An analysis of code submitted to LibreOffice this year shows at least three explicit mentions of LLM use, with community developers saying they used tools such as Claude or GitHub Copilot. The Document Foundation previously stated that LibreOffice would not build in AI features and that core developers would not use LLMs to assist with programming, but in response it said it does require contributors to disclose when they use LLMs, and that overall it does not encourage LLM use.
Modem launched its X integration on October 30, 2026, which can search X for posts about its own products, filter out spam and jokes, categorize them by topic, and push them to the #bots-social channel in Slack. According to a Modem blog post, over the past 30 days Modem read 30,000 X posts and distilled hundreds of actionable bug reports and feature requests; feedback on the same need from X, Slack, tickets, and sales calls is merged into a single feature request, linked to a Linear issue and a GitHub PR, and once the fix ships, it lists who to notify and where to reply. The integration is included in the paid subscription and can be enabled under Settings → Integrations → X. There are no further developments at present.
m blog post, over the past 30 days Modem read 30,000 X posts and distilled hundreds of actionable bug reports and feature requests; feedback on the same need from X, Slack, tickets, and sales calls is merged into a single feature request, linked to a Linear issue and a GitHub PR, and once the fix ships, it lists who to notify and where to reply. The integration is included in the paid subscription and can be enabled under Settings → Integrations → X. There are no further developments at present.
Rohan Paul proposes that the agent economy is taking over. He cites data saying that GitHub recorded 7.38 billion commits in September 2026, more than five times the figure a year earlier. To handle the flood of code generated by agents, GitHub has added 4 million CPU cores, 160PB of high-speed storage and 50Tb/s of network capacity this year. A traffic surge on August 17 caused a 7-hour-47-minute outage affecting authentication, Actions, pull requests and Copilot, and GitHub is migrating to multi-region Azure deployments and refactoring Git to decouple storage from compute.
Rohan Paul proposes that the agent economy is taking over. He cites data saying that GitHub recorded 7.38 billion commits in September 2026, more than five times the figure a year earlier. To handle the flood of code generated by agents, GitHub has added 4 million CPU cores, 160PB of high-speed storage and 50Tb/s of network capacity this year. A traffic surge on August 17 caused a 7-hour-47-minute outage affecting authentication, Actions, pull requests and Copilot, and GitHub is migrating to mul
On October 29, 2026, AYi open-sourced the source code and core System Prompt of the "emotional intelligence plugin" tool. According to an article published by AYi AI Notes, the tool was built using Cursor together with Claude Opus 5.5; it is a zero-dependency local web tool that can rewrite emotionally charged drafts according to the four elements of Nonviolent Communication, and comes with seven built-in categories of communication counterparts and three tone levels: gentle, firm, and direct. The tool runs locally at 127.0.0.1:8787, and fixed HTTPS links are generated through the UUMit client for distribution to colleagues, with no need to purchase servers or complete filing, and permissions can be granted and revoked on a per-person basis. The article also provides an 800-character limit per input, default rate limits of 10 times per minute and 200 times per day, as well as the source code and System Prompt in two GitHub repositories. There are currently no further developments.
ct. The tool runs locally at 127.0.0.1:8787, and fixed HTTPS links are generated through the UUMit client for distribution to colleagues, with no need to purchase servers or complete filing, and permissions can be granted and revoked on a per-person basis. The article also provides an 800-character limit per input, default rate limits of 10 times per minute and 200 times per day, as well as the source code and System Prompt in two GitHub repositories. There are currently no further developments.
On October 28, 2026, Entire, founded by a former GitHub CEO, launched a new-generation Git hosting platform aimed at human-machine collaborative coding, redesigning code hosting, review, CI, and Agent session memory around human-machine collaboration. The platform replaces the diff-centric PR timeline with Trail; each push is scored by a review Agent in a cloud sandbox that tracks unresolved issues, calling Claude Code, Codex, and others under the hood, with sandboxes provided by Daytona and E2B. Its self-developed Git service offers its own open-source benchmark, claiming pushes are up to about 89 times faster than GitHub, and it has integrated Buildkite and Depot as CI. There is currently no information on subsequent developments.
On October 28, 2026, Entire, founded by a former GitHub CEO, launched a new-generation Git hosting platform aimed at human-machine collaborative coding, redesigning code hosting, review, CI, and Agent session memory around human-machine collaboration. The platform replaces the diff-centric PR timeline with Trail; each push is scored by a review Agent in a cloud sandbox that tracks unresolved issues, calling Claude Code, Codex, and others under the hood, with sandboxes provided by Daytona and E2B
Serro has released "Agentic TPM," designed to keep coding agents in sync when the decisions they rely on change. The product connects to Slack, Linear, GitHub, Jira, Zoom, Notion, email, and code repositories, maintains a versioned record of each project's decisions, owners, risks, and history, and treats agent failures as coordination problems. The news was reported by Rohan Paul on October 30, 2026, and there have been no further developments so far.
On October 28, 2026, Unsloth announced that local LLMs can now take over the browser and complete tasks autonomously. According to its published information, Qwen3.8-27B completed operations such as playing chess and drawing without human intervention, and the tweet also provided links to the GitHub repository and a companion guide. Currently, this news comes from Unsloth's first-party release, and there are no independent reports or follow-up developments from other sources.
Ethan Mollick said he had Opus build a game that converts JIRA tickets from any real project into dramatized audio logs, serving as the storyline of a 2000s-style horror game set in a mysterious abandoned space station. The post includes a playable demo and a GitHub link. There is currently no information on further developments.
The author of Pico CSS announced that the project is no longer maintained; the GitHub repository was archived as read-only on October 4, 2026, and will no longer accept new issues, PRs, or release new versions. The author stated that AI can now generate lightweight, standalone, and accessible HTML on demand, which reduces the significance of a minimal CSS framework; to keep up with the times, it would need to adopt modern CSS and be rewritten, which would be a different project. npm, the jsDelivr CDN, and picocss.com will remain online for the long term, and the project remains under the MIT license and can be freely forked, but the name and logo are not covered by the MIT license.
The author of Pico CSS announced that the project is no longer maintained; the GitHub repository was archived as read-only on October 4, 2026, and will no longer accept new issues, PRs, or release new versions. The author stated that AI can now generate lightweight, standalone, and accessible HTML on demand, which reduces the significance of a minimal CSS framework; to keep up with the times, it would need to adopt modern CSS and be rewritten, which would be a different project. npm, the jsDeliv
heise online launches the iX workshop "Programming More Efficiently with AI Assistants," using GitHub Copilot as an example to guide developers through prompt techniques, Spec-Driven Development and Agentic Coding, and to distinguish these from Vibe Coding. The course also covers the architecture, features and pricing of Cursor, Claude Code, OpenAI Codex and Kilocode, and explains how MCP and RAG connect to external tools and your own data. The workshop takes place online on December 15–16, 2026, and is led by Rainer Stropek.
heise online launches the iX workshop "Programming More Efficiently with AI Assistants," using GitHub Copilot as an example to guide developers through prompt techniques, Spec-Driven Development and Agentic Coding, and to distinguish these from Vibe Coding. The course also covers the architecture, features and pricing of Cursor, Claude Code, OpenAI Codex and Kilocode, and explains how MCP and RAG connect to external tools and your own data. The workshop takes place online on December 15–16, 2026
On October 26, 2026, Entire added free direct hosting for private repositories to its human-AI collaborative development platform, allowing users to use it without keeping the original repository on GitHub. According to gihyo.jp, the platform also offers agent code review and a Continuous Memory feature that lets AI agents in new sessions refer to policies established in previous sessions. Hosting is free, and billing is based only on the amount of AI model usage by agents. The accompanying EntireDB stores complete copies of repositories by region to distribute read load, and is planned to be open-sourced within a few months. There are currently no further developments.
, Entire added free direct hosting for private repositories to its human-AI collaborative development platform, allowing users to use it without keeping the original repository on GitHub. According to gihyo.jp, the platform also offers agent code review and a Continuous Memory feature that lets AI agents in new sessions refer to policies established in previous sessions. Hosting is free, and billing is based only on the amount of AI model usage by agents. The accompanying EntireDB stores complet
chieve real-time generation at over 24 frames per second at 720p on a single consumer-grade RTX 5090. The open-source content includes the 5-billion- and 14-billion-parameter model weights, real-time video generation code, the EdenGolem v0.1 skill for turning text into simple games, and a complete toolchain from prompts to game front ends. The code is released on GitHub under the Apache 2.0 license, and the weights are available on Hugging Face. No further progress has been disclosed at present.
On October 30, 2026, Microsoft opened the public beta of the GitHub Copilot agent harness through the Foundry Agent Service in Microsoft Foundry. The harness provides built-in sandboxing, reusable skills, MCP integration, and sub-agent support; the same harness already supports Copilot Code, Copilot Studio, GitHub Copilot, CLI, and VS Code. When creating a prompt agent, this harness must be selected and cannot be changed afterward; CPU, memory, and idle duration are controlled by Microsoft, and bring-your-own-model is not supported. The service is free until December 1, 2026, after which it is billed at $0.0994 per vCPU-hour and $0.0118 per GiB-hour, with model inference and some tools billed separately.
On October 30, 2026, Microsoft opened the public beta of the GitHub Copilot agent harness through the Foundry Agent Service in Microsoft Foundry. The harness provides built-in sandboxing, reusable skills, MCP integration, and sub-agent support; the same harness already supports Copilot Code, Copilot Studio, GitHub Copilot, CLI, and VS Code. When creating a prompt agent, this harness must be selected and cannot be changed afterward; CPU, memory, and idle duration are controlled by Microsoft, and
Reflex has completed a $14 million Series A funding round led by Standard Capital, with participation from Databricks Ventures, Y Combinator and others, bringing its cumulative funding to $19 million. According to SiliconANGLE, Reflex's "software factory" workflow lets enterprises describe requirements in natural language to build, deploy and maintain their own business applications, which can run on public clouds, in on-premises data centers, or in air-gapped environments. Reflex originated from an open-source Python framework, with nearly 30,000 GitHub stars and 400,000 monthly downloads; Dell used it to build a server monitoring system for more than 6,000 employees. No follow-up developments are available at this time.
lex's "software factory" workflow lets enterprises describe requirements in natural language to build, deploy and maintain their own business applications, which can run on public clouds, in on-premises data centers, or in air-gapped environments. Reflex originated from an open-source Python framework, with nearly 30,000 GitHub stars and 400,000 monthly downloads; Dell used it to build a server monitoring system for more than 6,000 employees. No follow-up developments are available at this time.
On October 30, 2026, ScienceNet published an interview report mentioning that the Institute for Advanced Study in Mathematics of Zhejiang University and Zhijiang Laboratory jointly launched the Future Mathematics Program. The report stated that the program focuses on four areas: mathematical foundation models, formal verification, AI mathematical mechanisms, and interdisciplinary empowerment. Li Jianshu, an academician of the Chinese Academy of Sciences, said in the report that AI may change the paradigm of mathematical research, and pointed out that mathematics has done far from enough for AI; Wang Jian, an academician of the Chinese Academy of Engineering, believes that AI's reasoning ability currently comes mainly from code, and that learning deeper reasoning from mathematical data will bring greater gains. The report also mentioned that Google DeepMind's AI agent solved 9 previously unsolved Erdős problems and tackled 44 open mathematical conjectures in May this year, and that OpenAI recently published 722 mathematical manuscripts generated by its internal AI models on GitHub, while 25 Fields Medalists including Terence Tao and Deng Yu jointly issued an open letter warning of a serious misalignment between AI and mathematics. Currently, no further progress on the program has been disclosed.
gains. The report also mentioned that Google DeepMind's AI agent solved 9 previously unsolved Erdős problems and tackled 44 open mathematical conjectures in May this year, and that OpenAI recently published 722 mathematical manuscripts generated by its internal AI models on GitHub, while 25 Fields Medalists including Terence Tao and Deng Yu jointly issued an open letter warning of a serious misalignment between AI and mathematics. Currently, no further progress on the program has been disclosed.
On October 30, 2026, Ant Group's inclusionAI open-sourced the ZwZ model family and the ZoomBench fine-grained perception benchmark as companion results to an ICML 2026 paper. According to the introduction of inclusionAI's new GitHub repository, the ZwZ model family includes three sizes—4B, 7B, and 8B—and achieves SOTA on multimodal perception benchmarks among open-source models, requiring only a single forward inference pass and no tool calls at inference time. Its method is Region-to-Image Distillation (R2I), which distills high-quality VQA supervision generated from enlarged local regions back into the full image, with 37K training samples. The simultaneously released ZoomBench contains 845 VQA items covering 6 fine-grained perception dimensions, and Qwen2.5-VL-7B achieves only 42.5% average accuracy. There are currently no further developments.
pen-sourced the ZwZ model family and the ZoomBench fine-grained perception benchmark as companion results to an ICML 2026 paper. According to the introduction of inclusionAI's new GitHub repository, the ZwZ model family includes three sizes—4B, 7B, and 8B—and achieves SOTA on multimodal perception benchmarks among open-source models, requiring only a single forward inference pass and no tool calls at inference time. Its method is Region-to-Image Distillation (R2I), which distills high-quality VQ
Ant Group's GuangJian team has open-sourced the visual forensics model DefakerOne2 on GitHub and released the model weights. The model is built on the Qwen3.5-2B multimodal backbone with 2B parameters, covering AI-generated content, DeepFake faces, document tampering, natural image tampering, face and ID anti-counterfeiting, and AI-generated video detection. The team says the model was trained on about 50 million samples, using a three-stage Tide-Style Tuning process from LoRA to full parameters and back to LoRA, and employs entropy-based test-time routing to choose between the video and frame pathways. The team also says it achieved SOTA on 40 of 53 detection benchmarks and on 11 of 14 localization benchmarks, and that the weights and the RRVBench benchmark have been released on ModelScope.
Ant Group's GuangJian team has open-sourced the visual forensics model DefakerOne2 on GitHub and released the model weights. The model is built on the Qwen3.5-2B multimodal backbone with 2B parameters, covering AI-generated content, DeepFake faces, document tampering, natural image tampering, face and ID anti-counterfeiting, and AI-generated video detection. The team says the model was trained on about 50 million samples, using a three-stage Tide-Style Tuning process from LoRA to full parameters
On October 27, 2026, Axiom Math released what it calls the first complete computer-verified proof of the classification of finite simple groups (CFSG). According to Unite.AI, the project was directed by engineers and mathematicians commanding dozens of AI agents, who in 24 days wrote approximately 43.1 million lines of Lean code; the project page lists 2.05 million declarations and a corpus of 715 papers and books, and the code is a Lean 4 proof containing no sorry, pinned to version 4.35.0-rc3, built on Mathlib and TauCeti, and licensed under Apache-2.0. Phoenix Technology reported the same day that during the process the agents found 34 discrepancies in the literature, including a counterexample to a closure assertion in John Walter's 1986 study of unbalanced group theorems, and participated in constructing and formalizing a new result, "Preservation of simple tops," written into a 35-page paper as Theorem 2.3. The project has been uploaded to GitHub, with the claim that the final proof contains no sorry and relies only on standard axioms, and the repository's review status is a team self-assessment.
process the agents found 34 discrepancies in the literature, including a counterexample to a closure assertion in John Walter's 1986 study of unbalanced group theorems, and participated in constructing and formalizing a new result, "Preservation of simple tops," written into a 35-page paper as Theorem 2.3. The project has been uploaded to GitHub, with the claim that the final proof contains no sorry and relies only on standard axioms, and the repository's review status is a team self-assessment.
On October 28, 2026, Phoenix Technology reported that placeholder code for DeepSeek-V5, V5-open, V5-next, and others had appeared in the official DeepSeek Harness code repository, and that the official team had made advance preparations for the V5 series release. The report noted that these code entries are currently only placeholders; when released in the future, the server side will only need to modify /models to go live, with no client release required. Among them, V5-open follows a "no version threshold" path, while V5-next follows a "client upgrade required" path. On October 30, TMTPost·AGI further reported that these model names appeared in the test code of the official DeepSeek Harness GitHub repository, corresponding respectively to three release paths: unrecognized by the current client, usable directly on any version, and requiring a DSH upgrade to use. Among them, deepseek-v5-next requires a minimum version of 99.0.0-alpha.1, while the publicly available DSH version remains at 0.2.x. The report also stated that these entries were uploaded on September 24, 2026, by DSH core contributor Jiang Yichen. There is currently no official release information.
ile V5-next follows a "client upgrade required" path. On October 30, TMTPost·AGI further reported that these model names appeared in the test code of the official DeepSeek Harness GitHub repository, corresponding respectively to three release paths: unrecognized by the current client, usable directly on any version, and requiring a DSH upgrade to use. Among them, deepseek-v5-next requires a minimum version of 99.0.0-alpha.1, while the publicly available DSH version remains at 0.2.x. The report a
On October 28, 2026, heise online reported that developer Brandon Thomas's ArtCraft project uses AI agents such as Claude Code and GitHub Copilot, with natural-language prompts assisting development of open-source alternatives to several Adobe and Microsoft programs, including PhotoCraft, a replica of Photoshop. The report also noted that such "vibe-coding" software, when replicating existing proprietary software, may simultaneously implicate copyright, patent, and trademark rights, with the risk falling mainly on the manufacturers and suppliers that distribute such software, while the risk borne by users is relatively small. The report did not mention any subsequent progress of the project or related legal action.
On October 28, 2026, heise online reported that developer Brandon Thomas's ArtCraft project uses AI agents such as Claude Code and GitHub Copilot, with natural-language prompts assisting development of open-source alternatives to several Adobe and Microsoft programs, including PhotoCraft, a replica of Photoshop. The report also noted that such "vibe-coding" software, when replicating existing proprietary software, may simultaneously implicate copyright, patent, and trademark rights, with the ris