#40 · Primary category： LLM Application Frameworks
LangGPT
A structured, reusable prompt design framework enabling anyone to create high-quality prompts for large language models through modular templates and meta-prompting.
Project last updated：07/16/26
GitHub Stars
12.5K
Forks
945
Contributors
8
License
Apache-2.0
Why we included this project
Most people learn prompt engineering by guessing, tweaking, and hoping the next try works. LangGPT gives that process a structure: instead of one-off instructions, you design prompts from a reusable template with roles, variables, and modular blocks, much like writing code. The repository bundles practical examples and a documented methodology for everything from chat assistants to coding tasks on the major models, and since many of those models already internalize this style, prompts written in it tend to be understood with less friction. That makes it a solid reference for developers and non-engineers alike who want prompts that are easier to maintain, version, and adapt.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform