mudler/LocalAI
LocalAI is an open-source AI engine that enables running various AI models (LLMs, vision, voice, image, video) on any hardware, including CPU-only systems, with a composable and extensible architec...
Awesome AI Agents › LLM Framework Tools
mcpdotdirect/evm-mcp-server
The EVM MCP Server is a comprehensive Model Context Protocol (MCP) server designed to provide blockchain services across more than 30 EVM-compatible networks. It enables AI agents to interact seamlessly with various Ethereum Virtual Machine (EVM) chains such as Ethereum, Optimism, Arbitrum, Base, Polygon, and many others through a unified interface. The server supports a wide range of blockchain functionalities including reading blockchain state data like balances, transactions, and blocks, interacting with smart contracts, transferring tokens (native tokens, ERC20, ERC721, ERC1155), and querying token metadata and balances. One of the standout features is its support for ENS (Ethereum Name Service) name resolution, allowing users to use human-readable names instead of raw Ethereum addresses. The server exposes all its services through a consistent set of MCP tools and resources, making it easy for AI agents to discover and utilize blockchain functionalities. It supports multi-chain operations with detailed chain information, block data access, transaction details with decoded logs, and comprehensive token services. For ERC20 tokens, it provides metadata retrieval, balance checks, transfers, and spending approvals. For NFTs (ERC721), it offers collection and token metadata, ownership verification, transfers, and token URI retrieval. For multi-tokens (ERC1155), it supports balance checks, metadata access, transfers with quantity, and URI access. Smart contract interactions are well-supported, including reading contract state via view/pure functions, writing with private key signing, contract verification, and event log retrieval. The server also supports native token transfers, gas estimation, transaction status tracking, and detailed error handling. The server supports a wide array of mainnet and testnet EVM-compatible networks, making it highly versatile for blockchain development and AI integration. It can be run locally or via npx without installation, and it integrates smoothly with MCP-compatible clients like Cursor. The project is built with TypeScript and uses Bun or Node.js as runtime environments. It is open-source under the MIT license, making it accessible for developers to use and contribute to.
https://github.com/mcpdotdirect/evm-mcp-server
Also in LLM Framework Tools
langfuse/langfuse
Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.
567-labs/instructor
Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.
TEN-framework/ten-framework
TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.
google/adk-samples
A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.
truefoundry/cognita
Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.
lemony-ai/cascadeflow
In-process Python and TypeScript library that cascades model calls inside the agent loop, routing each query or tool call between small and flagship models by quality, cost, latency and budget.
shroominic/codeinterpreter-api
An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.