composio-openai-agents
Use Composio to get array of strongly typed tools for OpenAI Agents
Decision gist · record as of 2026-08-14
Yes—if you are building OpenAI Agents and need access to external app integrations. The package has low install friction, active maintenance, permissive licensing, and no known vulnerabilities. The only prerequisite is having both Composio and OpenAI API credentials configured. Suitable for production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires COMPOSIO_API_KEY and OPENAI_API_KEY environment variables to be set before use.
- Low friction: pure Python wheel with only two runtime dependencies (openai-agents and composio).
- Active maintenance—last commit 2026-08-14, released 3 days ago, 29690 repository stars.
License · maintenance · safety
permissive license (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for production agent deployments.
last release 2026-08-11 (3 days) · last repo commit 2026-08-14 · 29,690 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 275,533 downloads/mo, #8,175 on PyPI
Alternatives
Verify before relying
pip install composio composio-openai-agents openai-agents
from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner
composio = Composio(provider=OpenAIAgentsProvider())
session = composio.create(user_id="user_123")
tools = session.tools()
agent = Agent(name="Assistant", instructions="Use tools to help.", tools=tools)
result = Runner.run_sync(starting_agent=agent, input="Summarize my emails")- Specific count of integrated apps (description says '1000+' but no official inventory provided)
- Performance characteristics and latency of tool discovery and execution at runtime
- Session persistence and multi-turn conversation state management beyond the session_id reuse pattern shown
What it is and what it does
composio-openai-agents is an adapter that translates Composio's tool definitions into the native format expected by OpenAI's Agents framework. It sits between your agent and Composio's catalog of pre-built integrations, handling the conversion so agents can call external app actions without custom tool wrapping.
The package is designed for multi-turn agent workflows where you need to take real actions—sending emails, updating spreadsheets, querying databases—across many different services. You create a session scoped to a user, fetch the available tools, and pass them to your agent. Sessions include built-in meta-tools for discovery and authentication, and can be reused across multiple agent runs by storing and retrieving the session ID.
Use it for
- Build a personal assistant agent that reads emails, creates calendar events, and updates task lists across Gmail, Outlook, and Todoist.
- Create a customer support agent that queries CRM data, opens tickets, and sends notifications through Slack and email.
- Develop a data-sync agent that pulls information from one app (e.g., Salesforce) and pushes it to another (e.g., HubSpot).
- Build workflow automation where an agent decides which external actions to take based on user input and context.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes—if you are building OpenAI Agents and need access to external app integrations.
The package has low install friction, active maintenance, permissive licensing, and no known vulnerabilities. The only prerequisite is having both Composio and OpenAI API credentials configured. Suitable for production use.
Install
composio-openai-agents on PyPI
Before you install
Low friction: pure Python wheel with only two runtime dependencies (openai-agents and composio). Active maintenance—last commit 2026-08-14, released 3 days ago, 29690 repository stars.
Requires COMPOSIO_API_KEY and OPENAI_API_KEY environment variables to be set before use.
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for production agent deployments.
Quickstart
pip install composio composio-openai-agents openai-agents
from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner
composio = Composio(provider=OpenAIAgentsProvider())
session = composio.create(user_id="user_123")
tools = session.tools()
agent = Agent(name="Assistant", instructions="Use tools to help.", tools=tools)
result = Runner.run_sync(starting_agent=agent, input="Summarize my emails")Verify before relying
- Specific count of integrated apps (description says '1000+' but no official inventory provided)
- Performance characteristics and latency of tool discovery and execution at runtime
- Session persistence and multi-turn conversation state management beyond the session_id reuse pattern shown
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release <4,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesopenai-agentscomposio |
| Maintenance | Actively maintained 3 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 275,533 / month, #8,175 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: composio_openai_agents-0.19.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “openai agents tool integration”
- composio-openai-agentsBridges Composio's tool catalog to OpenAI's Agents framework, letting…
- unitycatalog-openaiExposes Unity Catalog functions as tools for OpenAI models, enabling…
- databricks-openaiIntegrates Databricks AI features, particularly vector search, into…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also composio · composio-langchain · composio-openai · openai-agents · composio-core · agent-framework · llama-index-agent-openai · opentelemetry-instrumentation-openai-agents · agent-framework-devui · openinference-instrumentation-openai-agents