Open source

AIAnthropic launches OSS Scanner, a free service that gives opt-in open-source projects periodic security scans by its strongest models, including Claude Mythos. The reports are fully model-generated without human review or triage, so Anthropic says some may be incorrect or invalid.

AIThariq, who works at Anthropic, accidentally made public the GitHub repo for ai-newtab, a Chrome extension he uses daily. It replaces the new tab page with an AI-generated homepage built each day from sites he reads.

AIMidjourney's alpha site now lets users share folders with others as Collaborators or Viewers, with sharing by link also available. A new thinking mode lets users rerun jobs made with 8.2 standard and edit models to fix missed prompt details such as objects, layout, anatomy, and text. Sharing does not change image privacy, so non-stealth images can still appear on Explore and profiles.

AIAnthropic is launching OSS Scanner, a service that uses its frontier models to periodically scan opted-in open-source projects for vulnerabilities at no cost. Its reports provide a proof-of-concept, an explanation, and a suggested fix.

AIThariq (@trq212) says the project is built on Claude Managed Agents, with code generated in a cloud sandbox using Sonnet 5.5. He puts each run at about $0.75 and links the GitHub repository for trying it.

AIRembrandt is a free, open-source photo editor for macOS, Windows and Linux that runs locally and needs no account or subscription. It saves edits as standard XMP sidecar files next to each photo and can also run as a self-hosted server accessed through a browser. Only optional cloud sync is paid.

AIAn astrophysicist worked with Claude Science to create the first complete ultraviolet map of the sky, covering regions never observed in UV. Claude located existing datasets, combined them, and filled gaps with statistical inference, taking a few days rather than weeks of human work. The map is presented as a teaching tool and an example of low-priority scientific work that AI now makes feasible.

AIClaude Code v2.1.295 adds onFailure: "block" for command and HTTP hooks, so a hook that cannot start, times out, or exits unexpectedly blocks the action. The release also adds an optional models list for Claude apps gateway upstreams, plus upstream_request_id in the inference audit event, and fixes a range of MCP, plugin, and terminal issues.

AISherwin Wu, an OpenAI employee, says the updated Harvey LAB-AA v1.1 benchmark, announced by Artificial Analysis with Harvey, is more useful than the original LAB results. The new Hallucination-Gated All-Pass Rate credits a task only when every rubric criterion passes and no material hallucination appears. Grok 4.7 (xhigh) leads at 9.4%, while GPT-6 Astra (max) at 8.6% has very few material hallucinations.

Why it matters: The update adds a hallucination gate to a legal benchmark, showing that models with high all-pass rates can rank much lower once material errors count.

AIOpenAI's Codex 0.162.0 release adds tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. The update also lets users pin tasks in the agent Command Center, copy transcript blocks with /copy, and make URLs clickable in approval headers, questions, and warnings, along with several Linux and Windows sandbox fixes.

AITessl's talk at AI Native DevCon London argues that agent skills, which can be markdown files with instructions and bundled material, act as supply chain components that can shape agent behavior. The author says reading SKILL.md once is insufficient because risks can sit in supporting files, updates, and workspace trust settings. He identifies the danger as the combination of private context, untrusted content, and external communication, and cites research scanning roughly 4,000 public skills for issues including malware-like behavior.

AIMozilla.ai's cq project proposes a shared knowledge layer where AI agents capture lessons from non-obvious fixes as structured knowledge units that other agents can later query. The default setup is local-first, using a local SQLite database so nothing leaves the machine, with an option to connect to a remote team server that adds review.

AILauren Tan invites users of Grok Bot on Omarchy and developers building plugins for it to share feedback and feature requests. The post points to the Omarchy plugin catalog and asks what integrations could be supported. Background from DHH says SpaceXAI joined the Omacom Foundation as a Founding Corporate Patron, contributing $1,500,000 in Grok tokens for Omarchy's maintenance and development.

AISpaceXAI has joined the Omacom Foundation as a Founding Corporate Patron, providing $1,500,000 in Grok tokens for Omarchy's maintenance and development. The main post says the company is glad to support the Omarchy team.

AINVIDIA Dynamo uses a unified session-level identifier to make its inference stack aware of agent sessions, subagents, and their KV cache across turns and tool calls. On SWE-bench, two TP4 MiniMax-M2 replicas on one 8xH100 node gained roughly 12-16% throughput from program-aware scheduling over KV-aware routing alone. The post also describes experimental shared-pool indexing and a proposed KvHint interface for session-aware cache policies in vLLM and SGLang.

Why it matters: The post explains how session identifiers let an inference stack track agent working sets, with measured throughput gains on SWE-bench and agentic RL rollouts.

AIMistral Large 4 and Reflection Beam are previewed now, with Mistral saying weights drop at the end of October and Reflection promising Apache 2.0 weights this month. The post argues that these announced future weights should be treated as a conditional migration dependency, not a current self-hosting option. API previews can be trialed immediately, but they do not prove an unreleased checkpoint will behave the same when downloaded.

AIPocketty is a $99 iPhone and iPad SSH terminal, with a 14-day free trial, that notifies you when an herdr-managed agent is blocked or done. The alert is sealed on your computer for your phone only, and tapping it opens that exact Pane over SSH so you can answer in a real terminal. The source says the relay forwards only sealed bytes and that terminal traffic goes directly between the app and your computers.

AISpaceXAI joins the Omacom Foundation, which oversees the Omarchy Linux distro, as a Founding Corporate Patron and donates $1.5 million in Grok tokens. According to David Heinemeier Hansson's blog post, the tokens will primarily accelerate development, review code, and patch bugs. The article notes Hansson's recent anti-immigration blog posts, and that 1Password and Cloudflare have also faced criticism for contributing to Omarchy.

AIHugging Face is asking users to try Paper Pages at to help keep scientific research open. The post provides no further technical details, figures, or feature specifics about the platform.

AIAI SRE Arena is an open, vendor-neutral benchmark that injects faults into a disposable Kubernetes fixture and scores AI SRE investigations with a configurable judge. In its first published comparison across 21 incident scenarios, Edge Delta's native AI investigations detected 18 of 21 incidents, and Grafana's detected 12. Claude, run through each vendor's observability CLI, reached 90.5% root cause analysis accuracy with Grafana's CLI and 85.7% with Edge Delta's.

AICursor says it is excited to support open-source software alongside SpaceXAI, and it plans to bring more projects on board soon. Background from DHH indicates SpaceXAI joined the Omacom Foundation as a Founding Corporate Patron, contributing $1,500,000 in @grok tokens for maintaining and developing Omarchy.

AITessl's blog post argues that repository automation needs Continuous AI, a third pillar alongside CI and CD for scheduled, auditable AI workflows that improve repositories over time. The article describes GitHub Agentic Workflows, which harden agentic workflow specifications into GitHub Actions that can run coding agents such as Claude Code, Copilot CLI, Gemini CLI, or Codex-style agents. It emphasizes read-only agent steps, restricted outputs, and human review of pull requests.

AIRSIGym provides a research agent with training, inference, evals, and sandboxes as callable services, so it spends its budget on experiments rather than rebuilding infrastructure. With Opus 5 as the researcher, the improved system rose from 17.67% to 50.33% on SWE-bench Verified. The post also highlights a way to measure co-evolution between harnesses and models.

AIJevman is an open-source Pac-Man benchmark where AI models play 100 games each against the classic scripted ghosts. Each model gets a maze state at every junction and returns a direction probability, with answers over 2 seconds replaced by a backup rule. Community models can join the leaderboard by submitting games that CI replays to verify their scores.

AIUnsloth now supports OS-level sandboxing on Linux via bwrap, on Mac via seatbelt, and on Windows via Microsoft's MXC. Per-tool-call latency is under 100ms across all three, and its software-style sandboxing with regex AST checks adds about 3ms. The Windows integration was built in collaboration with Microsoft.

AIOpenClaw released its v2026.9.9 patch, adding support for GPT-6.1 Sol in Codex and Claude Haiku 5.5. The update also improves recovery from failed updates, fixes missing iMessage replies, and resolves scheduled-job issues. The release credits 90 contributors.

AIJetBrains has released Mellum2.1, a 12B mixture-of-experts thinking model with 2.5B active parameters, under Apache 2.0 on Hugging Face. Post-training reinforcement learning in real software repositories raised SWE-bench Verified from 2.0 to 47.0, according to JetBrains' self-reported results. Qwen3.5-9B still leads on SWE-bench Pro, GPQA Diamond and AIME, and GGUF builds start at 7.0 GB for local use.

AIGoodfire Research describes probe-based cyber monitors for Kimi K3 and GLM 5.3 deployed on a production inference stack. The probe filters suspicious exchanges before an LLM judge reviews them, reaching about 93% recall at a 5.5% benign-session interruption rate at roughly 50x lower judge cost. In FAR.AI's red-teaming, the monitor reduced universal jailbreaks to zero across 140 tested strategies.

AIJulien Chaumond, Hugging Face's account, mocked the idea of needing US or Chinese rivals when European partners exist. The remark responds to Berlin-based search engine Ecosia dropping French AI partner Mistral in favor of open-source models, including those from China.