#160 · Primary category： LLM Application Frameworks
LLM-Kit
🚀WebUI integrated platform for latest LLMs, all-in-one toolkit for large language models, supporting mainstream APIs, open-source models, knowledge bases, databases, role-playing, MJ text-to-image, LoRA/full-parameter fine-tuning, dataset creation, live2d, and more.
Project last updated：11/25/25
GitHub Stars
553
Forks
62
Contributors
7
License
AGPL-3.0
Why we included this project
LLM-Kit is a WebUI that tries to cover the whole LLM toolchain in one place. You can chat with commercial model APIs or open-weight models, build a local knowledge base, and query a database from the same interface, all without writing code. It also goes beyond conversation: LoRA and full-parameter fine-tuning, dataset creation, and embedding model training are all included. A roleplay-oriented demo layer adds persona prompts, memory, TTS, and live2d avatars, which is handy if you are prototyping character-driven or interactive apps. The catch is that it is a wide integration rather than a deep tool, so plan to configure and test each module yourself before it feels polished.
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