composio-core
[DEPRECATED] Core package to act as a bridge between composio platform and other services. Please use 'composio' instead.
Decision gist · record as of 2026-08-14
Yes, if you are already committed to the composio ecosystem and your codebase targets this version. However, no for new projects—the package is explicitly deprecated and the maintainers recommend using 'composio' instead. Verify that your use case is compatible with version 0.7.21 before adopting it.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires COMPOSIO_API_KEY environment variable and pre-configured credentials for target services (GitHub, Slack, Gmail, etc.) via CLI setup or environment configuration.
- Low install friction with a pure-Python wheel distribution.
- Active maintenance with recent commits, though the package is marked deprecated in favor of the 'composio' package; users should verify whether the newer package is the intended target.
License · maintenance · safety
permissive license (permissive) — Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions.
last release 2025-09-09 (339 days) · last repo commit 2026-08-14 · 29,690 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 207,565 downloads/mo, #9,547 on PyPI
Alternatives
Verify before relying
pip install composio-core
from composio_core import ComposioToolSet
import requests
composio_tool_set = ComposioToolSet()
# Configure with COMPOSIO_API_KEY and target service credentials- Whether 'composio' (the replacement package) is a drop-in substitute or requires code changes
- Whether the 250+ tools mentioned in the description are available in version 0.7.21 or require a newer release
- Specific framework compatibility with OpenAI, Claude, LlamaIndex, Langchain, CrewAI, and Autogen versions
What it is and what it does
Composio-core is a bridge library that connects AI agents to a catalog of external tools and services. It handles authentication (OAuth, API keys, JWT) and exposes actions from platforms like GitHub, Slack, Gmail, Notion, and others as callable functions that an LLM can invoke. The package provides a toolset abstraction that lets you define which actions an agent can perform, then manages execution and response handling.
The library is designed for production use in agent workflows where you need reliable, authenticated access to third-party APIs without building integrations from scratch. It ships with 18 runtime dependencies including aiohttp, pydantic, fastapi, and uvicorn, which support both synchronous and asynchronous execution patterns. However, the package is now deprecated in favor of the 'composio' package, and new projects should evaluate whether to use the replacement instead.
Use it for
- Build an AI agent that can star GitHub repositories, create issues, or manage pull requests on behalf of a user
- Create a bot that uses an LLM to search conversations, draft messages, or post updates to Slack channels
- Develop an assistant that reads Gmail, creates calendar events, and sends emails through authenticated integrations
- Connect a multi-agent system to perform coordinated actions across Notion, Linear, and Salesforce
- Prototype an agent that searches the web and then files results into a database or document
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are already committed to the composio ecosystem and your codebase targets this version.
However, no for new projects—the package is explicitly deprecated and the maintainers recommend using 'composio' instead. Verify that your use case is compatible with version 0.7.21 before adopting it.
Install
composio-core on PyPI
Before you install
Low install friction with a pure-Python wheel distribution. Active maintenance with recent commits, though the package is marked deprecated in favor of the 'composio' package; users should verify whether the newer package is the intended target.
Requires COMPOSIO_API_KEY environment variable and pre-configured credentials for target services (GitHub, Slack, Gmail, etc.) via CLI setup or environment configuration.
License in practice
Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions.
Quickstart
pip install composio-core
from composio_core import ComposioToolSet
import requests
composio_tool_set = ComposioToolSet()
# Configure with COMPOSIO_API_KEY and target service credentialsVerify before relying
- Whether 'composio' (the replacement package) is a drop-in substitute or requires code changes
- Whether the 250+ tools mentioned in the description are available in version 0.7.21 or require a newer release
- Specific framework compatibility with OpenAI, Claude, LlamaIndex, Langchain, CrewAI, and Autogen versions
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release <4,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 18 packagesaiohttprequestsjsonschemasentry-sdkpysherpydanticimportlib-metadatajsonrefinflectionsemverclickrichpyperclipPillowparamikofastapiuvicornpyyaml |
| Maintenance | Actively maintained 339 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 207,565 / month, #9,547 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 7 - InactiveLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: composio_core-0.7.21-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 › “llm external service integration”
- composio-coreComposio-core bridges AI agents to external tools and services,…
- composio-langchainBridges Composio's 1000+ app integrations into LangChain agents by…
- azure-ai-agentsBuild and deploy AI agents on Azure using models from OpenAI,…
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-openai-agents · composio-langchain · composio-openai · openai-agents · cocoindex · workspace-mcp · fast-agent-mcp · agent-framework · mcp-proxy-for-aws