ai-agent

DeepSeek-V3

104,434 stars16,743 forksPythonUpdated 8/28/2025100% free · open source
What it does

Runs the open‑source DeepSeek‑V3 large language model locally for text generation or chat‑style completion.

When to use it
  • You need a powerful LLM but want to keep data on‑premise (e.g., for privacy‑sensitive SaaS).
  • You want to fine‑tune or prompt‑engineer a 7B‑parameter model without paying for API calls.
  • You are building a prototype chatbot and need a fast, locally hosted inference endpoint.
Ready-to-paste prompt
curl -X POST http://localhost:8000/generate -H "Content-Type: application/json" -d '{"prompt": "Write a concise investor email that pitches a AI‑driven customer support platform.", "temperature": 0.7, "max_new_tokens": 200}'
Heads up: DeepSeek‑V3 requires a GPU with at least 24 GB VRAM (or 2× A100 40 GB); attempting to run on CPU will fail or be extremely slow.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/deepseek-v3 && curl -fsSL https://workflowstacks.com/api/skills/deepseek-v3/claude-skill -o ~/.claude/skills/deepseek-v3/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How DeepSeek-V3 works
Codeflow
Free to inspect

DeepSeek-V3 is a small Python project (~1.5k lines across 5 code files). Setup is light: small project — see the README for how to run it. Last commit 12 months ago, MIT license, no tests found.

Size
Small codebase
~1.5k lines · 5 code files · 13 min skim
Setup
Light setup
Small project — see the README for how to run it.
Runs on
Python
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
What's in each folder
inference/Folder10 files
figures/Folder2 files
.github/CI / automation (GitHub Actions)3 files
READMENo tests foundDocumentedCI checksMIT licenseLast update 12 mo ago
Quick Actions
Details
Creator
deepseek-ai
Language
Python
Category
ai-agent
Published
12/26/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.