Tool Calling Python Packages

langchain-mcp-tools

MCP to LangChain Tools Conversion Utility / Python

pydeno

Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as the only way out.

scalekit-sdk-python

Python SDK for Scalekit — auth stack for agents. SAML, OIDC, SCIM, MCP Auth, agent auth, tool-calling.

rapid-mlx

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

ctrlrun

The execution safety layer for AI agents.

ratel-ai

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

roboz

Python framework for typed LLM agents with conditional tool chaining.

protocore

Protocore — the agent loop, and nothing else. A protocol-first ReAct runtime for LLM agents in Python 3.12+: context budget, tool surface, compaction, snapshot and resume. No database driver, no HTTP endpoint — everything outward is a Protocol you implement. MPL-2.0.

agent-friend

Find the MCP schema issues eating your context window. 156 checks. Grade A+ through F. ESLint for MCP.

llm-rosetta

Production-ready LLM API translation layer — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome!

vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

factory-droid-openai

Unofficial OpenAI-compatible bridge for Factory Droid

zett-agent

A small, simple Python runtime for LLM agents. One provider-neutral loop loads tools and skills on demand (JIT) instead of up front, streamed step by step, with sessions, compaction, subagents, and composable extensions.

omnicache-proxy

⚡ Zero-latency semantic caching, agent loop accelerator & cost optimization gateway for LLMs. Slash OpenAI & Anthropic bills by 40%-75%.

opendsstar

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.

chp-core

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

massgen

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

lightagent

LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

toolregistry

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs (OpenAI, Anthropic, Gemini, LangChain, MCP)

sourcerykit

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.

chp-host

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

shipit-agent

Powerful Python agent runtime with tools, MCP, Hooks, Skills, Rag, memory, sessions, reasoning, and streaming packets.

roboshed

Python framework for typed LLM agents with conditional tool chaining.