Forwarded from Telegram Info English (Sominemo)
Media is too big
VIEW IN TELEGRAM
Grok Integration
Pavel Durov announced that Telegram has reached an agreement with Elon Musk to integrate Grok into the messenger this summer.
The one-year partnership will give Telegram users access to xAI’s Grok chatbot.
Telegram will receive $300 million in cash and equity from xAI, as well as 50% of revenue from xAI subscriptions sold through Telegram. Grok may be sold as a separate subscription.
Privacy
Pavel Durov claims that Telegram will only send Grok the data that the user and their chat partners decide to share. The founder of the messenger did not specify whether xAI has the right to train its models on data received from Telegram users.
Note that these words should not be taken as a long-term guarantee — Telegram has changed its approach to privacy in the past, even after making promises.
What features can we expect?
In his post, Pavel Durov presented a video concept of future features. It is worth noting that in their final forms, the features may not work as shown in the demonstration.
1. Grok pinned for all users (0:02)
It is likely that the bot can be unpinned — there is an “unpin” button displayed in the video.
2. Questions through global search (0:04)
A Grok button will appear in global search, clicking on which sends the search query to the Grok chatbot.
3. Communication in threads (0:08)
Communication with Grok may be done in several threads in parallel, the interface will look similar to forums, but in private with the bot.
4. Editing text before sending (0:12)
Upon selecting text in the message input field and pressing “AI Tools”, you will be offered options to rewrite the text: to “Improve”, “Expand”, or “Change Tone”. The new menu is added right before Formatting options in the floating bar.
5. Chat summarization (0:16)
By holding down the unread message indicator, you may select the “Summarize” option to get a summary of the chat’s unread messages.
The interface also shows a selector for the range of messages the model will have access to, and the tone of the narrative. It may be possible to get a summary not only for unread messages, but also for messages you choose.
6. Document summarization (0:20)
In the context menu of PDF files uploaded to Telegram, you will be able to select the “Summarize” option to get a digest of the text inside, without opening the file.
7. Link summarization (0:24)
If you long press a link in a message and select the “Summarize” option, the chatbot will generate a digest of the Instant View article. The summary text may be listened to as audio.
It is not clear whether this function will be available for links without Instant View.
8. Moderating groups (0:28)
Automated moderation of group chats is shown.
In the example, Grok issues a warning to the user and threatens with a ban for repeated violations. How exactly admins will be able to set rules and control the number of warnings is unclear.
9. Grok in 1-on-1 chats (0:32)
It will be possible to configure the chatbot so that it responds in personal messages on behalf of the user. The video also shows how you will be able to monitor the bot’s responses in real time and a button to intercept control.
10. Fact-checking in channels (0:36)
A “Fact-Check” button will appear in the context menu of messages in channels.
What sources the model will use and how reliable such reviews will be is unknown.
11. Generating stickers (0:40)
The sticker editor will allow you to describe the desired sticker using text to generate new stickers, including video stickers.
12. Generating avatars (0:44)
Similar to stickers, it will be possible to generate avatars for your profile.
In the video, the user asks to change the background of their avatar, while the user’s face is preserved. Perhaps users will be able to not only generate images from scratch, but also ask to edit their own photos.
#Grok #AI
Pavel Durov announced that Telegram has reached an agreement with Elon Musk to integrate Grok into the messenger this summer.
The one-year partnership will give Telegram users access to xAI’s Grok chatbot.
Telegram will receive $300 million in cash and equity from xAI, as well as 50% of revenue from xAI subscriptions sold through Telegram. Grok may be sold as a separate subscription.
Privacy
Pavel Durov claims that Telegram will only send Grok the data that the user and their chat partners decide to share. The founder of the messenger did not specify whether xAI has the right to train its models on data received from Telegram users.
Note that these words should not be taken as a long-term guarantee — Telegram has changed its approach to privacy in the past, even after making promises.
What features can we expect?
In his post, Pavel Durov presented a video concept of future features. It is worth noting that in their final forms, the features may not work as shown in the demonstration.
1. Grok pinned for all users (0:02)
It is likely that the bot can be unpinned — there is an “unpin” button displayed in the video.
2. Questions through global search (0:04)
A Grok button will appear in global search, clicking on which sends the search query to the Grok chatbot.
3. Communication in threads (0:08)
Communication with Grok may be done in several threads in parallel, the interface will look similar to forums, but in private with the bot.
4. Editing text before sending (0:12)
Upon selecting text in the message input field and pressing “AI Tools”, you will be offered options to rewrite the text: to “Improve”, “Expand”, or “Change Tone”. The new menu is added right before Formatting options in the floating bar.
5. Chat summarization (0:16)
By holding down the unread message indicator, you may select the “Summarize” option to get a summary of the chat’s unread messages.
The interface also shows a selector for the range of messages the model will have access to, and the tone of the narrative. It may be possible to get a summary not only for unread messages, but also for messages you choose.
6. Document summarization (0:20)
In the context menu of PDF files uploaded to Telegram, you will be able to select the “Summarize” option to get a digest of the text inside, without opening the file.
7. Link summarization (0:24)
If you long press a link in a message and select the “Summarize” option, the chatbot will generate a digest of the Instant View article. The summary text may be listened to as audio.
It is not clear whether this function will be available for links without Instant View.
8. Moderating groups (0:28)
Automated moderation of group chats is shown.
In the example, Grok issues a warning to the user and threatens with a ban for repeated violations. How exactly admins will be able to set rules and control the number of warnings is unclear.
9. Grok in 1-on-1 chats (0:32)
It will be possible to configure the chatbot so that it responds in personal messages on behalf of the user. The video also shows how you will be able to monitor the bot’s responses in real time and a button to intercept control.
10. Fact-checking in channels (0:36)
A “Fact-Check” button will appear in the context menu of messages in channels.
What sources the model will use and how reliable such reviews will be is unknown.
11. Generating stickers (0:40)
The sticker editor will allow you to describe the desired sticker using text to generate new stickers, including video stickers.
12. Generating avatars (0:44)
Similar to stickers, it will be possible to generate avatars for your profile.
In the video, the user asks to change the background of their avatar, while the user’s face is preserved. Perhaps users will be able to not only generate images from scratch, but also ask to edit their own photos.
#Grok #AI
🖕5❤1
Forwarded from NoGoolag
The #AI That Triggered a War: How Palantir and the IAEA Fueled israel’s strike on Iran
A $50M software built for counterinsurgency now steers nuclear diplomacy... and may have lit the fuse for a regional war.
https://ddgeopolitics.substack.com/p/the-ai-that-triggered-a-war-how-palantir
...But what if the intelligence fueling this war came not from Mossad or Pentagon satellites but from a #UN agency’s software? Since 2015, the #IAEA has relied on #Palantir’s #Mosaic platform, a $50-million AI system that sifts 400 million data points—satellite imagery, social media, personnel logs—to predict nuclear threats. On June 12, Iran leaked documents it claimed showed IAEA chief Rafael Grossi shared Mosaic outputs with Israel, effectively turning the agency into a “tool for aggression.” The charge echoes a pattern: prior to 2025, Mosaic data helped shape sanctions and even UN aid decisions despite risks of bias...
...The problem? Mosaic’s lineage screams bias. Funded by #InQTel, the CIA’s venture arm, #Palantir powers IDF targeting in #Gaza and #Ukraine’s #drone strikes. Mosaic’s black-box algorithms, unauditable and proprietary, risk turning the IAEA from neutral inspector into a data proxy for preemptive war. As we’ll explore with Fordow’s role, this software may have already crossed that line, threatening the Non-Proliferation Treaty it was meant to uphold...
...Mosaic, crunching 400 million data points since 2015, mapped Fordow’s centrifuge cascades and satellite imagery, flagging anomalies as threats. Its AI, built for counterinsurgency, predicts intent—perfect for crafting a “nine-bomb” narrative. The May 31 report cited undeclared traces at Lavisan-Shian and Turquzabad, echoing 2018 when Mosaic’s findings sparked sanctions despite Iran’s “sabotage” claims. Iran’s nuclear chief, Behrouz Kamalvandi, alleged in 2025 that Turquzabad’s coordinates were “planted,” suggesting fabricated evidence. Iran’s June 12 leak, claiming Rafael Grossi shared Mosaic data with Israel, deepened suspicions...
...The answer lies in Mosaic’s design. Originally built to identify insurgent activity in Iraq and Afghanistan, Mosaic infers hostile intent from indirect indicators—metadata, behavioral patterns, signal traffic—not from confirmed evidence. When repurposed for nuclear oversight, this logic translates correlation into alarm. That Mosaic also powers IDF targeting systems in Gaza and Ukraine makes its presence inside the IAEA all the more explosive...
@FuryRoad_Intel
A $50M software built for counterinsurgency now steers nuclear diplomacy... and may have lit the fuse for a regional war.
https://ddgeopolitics.substack.com/p/the-ai-that-triggered-a-war-how-palantir
...But what if the intelligence fueling this war came not from Mossad or Pentagon satellites but from a #UN agency’s software? Since 2015, the #IAEA has relied on #Palantir’s #Mosaic platform, a $50-million AI system that sifts 400 million data points—satellite imagery, social media, personnel logs—to predict nuclear threats. On June 12, Iran leaked documents it claimed showed IAEA chief Rafael Grossi shared Mosaic outputs with Israel, effectively turning the agency into a “tool for aggression.” The charge echoes a pattern: prior to 2025, Mosaic data helped shape sanctions and even UN aid decisions despite risks of bias...
...The problem? Mosaic’s lineage screams bias. Funded by #InQTel, the CIA’s venture arm, #Palantir powers IDF targeting in #Gaza and #Ukraine’s #drone strikes. Mosaic’s black-box algorithms, unauditable and proprietary, risk turning the IAEA from neutral inspector into a data proxy for preemptive war. As we’ll explore with Fordow’s role, this software may have already crossed that line, threatening the Non-Proliferation Treaty it was meant to uphold...
...Mosaic, crunching 400 million data points since 2015, mapped Fordow’s centrifuge cascades and satellite imagery, flagging anomalies as threats. Its AI, built for counterinsurgency, predicts intent—perfect for crafting a “nine-bomb” narrative. The May 31 report cited undeclared traces at Lavisan-Shian and Turquzabad, echoing 2018 when Mosaic’s findings sparked sanctions despite Iran’s “sabotage” claims. Iran’s nuclear chief, Behrouz Kamalvandi, alleged in 2025 that Turquzabad’s coordinates were “planted,” suggesting fabricated evidence. Iran’s June 12 leak, claiming Rafael Grossi shared Mosaic data with Israel, deepened suspicions...
...The answer lies in Mosaic’s design. Originally built to identify insurgent activity in Iraq and Afghanistan, Mosaic infers hostile intent from indirect indicators—metadata, behavioral patterns, signal traffic—not from confirmed evidence. When repurposed for nuclear oversight, this logic translates correlation into alarm. That Mosaic also powers IDF targeting systems in Gaza and Ukraine makes its presence inside the IAEA all the more explosive...
@FuryRoad_Intel
Substack
The AI That Triggered a War: How Palantir and the IAEA Fueled Israel’s Strike on Iran
A $50M software built for counterinsurgency now steers nuclear diplomacy... and may have lit the fuse for a regional war.
🔥4❤2
NoGoolag
The #AI That Triggered a War: How Palantir and the IAEA Fueled israel’s strike on Iran A $50M software built for counterinsurgency now steers nuclear diplomacy... and may have lit the fuse for a regional war. https://ddgeopolitics.substack.com/p/the-ai-that…
Grossi Says IAEA Report 'Not Basis For War' After Threat Of Legal Action From Iran
An Iranian Foreign Ministry spokesman said this week that the IAEA report on Iran helped pave the way for Israel’s war on the country
The head of the International Atomic Energy Agency (IAEA), Rafael Grossi, said that the agency’s report accusing Iran of secret and illicit nuclear activity is not the reason behind Israel’s war against the country, after Tehran signaled it would take legal action against him.
“A report on the nuclear verification in Iran could hardly be a basis for any military action. Military action, from whomever it comes, is a political decision that has nothing to do with what we’re saying,” Grossi told CNN.
“In that report, I also said that, at this point, we do not have any indication that there is a systemic program in Iran to manufacture a nuclear weapon. It’s true that in the early 2000s, there had been some activities which were assessed at that time as related to nuclear weapon development … we are not seeing this now,” he added.
When asked about a potential “timeline” in which Iran could build a nuclear weapon, Grossi said discussing a timeline would be nothing but “pure speculation.”
On 19 June, the Head of the Atomic Energy Organization of Iran (AEOI) Mohammad Eslami sent a letter to Grossi condemning the “the criminal Zionist regime's repeated barbaric attacks” across Iran and on its nuclear facilities, adding that these attacks took place “despite repeated warnings to you regarding inaction, especially by the Board of Governors, which unfortunately operates under the guidance, influence, and support of three European countries, the US, and the Zionist regime.”
🔗SOURCE ➡️ The Cradle
Related: 6/20 — The #AI That Triggered a War: How Palantir and the IAEA Fueled israel’s strike on Iran
6/17 — ❗️❗️❗️ Director General of the International Atomic Energy Agency (IAEA), Rafael Grossi admits that Iran was not going to make a nuclear weapon.
2/27 — UN Watchdog Says Iran 'Sharply Increased' Stockpile Of Near Weapons-Grade Uranium
Follow us on Minds / X / Substack
Boost This Channel
Follow ➡️ @PsyopDaily
An Iranian Foreign Ministry spokesman said this week that the IAEA report on Iran helped pave the way for Israel’s war on the country
The head of the International Atomic Energy Agency (IAEA), Rafael Grossi, said that the agency’s report accusing Iran of secret and illicit nuclear activity is not the reason behind Israel’s war against the country, after Tehran signaled it would take legal action against him.
“A report on the nuclear verification in Iran could hardly be a basis for any military action. Military action, from whomever it comes, is a political decision that has nothing to do with what we’re saying,” Grossi told CNN.
“In that report, I also said that, at this point, we do not have any indication that there is a systemic program in Iran to manufacture a nuclear weapon. It’s true that in the early 2000s, there had been some activities which were assessed at that time as related to nuclear weapon development … we are not seeing this now,” he added.
When asked about a potential “timeline” in which Iran could build a nuclear weapon, Grossi said discussing a timeline would be nothing but “pure speculation.”
On 19 June, the Head of the Atomic Energy Organization of Iran (AEOI) Mohammad Eslami sent a letter to Grossi condemning the “the criminal Zionist regime's repeated barbaric attacks” across Iran and on its nuclear facilities, adding that these attacks took place “despite repeated warnings to you regarding inaction, especially by the Board of Governors, which unfortunately operates under the guidance, influence, and support of three European countries, the US, and the Zionist regime.”
🔗SOURCE ➡️ The Cradle
Related: 6/20 — The #AI That Triggered a War: How Palantir and the IAEA Fueled israel’s strike on Iran
A $50M software built for counterinsurgency now steers nuclear diplomacy... and may have lit the fuse for a regional war.
https://ddgeopolitics.substack.com/p/the-ai-that-triggered-a-war-how-palantir
...But what if the intelligence fueling this war came not from Mossad or Pentagon satellites but from a #UN agency’s software? Since 2015, the #IAEA has relied on #Palantir’s #Mosaic platform, a $50-million AI system that sifts 400 million data points—satellite imagery, social media, personnel logs—to predict nuclear threats. On June 12, Iran leaked documents it claimed showed IAEA chief Rafael Grossi shared Mosaic outputs with Israel, effectively turning the agency into a “tool for aggression.” The charge echoes a pattern: prior to 2025, Mosaic data helped shape sanctions and even UN aid decisions despite risks of bias...
...The problem? Mosaic’s lineage screams bias. Funded by #InQTel, the CIA’s venture arm, #Palantir powers IDF targeting in #Gaza and #Ukraine’s #drone strikes. Mosaic’s black-box algorithms, unauditable and proprietary, risk turning the IAEA from neutral inspector into a data proxy for preemptive war. As we’ll explore with Fordow’s role, this software may have already crossed that line, threatening the Non-Proliferation Treaty it was meant to uphold...
...Mosaic, crunching 400 million data points since 2015, mapped Fordow’s centrifuge cascades and satellite imagery, flagging anomalies as threats. Its AI, built for counterinsurgency, predicts intent—perfect for crafting a “nine-bomb” narrative. The May 31 report cited undeclared traces at Lavisan-Shian and Turquzabad, echoing 2018 when Mosaic’s findings sparked sanctions despite Iran’s “sabotage” claims. Iran’s nuclear chief, Behrouz Kamalvandi, alleged in 2025 that Turquzabad’s coordinates were “planted,” suggesting fabricated evidence. Iran’s June 12 leak, claiming Rafael Grossi shared Mosaic data with Israel, deepened suspicions...
6/17 — ❗️❗️❗️ Director General of the International Atomic Energy Agency (IAEA), Rafael Grossi admits that Iran was not going to make a nuclear weapon.
2/27 — UN Watchdog Says Iran 'Sharply Increased' Stockpile Of Near Weapons-Grade Uranium
Follow us on Minds / X / Substack
Boost This Channel
Follow ➡️ @PsyopDaily
The Cradle
Grossi says IAEA report 'not basis for war' after threat of legal action from Iran
An Iranian Foreign Ministry spokesman said this week that the IAEA report on Iran helped pave the way for Israel’s war on the country
🔥3
Forwarded from Science in telegram
Atari 2600 Beats ChatGPT at Chess — No, Seriously
In an unexpected clash of tech generations, an engineer from Citrix pitted ChatGPT against a 1977 Atari 2600 console running Atari Chess. The result? The retro console won — and convincingly so.
For over 90 minutes, GPT-4o struggled against the 8-bit game’s simplest difficulty setting. It confused pieces, forgot past moves, and made blunders that would embarrass a novice. Even after switching from icon-based display to standard chess notation, its gameplay didn’t improve.
The funniest part? ChatGPT kept complaining that the piece icons were “too abstract” to interpret — a very human excuse for losing to a machine older than most of its users’ parents.
Despite Atari only looking 1–2 moves ahead, it managed to consistently outplay a state-of-the-art language model. A stark reminder: understanding language ≠ understanding logic or spatial reasoning.
Full story here 👉 https://futurism.com/atari-beats-chatgpt-chess
#AI #ChessFail #Atari2600 #GPT4 #RetroTech
In an unexpected clash of tech generations, an engineer from Citrix pitted ChatGPT against a 1977 Atari 2600 console running Atari Chess. The result? The retro console won — and convincingly so.
For over 90 minutes, GPT-4o struggled against the 8-bit game’s simplest difficulty setting. It confused pieces, forgot past moves, and made blunders that would embarrass a novice. Even after switching from icon-based display to standard chess notation, its gameplay didn’t improve.
The funniest part? ChatGPT kept complaining that the piece icons were “too abstract” to interpret — a very human excuse for losing to a machine older than most of its users’ parents.
Despite Atari only looking 1–2 moves ahead, it managed to consistently outplay a state-of-the-art language model. A stark reminder: understanding language ≠ understanding logic or spatial reasoning.
Full story here 👉 https://futurism.com/atari-beats-chatgpt-chess
#AI #ChessFail #Atari2600 #GPT4 #RetroTech
Futurism
ChatGPT "Absolutely Wrecked" at Chess by Atari 2600 Console From 1977
Despite all its advances, ChatGPT still, seemingly, is less smart than an Atari simulator on beginner mode.
🤣3
The Daily Psyop
ICYMI: While You Were Distracted By Trump's Army Parade, The U.s. Army Quietly Swore In 4 Silicon Valley Execs As Reserve Lt. Colonels: Shyam Sankar: Palantir Andrew Bosworth: META Kevin Weil: OpenAI Bob McGrew: ex-Open AI Oh, the technocratic state will…
Palantir and Accenture Federal Services have formed a strategic partnership to offer AI solutions to U.S. federal agencies. They aim to tackle major operational challenges, enhancing workflows and decision-making.
Both companies will train 1,000 professionals from Accenture on Palantir's platforms to ensure effective AI deployment.
Key focus areas include:
1. Data Fusion
2. Supply Chain Orchestration
3.Financial Intelligence
Mike Galagher, head of Defense for Palantir Technologies says:
“..we need to provide America’s warfighters with cutting-edge AI computing and solutions in order to enhance deterrence, this partnership will empower those warfighters with information and analytics.."
Leaders from both companies emphasize the partnership's potential to empower government operations and support warfighters with advanced AI capabilities.
Businesswire: Palantir and Accenture Federal Services Join Forces to Help Federal Government Agencies Reinvent Operations with AI [X]
🔗SOURCE ➡️ Disclose [2], BusinessWire [2]
Related: 6/20 — The #AI That Triggered a War: How Palantir and the IAEA Fueled israel’s strike on Iran
ICYMI:.. The U.S. Army Quietly Swore In 4 Silicon Valley Execs As Reserve Lt. Colonels:
6/15 — U.S. Army swears in senior tech leaders from Meta, Palantir, OpenAI as lieutenant colonels to be part-time advisors.
6/14 — If Elon’s Really A Warrior For Liberty And Free Speech, Why Is He Cozying Up To Palantir’s Architect Of Mass Surveillance?
6/6 — Alex Karp, CEO Of Palantir. The UK NHS Is Giving Them All Your Medical Data...
6/1 — Trump Taps Palantir to Create Master Database on Every American
4/16 — The Main Lobbying Firm Elon Musk's Space X And Peter Theil's Palantir Have Used To Lobby Is Invariant LLC, Whose CEO Has Been And Is Heather Podesta. (Tony Podesta's Ex-Wife).
3/11 —Grok: Today, Companies Like Palantir, Supplying AI For Israel’s Targeting In Gaza, Could Face International Law Risks—similar To How Firms Aiding Nazi War Crimes Were Later Held Accountable...
1/22 — "I don't Trust Palantir, Thiel, Musk and Co But At Least Its Not Kamala."
11/16 — ... Once You Go Down The Thiel Rabbit Hole...
9/11/24 — The Trump-RFK-Musk-Thiel Cabal Is Fooling The Freedom Movement
6/12/24 — ‘Digital Kill Chains’: The Dark Side of Tech in Warfare
Companies like Palantir Technologies, led by CEO Alex Karp, have been implicated in enabling some of these atrocities. Its advanced data analytics and AI tools that supposedly provide “precision targeting” are mass-killing civilians and have transformed warfare into a calculated and systematic campaign of extermination with little human oversight.
... Initially funded by the CIA’s venture capital arm, In-Q-Tel, Palantir’s tech products have become integral to numerous US government agencies, including the FBI, Department of Defense, and various police departments.
This deep entanglement with US intelligence and military bodies paved the way for Palantir’s strategic alignment with Israel.
5/9/24 — Palantir CEO Alex Karp presents the Palestine solidarity campus protest movement as an existential threat to American empire
2/25/24 — Censorship Continues on 'Free Speech Platform' X, Elon Musk Expanding Contracts With Intelligence Agencies.. — TheMcgwire / @PsyopDaily Original
...Thiel is also known to have been an associate of Jeffrey Epstein
...The Daily Mail's exclusive in May which described Peter Thiel and the current CIA director William Burns meeting Epstein in the same private meeting..
1/3/24 — Epstein and CIA — Excerpt From The Human Trafficking Circus in The Room, Epstein Is Just the Elephant - Pizzagate Needs to be Revisited [X]
Epstein, Mossad - Blackmail Honeypot Operation? — Excerpt From ⬆️
... “Who Are the Newly Revealed Jeffrey Epstein Associates?”, which included CIA director Burns, and Peter Thiel of Palantir, Google’s cofounder Sergey Brin, Bill Gates, and even Ehud Barak, former prime minister of Israel….among others.
Follow ➡️ @PsyopDaily
Please open Telegram to view this post
VIEW IN TELEGRAM
Businesswire
Palantir and Accenture Federal Services Join Forces to Help Federal Government Agencies Reinvent Operations with AI
Palantir has named Accenture Federal Services as a Palantir preferred implementation partner for U.S. federal government customers.
😈1👻1😨1
Forwarded from NoGoolag
#Gemini CLI, a light and powerful open-source #AI agent that brings Gemini directly into your terminal. >_
Write code, debug, and automate tasks with Gemini 2.5 Pro with industry-leading high usage limits at no cost.
Install: https://github.com/google-gemini/gemini-cli/
💡 Hierarchical Memory and instructions from GEMINI md files.
🛠 Bulit-in tools for filesystem, shell, MCP servers, and new shareable custom extensions.
📄 Multi-modal context, understands images, PDFs, and live web search results.
🔒 Supports secure tools via container sandboxes (Docker, Podman, or macOS sandbox-exec)
📈 Switches models automatically (e.g., pro to flash) to bypass API rate limits.
📊 Built-in Observability with OTEL traces, metrics, and logs.
💾 Save and resume conversations: persistent history across sessions, isolated per project.
💡 Git-Aware Context, the @ command respects .gitignore, --yolo flag to auto-approve
🤗 Native Windows support, no WSL required and Open Source under Apache 2.0!
@axisofordinary
Write code, debug, and automate tasks with Gemini 2.5 Pro with industry-leading high usage limits at no cost.
Install: https://github.com/google-gemini/gemini-cli/
💡 Hierarchical Memory and instructions from GEMINI md files.
🛠 Bulit-in tools for filesystem, shell, MCP servers, and new shareable custom extensions.
📄 Multi-modal context, understands images, PDFs, and live web search results.
🔒 Supports secure tools via container sandboxes (Docker, Podman, or macOS sandbox-exec)
📈 Switches models automatically (e.g., pro to flash) to bypass API rate limits.
📊 Built-in Observability with OTEL traces, metrics, and logs.
💾 Save and resume conversations: persistent history across sessions, isolated per project.
💡 Git-Aware Context, the @ command respects .gitignore, --yolo flag to auto-approve
🤗 Native Windows support, no WSL required and Open Source under Apache 2.0!
@axisofordinary