Tool Use Python Packages

tooluniverse

Democratizing AI scientists with ToolUniverse

verel

Verified agents — nothing is "done" until a grader returns a verdict. Eyes (AgentVision) + verdict bus + compounding memory + a fleet + agent-built tooling + agent-run CI/CD.

systemu

An open-source AI agent that builds the tools it's missing, mid-task — under your governance. Pull capabilities at runtime instead of pre-wiring them. Local-first, MIT.

agentcrew-ai

Chat application with multi-agents system supports multi-models and MCP

fabri

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

siglume-api-sdk

SDK for publishing APIs that AI agents subscribe to on the Siglume API Store. Python + TypeScript. Earn 93.4% of subscription revenue.

toolregistry

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

tvastar

Loop quality layer for production AI agents. Detects silent failures, runs agents on a schedule with verify + handoff, and generates cryptographic audit receipts. Works with Claude, OpenAI, LiteLLM, LangGraph, and AgentCore.

litestar-mcp

Litestar plugin for Model Context Protocol (MCP) — expose route handlers as MCP tools and resources for AI agents.

agentsynth-ai

Outcome-verified agent trajectories, benchmarks, and RL environments — with a live leaderboard and a CI gate for your agents. Offline-first, MIT.

pawnlogic

A modular AI Agent framework designed for complex task orchestration and logic reasoning.

toolsconnector

Open-source Python library for 73 API connectors — Gmail, Slack, GitHub, Stripe, OpenAI, Anthropic & more. MCP server, OpenAI function calling, Anthropic tool use. 1,519 actions, 11 live-verified. Apache 2.0.

bigcodebench

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

agentdog

AgentDog helps developers inspect, test, score, and monitor AI agent runs locally.

kani

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

agentix-toolkit

A generic, batteries-included, async-first agent toolkit — configurable loop, tools, security guards, streaming, persistence, and MCP. Import as 'agentix'.

agenticx

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

dendrux

Async Python runtime for agents that survive failure, persist evidence, and pause for the real world.

tool-scorer

Python framework for evaluating LLM tool-calling behavior with comprehensive metrics on accuracy, efficiency, and correctness

intaris

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

document-adapter

LLM이 DOCX/PPTX/HWPX 문서를 직접 편집할 수 있게 해주는 통합 어댑터 + MCP 서버. Claude Desktop / Claude Code / Anthropic API Tool Use 호환. pip install document-adapter

sop-mcp

An MCP server that guides AI agents through Standard Operating Procedures step by step, enforcing execution at each step instead of letting models skip ahead.

agent-action-guard

Runtime classifier for screening AI agent actions as safe, harmful, or unethical.

etchplan

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.