fast-agent
A flexible LLM interaction tool supporting multiple models and skills.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 3.8k
- Source
- mcp-github
- Repository
- github.com/evalstate/fast-agent
Overview
fast-agent is a versatile LLM interaction tool suitable for coding agents, development toolkits, evaluation, or workflow platforms. It supports various models and skills, can connect via MCP servers, and offers rich features such as code generation and automation. Users can quickly start and configure it through a simple command-line interface, making it ideal for developers and researchers.
Capabilities
- ▪Multi-model support
- ▪MCP server connection
- ▪Skill management
- ▪Automated workflows
- ▪Real-time response
Use cases
Setup
uv pip install fast-agent-mcp
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with fast-agent?
After installing the uv package manager, run `uv pip install fast-agent-mcp` and start an interactive session.
Which models are supported?
Supports multiple models including Anthropic, OpenAI, Google, and more.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.