Reach more potential users and drive product growth and revenue.
AdvertiseTools tagged with "DeepSeek"
DeepSeek Harness
Free ListingStars: 237.5KEverything is a plugin.
DeepSeek Harness (dsh) is an open-source agent harness in developer preview. Every agent capability is implemented as a composable Cordis plugin for models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI.
DeepSeek-V3
Free ListingStars: 104.5KMixture-of-Experts language model with 671B parameters
DeepSeek-V3 is a Mixture-of-Experts language model with 671B total parameters and 37B activated per token. It supports a 128K context and is available in Base and Chat variants with open weights for local deployment and API use.
OpenDesign
Free ListingStars: 98.3KThe open-source, local-first Claude Design alternative
OpenDesign is an open-source, local-first Claude Design alternative. It turns coding agents into a design engine for prototypes, landing pages, dashboards, slides, images, and video, with real files and HTML, PDF, PPTX, or MP4 export.
FreeLLMAPI
Free ListingStars: 48KOne OpenAI-compatible API for free LLM provider tiers
FreeLLMAPI routes free LLM provider tiers and custom OpenAI-compatible endpoints through one /v1 API, adding smart routing, automatic failover, encrypted keys, and a self-updating catalog.
CowAgent
Free ListingStars: 47.6KOpen-source super AI assistant and Agent Harness
Open-source AI assistant and Agent Harness that plans tasks, runs tools and skills, and grows with memory and knowledge. Supports multiple models, channels, and agents; lightweight, extensible, and installable with one line.
Open Code Review
Free ListingStars: 47.5KAI code review agent with line-level precision
Open Code Review is a battle-tested AI code review CLI combining deterministic engineering with an LLM agent for precise, line-level comments. It supports multiple model providers, private data control, and built-in multi-language rules.
SGLang
Free ListingStars: 37.2KHigh-performance LLM and multimodal model serving
SGLang is a high-performance serving framework for large language and multimodal models, designed for fast, scalable inference across diverse models and hardware.
DwarfStar
Free ListingStars: 24KLocal inference engine for DeepSeek, GLM, and Qwen
DwarfStar is a small native inference engine for running selected DeepSeek, GLM, and Qwen models on consumer hardware with Metal, CUDA, and ROCm support. It uses the project's own GGUF files and is not a general GGUF runner.
FlashMLA
Free ListingStars: 13.1KOptimized attention kernels for DeepSeek inference
FlashMLA is DeepSeek's library of optimized attention kernels for inference on NVIDIA GPUs and Huawei Ascend NPUs, including sparse and dense attention kernels with FP8 or FP4 KV cache support.
InkOS
Free ListingStars: 10.9KAI agent for novels, scripts, and interactive games
InkOS is an open-source story creation AI agent for long and short fiction, scripts, interactive games, IP content, and translation. Studio, TUI, and CLI share one workspace for settings, characters, memory, review, revision, covers, and

VidBee
Free ListingStars: 10.8KDownload videos and create searchable transcripts locally.
VidBee downloads video and audio from YouTube, TikTok, Instagram, X, and 1000+ sites, or local files. It creates searchable, timestamped transcripts on your computer, then summarizes, translates, or answers questions with your AI provider.
Jev Chat Assistant
Free ListingStars: 8.1KReads chats, judges intent, drafts replies you send
Jev Chat Assistant is an open-source chat copilot for Android, Windows, and macOS. It reads visible chats, judges intent and danger level, drafts ranked replies, and fills a chosen reply into the input box; you decide whether to send.
DeepInfer
Free ListingStars: 7.9KHigh-performance inference framework for DeepSeek models
DeepInfer is a high-performance, large-scale inference framework for DeepSeek models. This open-source release provides offline inference with optimized kernels, parallelism, scheduling, deterministic sampling, and structured outputs.
OpenAgent
Free ListingStars: 5.7KSingle-binary, self-hosted personal AI assistant
OpenAgent is a self-hostable, single-binary personal AI assistant powered by LLMs, RAG, and agent loops. It supports MCP tools, 30+ model providers, Telegram, Discord, and WeCom, with no vendor lock-in.
magpie
Free ListingStars: 3.9KEvery agent's model. One place.
magpie is a menu bar app that lets you pick the model each AI coding agent uses, routing Codex, Claude Code, Gemini CLI and others through one local gateway to providers such as DeepSeek, Kimi and GLM.
Locally Uncensored
Free ListingStars: 3KFree, open-source local AI studio for desktop
Locally Uncensored is a free, open-source desktop AI studio for chat, coding, image generation, and video generation in one app. It runs locally without Docker or a command line, and can optionally use LU Cloud.
dsh-superagent
Free ListingStars: 2.6KA proactive coding agent for one GitHub repository
Proactive coding agent for one GitHub repository, packaged for DeepSeek Harness. It listens to GitHub and optionally Feishu, opens work items, works independently, replies in the original conversation, and shows human-needed work in a web
Deep Code
Free ListingStars: 2.2KTerminal AI coding assistant optimized for DeepSeek
Deep Code is a terminal AI coding assistant optimized for deepseek-v4 models, with deep thinking, reasoning effort control, Agent Skills, and MCP integration, available as a CLI and VS Code extension.
Reason Network
Free ListingStars: 1.3KPeer-to-peer messaging for your team's coding agents
Reason Network lets a team's coding agents message each other directly, peer to peer and end-to-end encrypted, as part of the Reason AI teammate for work and code.
AnyModelBot
Free ListingStars: 1KOpen-source, local-first AI assistant on your computer
Open-source local-first AI agent app for Windows, macOS, Linux. One Modelflare key unlocks 70+ models. Bots have personas, workspaces, and memory; chat in WeChat or Feishu; they can read files, run commands, and use computers. Pay per use.
sapper-v2
Free ListingStars: 0.9KAI commander and worker swarm for autonomous pentests
sapper-v2 is an autonomous pentest legion: an AI commander coordinates general, scout, and soldier agents through a shared layered fact-intent graph, using model tiering and tmux sessions for unattended security testing campaigns.
Octomind
Free ListingStars: 0.6KPortable open-source agents that finish the job.
Octomind is an open-source AI coding agent and agent runtime: one binary, any model, MCP-native. It runs in the terminal, CI, or as a daemon, with portable agents defined in TOML and policy in guardrails.

