RailtownAI/railtracks
An agentic framework that helps developers build resilient agentic systems
Defines agent behavior, tools, and multi-step workflows entirely in standard Python without DSLs or YAML, leveraging native control flow for execution logic. Automatically converts decorated functions into LLM tools and supports MCP protocol integration. Includes a local observability visualizer for inspecting agent runs and integrates with OpenAI, Anthropic, Google, Azure, and local models through a unified interface.
111 stars. Used by 1 other package. Available on PyPI.
Stars
111
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
6
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/RailtownAI/railtracks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with...
i-am-bee/beeai-framework
Build production-ready AI agents in both Python and Typescript.
fetchai/uAgents
A fast and lightweight framework for creating decentralized agents with ease.
agentuniverse-ai/agentUniverse
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent...
cognizant-ai-lab/neuro-san
Neuro AI System of Agent Networks