fast-agent
Fast-agent is a flexible Python infrastructure to interact with large language models and create coding assistants, development tools, assessment or workflow platforms. The Model Context Protocol (MCP) offers Agent Client Protocol (ACP) and Agent-to-Agent (A2A) support; it also provides terminal-based interactive sessions and shell support.
evalstate · AI Agent Frameworks
Common commercial products in this category: OpenAI Assistants API, Microsoft Copilot Studio, Amazon Bedrock Agents
- You can create multi-mode agents for coding, workflow management, and model evaluation.
- By connecting to MCP servers, you can manage skills and identify customized tool hooks.
- You can run models of various providers such as Anthropic, OpenAI, Google and Ollama in a local or cloud environment.
- ↑ PositiveHacker News
Show HN: Fast-agent – Compose MCP enabled Agents and Workflows in minutes
“The Messages API contains a special section for placing Tool information, which is added to the Context Window - and it's this information that the Model then uses to decide whether to attempt a Tool Call. In that case, we configure the MCP Server, and then the Host application…”
- • NeutralGitHub Issue
Google Gemini Support
“Having Gemini Support would be super helpful. Specifically 2.5 as it has larger context window.”
My note
Alternative pages
More in: AI Agent Frameworks
- deepseek-harness★ 266,838 · yesterday
- claude-mem★ 106,517 · today
- ragflow★ 93,228 · today
- ruflo★ 80,322 · today
- Prompt-Engineering-Guide★ 79,688 · 7 mo ago
- OmniRoute★ 79,041 · 10 days ago