fast-agent and mcp-agent
About fast-agent
evalstate/fast-agent
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support
Supports multiple LLM providers (Anthropic, OpenAI, Google, Azure, Ollama, Deepseek) with native MCP server integration via stdio and HTTP transports, plus structured outputs, vision, and PDF capabilities. CLI-first architecture with prompt_toolkit TUI, live streaming responses, and diagnostic tools for inspecting MCP transport behavior. Enables declarative agent composition through simple Python decorators and YAML configs, with built-in skills registry, shell mode, and ACP client compatibility for embedding agents into other applications.
About mcp-agent
lastmile-ai/mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
Fully implements MCP with automatic lifecycle management of server connections, and provides composable agent patterns (map-reduce, orchestrator, evaluator-optimizer, router) based on Anthropic's best practices. Scales from simple agents to production workflows via Temporal integration without API changes, enabling pause/resume/recovery capabilities. Supports the complete MCP specification including tools, resources, prompts, notifications, OAuth, and sampling.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work