swarms-tools and swarms-client
These are ecosystem siblings where swarms-tools provides the functional building blocks (pre-built tools and MCP servers) that agents created through the swarms-client API would integrate and utilize.
About swarms-tools
The-Swarm-Corporation/swarms-tools
Swarms Tools provides a vast array of pre-built tools for your agents, MCP servers, and multi-agent systems.
Based on the README, here's a technical summary: Organizes domain-specific tools (finance APIs like HTX and CoinGecko, social media integrations, web scraping, code execution) with standardized schemas and type hints for seamless agent integration. The `tool_chainer` framework enables sequential or parallel orchestration of multiple tools, with performance optimized through async HTTP via `httpx` and fast JSON serialization with `orjson`. Designed as a plugin ecosystem for the Swarms multi-agent orchestration platform, supporting MCP servers with enterprise security patterns for API key management.
About swarms-client
The-Swarm-Corporation/swarms-client
A production-grade Python client for the Swarms API, providing a simple and intuitive interface for creating and managing AI swarms.
Provides both synchronous and asynchronous HTTP clients via httpx and optional aiohttp backend, with full type safety through TypedDict request parameters and Pydantic response models. Supports orchestrating multi-agent workflows using configurable swarm types (e.g., ConcurrentWorkflow) where agents with different models and system prompts collaborate on tasks. Includes helper methods for model discovery, health checks, rate limit monitoring, and automatic retry logic with exponential backoff for transient failures.
Scores updated daily from GitHub, PyPI, and npm data. How scores work