PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Tool Use Python Packages

Python packages with the GitHub topic tool-use. Sorted by relevance, with stars and monthly downloads.
mims-harvard
tooluniverse

Democratizing AI scientists with ToolUniverse

346K 1K 207
saigontechnology
agentcrew-ai

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

18K 200 38
bigcode-project
bigcodebench

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

17K 500 72
taihei-05
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.

8K 3 5
Oaklight
toolregistry

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

7K 54 7
DemonDamon
agenticx

AgenticX is a unified, production-ready multi-agent platform β€” 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).

3K 119 16
sachinshelke
toolsconnector

Open-source Python library for 68 API connectors β€” Gmail, Slack, GitHub, Stripe, OpenAI, Anthropic & more. MCP server, OpenAI function calling, Anthropic tool use. 1,370+ actions. Apache 2.0.

3K 4 2
Pro-GenAI
agent-action-guard

πŸ›‘οΈ Safe AI Agents through Action Classifier

3K 10 7
zhudotexe
kani

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

3K 601 29
ValueArchitectsAI
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.

2K 3 0
KTCrisis
flux7-mesh

Guardrail sidecar proxy for AI agents β€” policy, approval gates, grants, tracing. One Go binary, one YAML.

1K 1 0
fpytloun
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.

1K 15 4
dendrux
dendrux

The runtime for agents that act in the real world.

1K 11 0
PlateerLab
document-adapter

LLM이 DOCX/PPTX/HWPX λ¬Έμ„œλ₯Ό 직접 νŽΈμ§‘ν•  수 있게 ν•΄μ£ΌλŠ” 톡합 μ–΄λŒ‘ν„° + MCP μ„œλ²„. Claude Desktop / Claude Code / Anthropic API Tool Use ν˜Έν™˜. pip install document-adapter

1K 0 0
hsaghir
looplet

The tool-calling loop for LLM agents; iterator-first, protocol-hooked, one dependency.

1K 6 3
ruairidhwm
halftrace

Diagnostics for agent loops. Measure how fast each capability decays over long trajectories.

1K 0 0
vinhnx
vtai

VT.ai - multimodal AI chat app with dynamic conversation routing

1K 112 17
joemunene-by
ghostloop

The agent loop, embodied. Tool-using runtime + fail-closed safety pipeline + sim-first execution + statistically-rigorous bench harness + post-hoc analysis (counterfactual replay, causal attribution, LLM judge, property mining) for embodied AI. Sister project to GhostLM.

1K 0 0
auraguardhq
aura-guard

Exactly-once + circuit breaker for agent tool calls (loops, retries, duplicate side effects)

1K 7 0
vdineshk
dominion-observatory-sdk

Behavioral trust scoring, MCP servers, and x402 payment gating for autonomous AI agents. Live Observatory + LangChain tool + testnet demo.

1K 0 2
hidearmoon
agentguardx

Runtime security layer for AI agents β€” inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.

908 1 1
jstibal
crewai-openterms

OpenTerms tools for CrewAI agents. Add machine-readable permission checks and fail-closed guarded tool execution.

907 0 0
jstibal
langchain-openterms

OpenTerms tools for LangChain agents. Check machine-readable permission rules before agent tools execute.

877 0 0
James-Wirth
phantom-ai

Sandboxed data analysis with LLMs, powered by DuckDB

661 0 0
    • Data from PyPI, GitHub, ClickHouse, and BigQuery