Search Results for "deepseek" - Page 3
Sort By:
Showing 82 open source projects for "deepseek"
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
tlm
Local CLI Copilot, powered by Ollama
...Instead of relying on cloud APIs or paid AI services, TLM runs entirely on the user’s workstation and integrates with local models managed through the Ollama runtime. This approach allows developers to use powerful open-source models such as Llama, Phi, DeepSeek, and Qwen while maintaining privacy and avoiding external service dependencies. The system supports contextual queries where the AI analyzes files within a directory and generates answers based on project documentation or source code. It also detects the user’s shell environment automatically, allowing it to generate commands tailored to shells such as Bash, Zsh, or PowerShell. -
2
5ire
5ire is a cross-platform desktop AI assistant, MCP client
5ire is a sleek, cross‑platform desktop AI assistant and MCP client that connects to major service providers, supports a local knowledge base and tool integration via MCP servers, enabling robust RAG and assistant features. These components are required as they constitute the runtime environment for the MCP Server. If you don't anticipate using the tools feature immediately, you may choose to skip this installation step and complete it later when the need arises. MCP is an open protocol that... -
3
Open Infra Index
Production-tested AI infrastructure tools
open-infra-index is a central “infrastructure index” repository maintained by DeepSeek AI that acts as a catalog and hub for a collection of production-tested AI infrastructure tools and internal building blocks they have open-sourced. Instead of a single monolithic codebase, it functions more like an index or launching point: linking and documenting a set of library repos (e.g. FlashMLA, DeepEP, DeepGEMM, 3FS, etc.) that together form DeepSeek’s infrastructure stack. -
4
BrowserAI
Run local LLMs like llama, deepseek, kokoro etc. inside your browser
BrowserAI is a cutting-edge platform that allows users to run large language models (LLMs) directly in their web browser without the need for a server. It leverages WebGPU for accelerated performance and supports offline functionality, making it a highly efficient and privacy-conscious solution. The platform provides a developer-friendly SDK with pre-configured popular models, and it allows for seamless switching between MLC and Transformer engines. Additionally, it supports features such as... -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
...GLM-4.6 also enhances writing quality, producing outputs that better align with human preferences and role-playing scenarios. Benchmark evaluations demonstrate that it not only outperforms GLM-4.5 but also rivals leading global models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4. -
6
magpie
One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar
Magpie is a cross-platform utility for managing which AI models local coding agents use from one interface. It detects supported tools such as Claude Code, Codex, Gemini CLI, OpenCode, Cursor CLI, Copilot CLI, and many others. Users can switch providers, models, reasoning settings, and related fields without manually editing each agent's configuration file. A local gateway translates OpenAI and Anthropic-style APIs so different agents can share one model catalog and provider setup. Existing... -
7
EmoLLM
Pre & Post-training & Dataset & Evaluation & Depoly & RAG
...The project is designed to help users through mental health conversations and has been fine-tuned from existing instruction-following LLMs rather than built as a base model from scratch. Its repository includes multiple model variants and training configurations spanning several underlying model families, including InternLM, Qwen, DeepSeek, Mixtral, LLaMA, and others, which shows that the initiative is structured as a broad ecosystem rather than a single release. The project also covers more than just model weights, with material for datasets, fine-tuning, evaluation, deployment, demos, RAG, and related subprojects such as its psychological digital assistant work. -
8
DeepReasoning
High-performance API combining reasoning and creative AI models
DeepReasoning is a high-performance large language model inference API designed to unify advanced reasoning and creative generation capabilities into a single system. It combines DeepSeek R1’s chain-of-thought reasoning with Claude’s strengths in code generation and conversational output, enabling more capable and balanced responses. DeepReasoning provides both an API and a chat interface, allowing developers and users to interact with the combined models in a streamlined way. It emphasizes real-time streaming responses, where reasoning and final answers can be delivered efficiently in a single flow. ... -
9
Chitu
High-performance inference framework for large language models
Chitu is a high-performance inference engine designed to deploy and run large language models efficiently in production environments. The framework focuses on improving efficiency, flexibility, and scalability for organizations that need to run LLM inference workloads across different hardware platforms. It supports heterogeneous computing environments, including CPUs, GPUs, and various specialized AI accelerators, allowing models to run across a wide range of infrastructure configurations.... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
Smallpond
A lightweight data processing framework built on DuckDB and 3FS
smallpond is a lightweight distributed data processing framework built by DeepSeek, designed to scale DuckDB workloads over clusters using their 3FS (Fire-Flyer File System) backend. The idea is to preserve DuckDB’s fast analytics engine but lift it from single-node to multi-node settings, giving you the ability to operate on large datasets (e.g. petabyte scale) without moving to a heavyweight system like Spark. -
11
Forge Code
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek
Forge is a modern, open-source tool that brings AI-powered code assistance directly into your terminal workflow, effectively turning your shell into a “pair programmer”, without ever leaving your development environment. Written in Rust (with a command-line interface), Forge integrates with your existing shell (bash, zsh, fish, etc.) or IDE-agnostic workflows, allowing you to interact with your codebase, command-line tools, and version control as usual, but with the added support of large... -
12
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. -
13
Crush
The glamourous AI CLI coding agent for your favourite terminal 💘
Crush is a next-generation, terminal-based AI coding assistant developed by Charm, designed to seamlessly integrate with your tools, workflows, and preferred LLMs. It provides developers with an intuitive, session-based experience where multiple contexts can be managed across projects. With flexible model switching, Crush allows you to change providers mid-session while retaining conversation history. It enhances productivity by combining LSP (Language Server Protocol) support with... -
14
claude-multi
A tool to have multiple claude-code instance with deepseek, minimax, and z.ai glm models
-
15
DeepSeek VL
Towards Real-World Vision-Language Understanding
DeepSeek-VL is DeepSeek’s initial vision-language model that anchors their multimodal stack. It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot). -
16
DeepSeek Math
Pushing the Limits of Mathematical Reasoning in Open Language Models
...The repo may also include modules that integrate external computational tools (e.g. a CAS / computer algebra system) or calculator assistance backends to enhance correctness. Because math reasoning is a high bar for LLMs, DeepSeek-Math aims to showcase their model’s ability not just in natural text but in precise formal reasoning. -
17
AI Local - Choose Models with LM Studio
TN 365 AI Ready - LM Studio & Assistant Vocal Murmure !
TN365 AI Edition est une version avancée de TN365, conçue pour offrir une expérience Linux moderne, rapide et entièrement orientée intelligence artificielle. Grâce à LM Studio préinstallé, les utilisateurs peuvent ajouter en un clic les modèles IA puissants tels que DeepSeek R1, Gemma, Llama 3.1, Qwen, Mistral, et bien d’autres. Pensée pour les créateurs, développeurs, Terminal DevOps inclus dans LM Studio, TN365 IA offre stabilité, élégance et puissance, tout en offrant une plateforme IA locale et extensible unique dans l’écosystème Linux. “Support IA local (GGUF) + IA cloud (OpenAI, DeepSeek, Mistral, Groq).” ... -
18
A community port of clMAGMA, supporting OpenCL 1.2+ devices and tuned clBLAST. This project is a future‑port of clMAGMA maintained by Prof. Jinchuan Tang (jctang@gzu.edu.cn). It works with many OpenCL 1.2+ devices and uses a tuned version of clBLAST (the maintainer and his students at GZU actively contribute to clBLAST as well). Github link: https://github.com/octaveoclx/AnyMagma
-
19
ChatbotX
A self-hosted, white-label alternative to ManyChat for agencies.
...Connect across WhatsApp, Facebook, Instagram, Telegram, Zalo, Email, and Webchat with support for rich messaging, comment-to-DM, triggers, webhooks, and external APIs. ChatbotX also supports APIs, CLI, and MCP-compatible clients for building advanced agentic workflows using OpenAI, Gemini, DeepSeek, and more. -
20
Deepin 25.2 Desktop
Deepin 25.2 — L’OS IA Moderne, Productif et Élégant
Deepin 25.2 est disponible en deux versions : x86_64 et ARM64. La version x86_64 offre une expérience fluide et moderne grâce au bureau DDE, Treeland (Wayland Deepin), Solid pour la stabilité, un App Store rapide, des animations 60 FPS et une interface premium. Elle inclut les applications essentielles, une configuration soignée et une compatibilité large avec les PC classiques. La version ARM64, destinée aux plateformes ARM64 UEFI compatibles, propose les mêmes fonctionnalités visuelles... -
21
Chat4Us-Creator
A lightweight intelligent chatbots creator platform.
...Chatbots can be created using the graphic nodes editor from basic to advanced chat flows with the ability to connect them either to local/offline LLMs using GPT4All/Ollama or external API providers like OpenAI, DeepSeek or Groq. Requires Java (JRE) 21 or higher installed. Default authentication password: a123456/* -
22
Council.
Open-source, serverless, multi-LLM group chat application
Council. is an open-source, serverless, multi-LLM group chat application designed to let you talk to multiple AI agents simultaneously. Have debates, get consensus, or collaborate with custom AI configurations. -
23
DeepSeek LLM
DeepSeek LLM: Let there be answers
The DeepSeek-LLM repository hosts the code, model files, evaluations, and documentation for DeepSeek’s LLM series (notably the 67B Chat variant). Its tagline is “Let there be answers.” The repo includes an “evaluation” folder (with results like math benchmark scores) and code artifacts (e.g. pre-commit config) that support model development and deployment. -
24
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
DeepSeek-MoE (“DeepSeek MoE”) is the DeepSeek open implementation of a Mixture-of-Experts (MoE) model architecture meant to increase parameter efficiency by activating only a subset of “expert” submodules per input. The repository introduces fine-grained expert segmentation and shared expert isolation to improve specialization while controlling compute cost. -
25
DeepSeek-V3.2
High-efficiency reasoning and agentic intelligence model
DeepSeek-V3.2 is a cutting-edge large language model developed by DeepSeek-AI, focused on achieving high reasoning accuracy and computational efficiency for agentic tasks. It introduces DeepSeek Sparse Attention (DSA), a new attention mechanism that dramatically reduces computational overhead while maintaining strong long-context performance.
