🔓Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock…
// mcp-serversBerriAI/⟨Python⟩★ 59,677◷ NOASSERTION[ claude ]
Projects tagged #langchain
// langchain (16)
🔓
🔓🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
// uncategorized1Panel-dev/⟨Python⟩★ 22,909◷ GPL-3.0[ claude ]
🔓[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
// mcp-serversStarTrail-org/⟨Python⟩★ 13,006◷ MIT[ claude ]
🔓A Unified Virtual Filesystem For AI Agents
// automationstrukto-ai/⟨TypeScript⟩★ 3,667◷ Apache-2.0[ claude ]
🔓FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-p…
// uncategorizedFireRedTeam/⟨Python⟩★ 3,455◷ Apache-2.0[ claude ]
🔓
🔓✨ AI-powered markdown editor - leverage LLMs with your documents - 100% local or in the cloud
// ragfynnfluegge/⟨TypeScript⟩★ 1,498◷ Apache-2.0[ claude ]
🔓Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.
// otherbrainlid/⟨Elixir⟩★ 1,201◷ NOASSERTION[ claude ]
🔓Ship RAG based LLM web apps in seconds.
// uncategorizedfcakyon/⟨Python⟩★ 1,004◷ AGPL-3.0[ claude ]
🔓Ship RAG based LLM web apps in seconds.
// educationviddexa/⟨Python⟩★ 1,005◷ AGPL-3.0[ claude ]
🔓AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 Ela…
// mcp-serversShy2593666979/⟨Python⟩★ 907◷ MIT[ claude ]
🔓Python API client for AI providers that intends to replace LangChain and LangGraph for most common use cases.
// frameworkskennethreitz/⟨Python⟩★ 537◷ Apache-2.0[ claude ]
🔓CoexistAI is a modular, developer-friendly research assistant framework . It enables you to build, search, summarize, and automate research workflows using L…
// mcp-serversSPThole/⟨Jupyter Notebook⟩★ 529◷ NOASSERTION[ claude ]
🔓Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability.
// devtoolsWritesonic/⟨TypeScript⟩★ 454◷ MIT[ claude ]
🔓
🔓Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…
// ragiKislay/⟨Python⟩★ 20◷ Apache-2.0[ claude ]