litellm
11 servers · 91★ total
Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
Transform OpenAPI specifications into production-ready MCP servers with AI-powered evaluation and enhancement. Leverages LLMs to analyze, improve, and generate Model Context Protocol implementations from your existing API documentation.
Open-source native iOS, iPadOS & macOS LLM client for LiteLLM, Ollama and OpenAI-compatible APIs. Built with SwiftUI.
Use Codex from Claude Code, or Claude Code from Codex, through the subscriptions you already have. Multi-turn consultations between agent CLIs with no provider API key, a validated response envelope, and a local dashboard of every consultation.
MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestrator session.
MCP server built with Google’s Agent Development(ADK) Kit featuring multiple specialised agents that collaborate through intelligent routing. The system provides RESTful API endpoints for various capabilities including web searches, data analysis, and code generation while maintaining extensibility through a modular architecture
Self-hosted AI gateway: OpenAI/Anthropic-compatible APIs, virtual keys with token budgets, exact+semantic response cache, reverse MCP governance (REST→MCP), Prometheus/Langfuse observability — fake-provider-first, zero credentials to try.
Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.
A Model-Agnostic, Git-Sandboxed Multi-Agent Nexus MCP Server.
MCP routing proxy for Claude Desktop — local Ollama model switching via LiteLLM
Model-agnostic multi-agent orchestration built on CrewAI. YAML-driven agent and MCP catalogs, dynamic LLM planning, sessions, and pluggable execution — mix Ollama, OpenAI, Anthropic, HuggingFace, and your own tools without rewriting orchestration logic.