OpenAGI
A Python package for structuring, sharing, and retrieving agents built for AIOS.
- Source repo
- agiresearch/OpenAGI
- Stars
- ★ 2.3k
- Last updated
- 1y ago
- License
- MIT
- Primary language
- Python
- FA score
- 44/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A Python developer building a custom agent for AIOS who needs the repository's prescribed author-and-agent directory layout.
- Not a fit if
- Teams needing agents portable beyond the AIOS platform
- Developers who already migrated to Cerebrum per the README
- Teams needing documented auth, endpoints, or error handling
- Website
- docs.aios.foundation ↗ set on GitHub
- Maintenance
- No commits for 6+ monthslast commit 2024-11-28
- Source review
- 44/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
OpenAGI is the pyopenagi package for creating agents intended for AIOS. It defines an agent layout under pyopenagi/agents, organized by author and agent name, with agent.py, config.json, and meta_requirements.txt. Developers can configure external tools and add new tool files under pyopenagi/tools/. Its interact.py command supports uploading a developed and tested agent or downloading an implementation created by someone else. The README also advises developers building agents for AIOS to migrate to Cerebrum, identified as the latest SDK for connecting with the AIOS kernel.
A developer creates pyopenagi/agents/<author>/<agent_name>/ and places agent.py for execution logic, config.json for configuration, and meta_requirements.txt for dependencies in that folder. External tools can be configured following tools.md, while new tools can be added as files under pyopenagi/tools/. After development and testing, python pyopenagi/agents/interact.py --mode upload --agent <author_name/agent_name> uploads an agent for sharing; the --agent value must exactly match the local folder path. Using the same script with --mode download downloads another developer's named agent implementation.
- A Python developer building a custom agent for AIOS who needs the repository's prescribed author-and-agent directory layout.
- An engineering team separating an agent's execution code, configuration, and dependency declaration into agent.py, config.json, and meta_requirements.txt.
- A developer whose in-progress agent needs external tools and can follow the documented tool setup path.
- A maintainer extending an agent with a new tool file in pyopenagi/tools/.
- An agent author who has finished testing and wants to share a local implementation through interact.py upload mode.
- A developer who wants to retrieve another contributor's implementation using interact.py download mode.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
pip install pyopenagipip install -e
- Config files
config.json
How do you install or deploy this agent?
Install from PyPI:
pip install pyopenagiInstall locally:
git clone https://agiresearch/OpenAGI
cd OpenAGIpip install -e .
The supplied material does not specify a Python version, authentication method, upload service endpoint, or credentials for external tools.
How do you use this agent?
Create pyopenagi/agents/<author>/<agent_name>/ and include agent.py, config.json, and meta_requirements.txt. Upload a developed and tested agent with: python pyopenagi/agents/interact.py --mode upload --agent <author_name/agent_name>. Download an agent with: python pyopenagi/agents/interact.py --mode download --agent <author_name/agent_name>. The README states that the agent argument must exactly match the local folder path.
What are this agent's strengths and limitations?
- Defines a concrete separation of execution logic, configuration, and dependency metadata for each agent.
- Uses one interact.py command interface for both uploading and downloading agents.
- Provides an extension location for new tools in pyopenagi/tools/ and a documented path for external-tool setup.
- Supports both PyPI installation and editable local installation with pip.
- The documented purpose is building agents for AIOS, with no evidence of portability to other platforms or runtimes.
- The README recommends migrating AIOS agent development to Cerebrum, which may require an adoption or migration plan.
- The supplied material does not document Python-version support, upload/download authentication, service endpoints, or error handling.
- It does not enumerate supported external tools, their credentials, or their runtime dependencies.
How does this agent compare with similar options?
For connecting with the AIOS kernel, the README identifies Cerebrum as the latest SDK and advises migration to it for building agents in AIOS.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| OpenAGI This agent | 44 · Major gaps | CLIFree | ★ 2.3k | 1y ago | Python | — |
| LightAgent | 60 · Some gaps | Library / SDKFree + model costs | ★ 1.2k | 6d ago | Python | OpenAI API |
| Promptulate | 41 · Major gaps | Library / SDKFree + model costs | ★ 511 | 8mo ago | Python | OpenAI API |
| AG2: Open-Source AgentOS | 75 · Good | Library / SDKFree + model costs | ★ 5.1k | 1d ago | Python | OpenAI API |
How does FollowAgents rate this agent?
Why each dimension lost points
The package is described as supporting Agent creation, upload and download, and external tools; the dependency list includes capabilities such as Playwright. The files do not explain permission boundaries, user confirmation, data flows, sensitive-data protection, or recovery from side effects, so those criteria receive only thin credit; rollback has no supporting evidence and scores 0. The README links the project to a research paper and the LICENSE names a copyright holder, supporting source attribution at 2, while publisher identity remains unknown.
CI configures Python 3.11 and pytest. The sample tests check an AgentProcess name, and the currency-tool test skips when its API key is absent and otherwise checks the return type. Coverage and assertions are narrow, and some dependencies are unpinned, so consistency, dependency availability, and failure messaging receive only partial credit.
The README identifies developers as the audience and gives an Agent directory layout, a tool-extension path, and AIOS context, supporting ordinary development scenarios. Capability boundaries and trigger conditions are not clearly specified. Python >=3.9 and installation instructions help with environment fit, but the described runtime environments are limited.
The README, tool-documentation entry point, contribution entry point, and directory layout provide a reasonably clear structure, with examples for installation, adding, uploading, and downloading agents. The complete MIT license merits full credit. The only explicit limitation is a migration notice for Cerebrum; there is no systematic limitations list. Version 0.0.11 is stated, but no changelog is included. Contribution and issue paths are visible, while maintenance responsibility and the update path remain unclear.
The framework provides Agent layout conventions, tool integration, and sharing workflows that give developers a practical starting point, supporting a marginal-value score of 2. The files do not show an output contract or actual result quality, and they do not weigh setup, configuration, and external API-key costs, so output usability and cost-benefit receive only 1.
Installation commands, directory structure, version, dependencies, and sample tests are traceable to the supplied files. The README's research connection is supported by a paper citation. Cross-checking between the README's functional claims and tests is limited, and the tests do not validate core Agent capabilities. The materials distinguish instructions from examples, but provide little evidence for claims about performance or quality.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The currency-converter test uses RAPID_API_KEY and makes an external API request; the supplied materials do not describe how that credential is stored or protected.
- The dependency list contains unpinned packages, and the static materials provide no vulnerability review or complete dependency-maintenance policy.
- The README directs AIOS users to migrate to Cerebrum, so OpenAGI's current maintenance status and long-term support scope need further confirmation.
FAQ
Is OpenAGI still the recommended choice for new AIOS agents?
What value should I pass to --agent when uploading?
What account or credentials are required for upload and download?
Can I use external tools with an agent?
Is OpenAGI free?
Is OpenAGI open source?
Is OpenAGI safe to use?
Is OpenAGI still maintained?
Who makes OpenAGI?
What is OpenAGI's official website?
Thanks — we use this to improve the page.