LLM Application Frameworks
Frameworks for building LLM applications — LangChain-class tooling.
148 projects
See methodology for ranking rules; order uses public GitHub metrics within this scenario.
| Rank | Project | Stars | Forks | Updated | License |
|---|---|---|---|---|---|
| 1 |
langchain
The agent engineering platform. |
145.2K | 24.2K | 08/29/26 | MIT |
| 2 |
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. |
153.8K | 24.3K | 08/29/26 | Other |
| 3 |
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. |
68.0K | 5.3K | 08/29/26 | Apache-2.0 |
| 4 |
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] |
57.6K | 11.0K | 08/29/26 | Other |
| 5 |
llama_index
LlamaIndex is the leading document agent and OCR platform |
51.9K | 8.1K | 08/29/26 | MIT |
| 6 |
pathway
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG. |
62.4K | 1.7K | 08/29/26 | Other |
| 7 |
private-gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server. |
57.5K | 7.6K | 08/28/26 | Apache-2.0 |
| 8 |
new-api
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. |
46.7K | 11.1K | 08/29/26 | AGPL-3.0 |
| 9 |
Fabric
Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere. |
43.6K | 4.2K | 08/29/26 | MIT |
| 10 |
langgraph
Build resilient agents. |
40.7K | 6.9K | 08/28/26 | MIT |
| 11 |
langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. |
38.5K | 2.7K | 08/27/26 | Apache-2.0 |
| 12 |
prompt-optimizer
An AI prompt optimizer for writing better prompts and getting better AI results. |
33.7K | 3.9K | 08/26/26 | Other |
| 13 |
mastra
Mastra is the modern TypeScript framework for AI-powered applications and agents. |
27.6K | 2.7K | 08/29/26 | Other |
| 14 |
semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps |
28.5K | 4.7K | 08/27/26 | MIT |
| 15 |
ai
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents |
26.5K | 5.0K | 08/29/26 | Other |
| 16 |
fastmcp
🚀 The fast, Pythonic way to build MCP servers and clients. |
27.4K | 2.3K | 08/29/26 | Apache-2.0 |
| 17 |
haystack
Open-source AI orchestration framework for building production-ready LLM applications with modular pipelines, agent workflows, and explicit control over retrieval, routing, memory, and generation. |
26.4K | 3.0K | 08/29/26 | Apache-2.0 |
| 18 |
toon
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks. |
25.3K | 1.1K | 08/23/26 | MIT |
| 19 |
langchainjs
The agent engineering platform |
18.1K | 3.3K | 08/28/26 | MIT |
| 20 |
pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. |
19.6K | 2.6K | 08/29/26 | MIT |