emphasizes integration with external tools and services, allowing agents to extend their capabilities beyond internal reasoning. Its architecture suggests support for multi-agent collaboration, enabling distributed problem-solving and task delegation. It may also include monitoring and control features to ensure that agent behavior remains aligned with user goals. The project reflects a broader trend toward building AI systems that act as autonomous operators rather than passive assistants. ... -
18
MemMachine
Universal memory layer for AI Agents
...Unlike ephemeral LLM prompt state, MemMachine supports distinct memory types—short-term conversational context, long-term persistent knowledge, and profile memory for personalized facts—persisted in optimized stores (e.g., graph databases for episodic lines of reasoning and SQL for user facts) to support robust, context-aware intelligence in agents. It offers flexible APIs, a Python SDK, REST interfaces, and MCP (Model Context Protocol) connectivity to integrate seamlessly with agent frameworks receiving and storing memories over time, effectively boosting relevance, continuity, and tailored behavior. -
19
Portia SDK Python
Portia Labs Python SDK for building agentic workflows
portia‑sdk‑python is an open-source Python SDK by Portia Labs for creating reliable, stateful, authenticated multi-agent AI workflows. It supports tool-backed agents capable of real-world interactions—like web browsing, API access, and human-in-the-loop clarifications—while maintaining transparency and auditability through structured plans and execution hooks. Designed for production environments, the SDK integrates with local or cloud LLMs (e.g. OpenAI, Anthropic, Mistral, Gemini) and... -
20
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. -
21
Agentex
Open source codebase for Scale Agentex
...The repo focuses on structured experiments: standardized tasks, canonical tool interfaces, and logs that make it possible to compare models, prompts, and tool sets fairly. It also includes evaluation harnesses that capture success criteria and partial credit, plus traces you can inspect to understand where reasoning or tool use failed. The design encourages clean separation between experiment configuration and code, which makes sharing results or re-running baselines straightforward. Teams use it to progress from prototypes to production-ready agent behaviors by iterating on prompts, adding tools, and validating improvements with consistent metrics. -
22
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
CogVLM2 is the second generation of the CogVLM vision-language model series, developed by ZhipuAI and released in 2024. Built on Meta-Llama-3-8B-Instruct, CogVLM2 significantly improves over its predecessor by providing stronger performance across multimodal benchmarks such as TextVQA, DocVQA, and ChartQA, while introducing extended context length support of up to 8K tokens and high-resolution image input up to 1344×1344. The series includes models for both image understanding and video... -
23
MemPalace
The highest-scoring AI memory system ever benchmarked
...It operates fully locally using tools like ChromaDB, meaning it requires no API keys, cloud services, or external dependencies once installed. MemPalace emphasizes fidelity over compression, preserving full conversational history to maintain reasoning, nuance, and decision-making context that is typically lost in other systems. -
24
DeepAnalyze
Autonomous LLM agent for end-to-end data science workflows
...DeepAnalyze is capable of conducting open-ended data research across multiple data formats such as structured tables, semi-structured files, and unstructured text, enabling flexible and comprehensive analysis workflows. It integrates execution-based reasoning by generating and running code as part of its analysis process, allowing it to iteratively refine results and produce more accurate outputs. DeepAnalyze provides multiple interaction interfaces, including a web-based UI, a command-line interface, and a Jupyter-style notebook environment for interactive workflows. -
25
Agent Behavior Monitoring
The open source post-building layer for agents
Agent Behavior Monitoring is an open-source framework designed to monitor, evaluate, and improve the behavior of AI agents operating in real or simulated environments. The system focuses on agent behavior monitoring by collecting interaction data and analyzing how agents perform across different scenarios and tasks. Developers can use the framework to observe agent actions in both online production environments and offline evaluation settings, making it useful for debugging and performance...