Google unveils open-source Gemini CLI
SAN FRANCISCO, June 25 (Xinhua) -- Google announced on Wednesday the launch of Gemini CLI, an agentic artificial intelligence (AI) tool designed to run locally from terminals.
The new tool connects Google's Gemini AI models to local codebases, and it allows developers to make natural language requests, the company said.
Google offers AI coding tools such as Gemini Code Assist. With the release of Gemini CLI, it competes directly with other command-line AI tools such as OpenAI's Codex CLI and Anthropic's Claude Code.
The company said it designed the tool to handle other tasks as well. Developers can tap Gemini CLI to create videos with Google's Veo 3 model, generate research reports with the company's Deep Research agent, or access real-time information through Google Search.
Google is also open-sourcing Gemini CLI under the Apache 2.0 license. Free users can make 60 model requests per minute and 1,000 requests per day. According to Google, it is roughly double the average number of requests developers made when using the tool.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Borneo Post
2 hours ago
- Borneo Post
Ensuring benefits for the rakyat with responsible use of mobile phone data
The Mobile Phone Data Programme is not a breach of privacy but instead, an important tool for digital nation-building. – AI IMAGE R ecent discussions surrounding the Malaysian Communications and Multimedia Commission's (MCMC) Mobile Phone Data Programme have stirred public debate, raising questions over privacy, cybersecurity, and the government's role in data stewardship. As someone deeply involved in nation building in the areas of network infrastructure and cybersecurity, I feel it is crucial to bring technical clarity to the Malaysian public regarding this issue and separating speculation from substantiated fact. Understanding the Nature of the Data First and foremost, the data collected under the Mobile Phone Data Programme is aggregated, anonymised, and devoid of any personally identifiable information (PII). The data only provides generalised metadata such as signal strength, network usage trends, location area codes, and other non-personal metrics that can help our regulator assess mobile network performance, digital divide issues, and emergency response readiness. To equate this program with intrusive surveillance is technically inaccurate and misleading. The data points collected are no different, if not significantly less granular, than the metadata routinely collected by global platforms like Google, Apple, Meta, and numerous other mobile apps for analytics, service optimisation, and targeted advertising. Legal and Ethical Boundaries Are Intact The Malaysian regulator, MCMC, in line with the Communications and Multimedia Act 1998 and the Personal Data Protection Act 2010, operates within strict regulatory boundaries. This particular programme does not collect names, phone numbers, call logs, browsing history, or message contents. Generally, the participating Mobile Network Operators (MNOs) are very cautious on sharing their data yet, they have had no issues in working closely with MCMC on this project. Furthermore, access to the metadata is limited to selected analytical tools within the Commission, with no commercial or third-party exposure. This makes the dataset fundamentally different from the kind of data typically vulnerable to misuse or monetisation in commercial tech ecosystems. Strategic Importance in a Digital Nation From a technical and policy standpoint, the Mobile Phone Data Programme is strategically very important for national digital infrastructure planning. With Malaysia advancing toward wider 5G deployment and smart city initiatives, regulators require real-time, evidence-based insights into mobile coverage, device density, and population mobility to guide resource allocation, spectrum planning, and emergency readiness. For instance, during natural disasters or public health crises, such data can significantly improve our authorities' responses, enabling faster and more targeted assistance being provided to the needy. Several advanced economies, including South Korea, Finland, and Estonia, have long adopted similar anonymised data programs providing effective public benefits and without any complains about infringing on personal privacy. Addressing the Misinformation Ecosystem It is unfortunate that a narrative of distrust has taken root, largely fuelled by misinformation and a poor understanding of network-level data analytics. In the absence of context, the public is led to fear a 'surveillance state,' even when the technical facts clearly indicate that no such risk exists. MCMC's proactive move to engage cybersecurity experts, telcos, and the public through open communication is the correct path forward. Transparency, ongoing stakeholder dialogue, and third-party audits should be encouraged, not to defend against wrongdoing, but to reinforce trust in a system that is technically sound and ethically implemented. Final Thoughts The integrity of our digital ecosystem must be safeguarded, not only from cyber threats but from disinformation that can undermine our national progress. The Mobile Phone Data Programme is not a breach of privacy but instead, an important tool for digital nation-building, designed with checks and balances that preserves user anonymity and protects public trust. Let us not conflate good governance with intrusion, or precaution with paranoia. This part of Malaysia's digital journey uses the carefully redacted data to ensure better mobile coverage and connectivity, amongst other things, to bring better comfort and telco services to the Malaysian public. * Prof Emeritus Dr Sureswaran Ramadass is Chairman of APAC IPv6 Council & Cybersecurity Subject Matter Expert Data Collection MCMC Metadata mobile data
The Star
5 hours ago
- The Star
Microsoft and OpenAI dueling over artificial general intelligence, The Information reports
FILE PHOTO: OpenAI logo is seen in this illustration taken June 18, 2025. REUTERS/Dado Ruvic/Illustration/File photo (Reuters) -Microsoft and OpenAI are at odds over a contractual provision related to artificial general intelligence, The Information reported on Wednesday. Under the current terms, when OpenAI achieves AGI, Microsoft's access to such a technology would be void. Microsoft wants OpenAI to remove that clause but so far OpenAI has refused, the report said. "We have a long-term, productive partnership that has delivered amazing AI tools for everyone. Talks are ongoing and we are optimistic we will continue to build together for years to come," OpenAI and Microsoft said in a joint statement emailed to Reuters. The report comes at a time when one of the most pivotal partnerships in the field of AI is under strain. OpenAI needs Microsoft's approval to complete its transition into a public-benefit corporation. But the two have not been able to agree on details even after months of negotiations, according to sources. Microsoft partnered with OpenAI in 2019, investing $1 billion to support the startup's development of AI technologies on its Azure cloud platform. (Reporting by Niket Nishant and Nathan Gomes in Bengaluru; Additional reporting by Harshita Meenaktshi; Editing by Alan Barona)
The Sun
6 hours ago
- The Sun
Microsoft and OpenAI dueling over artificial general intelligence, The Information reports
MICROSOFT and OpenAI are at odds over a contractual provision related to artificial general intelligence, The Information reported on Wednesday. Under the current terms, when OpenAI achieves AGI, Microsoft's access to such a technology would be void. Microsoft wants OpenAI to remove that clause but so far OpenAI has refused, the report said. The report comes at a time when one of the most pivotal partnerships in the field of AI is under strain. OpenAI needs Microsoft's approval to complete its transition into a public-benefit corporation. But the two have not been able to agree on details even after months of negotiations, according to sources. Microsoft partnered with OpenAI in 2019, investing $1 billion to support the startup's development of AI technologies on its Azure cloud platform. The companies did not immediately respond to Reuters requests for comment. In multiple statements addressing recent media speculation, both have said that discussions are ongoing and they remain optimistic about a long-term partnership.
