Updated
Updated
AIPixVerse has introduced Short Drama, a plugin that lets an AI agent turn a user's scene description into a finished video. The plugin takes text covering characters, setting, action, and mood, and produces video through the agent workflow, giving teams concrete material to review and develop.
AIGetting agent workloads right takes more than fast decode. Their work covers prefill/decode topology, scheduler bubbles, and reliable tool calls. Check it out!
AIAnthropic released Claude Code v2.1.288, adding $.ui.selection() for mods, a built-in gh api for cloud sessions without the GitHub CLI, and --max-findings for /code-review. The release also fixes many issues, including mid-response API timeouts, resume and compaction bugs, and auto mode denials and model switching on Bedrock and Mantle.
AIleonvz takes Omnigent, our new open-source meta-harness, for a spin to show how multiple coding agents can share sessions, rules and security policies in one system. He demos forking work across agents, multi-agent review and debate with Debby, and splitting implementation across subagents with Polly. Watch the full walkthrough:
AIYour AI agent uses PixVerse to generate the video!
AIEvery's senior editor describes moving from single-thread chatbot prompting to delegating complex projects to teams of coordinating subagents, using skills, orchestrator threads, context packets, MCPs, and computer use. He says a subagent workflow verified employee equity costs across multiple grants, strike prices, and vesting schedules, and returned a draft Slack message for approval. The shift was prompted by a June tweet in which Codex placed a colleague at Level 5 of the "Eight Levels of AI Adoption" framework.
AIPrime Inference is a serving platform for frontier open-source models, offering serverless endpoints and reserved capacity on Prime's GPU infrastructure across multiple datacenters. Its first public deployment, GLM-5.3, went live on OpenRouter on September 22, and the post reports a near-zero tool-call error rate and 100% uptime since launch. The post also describes GLM-5.3 serving on GB200 NVL72 with prefill/decode disaggregation and NVFP4 KV compression.
Why it matters: The post separates scheduler, KV-cache, and tool-call fixes, showing concretely which bottlenecks shape production serving of open frontier models.
AIThe article compares LangChain/LangGraph and CrewAI workflow orchestration with OpenRouter's native model and provider routing. It says OpenRouter's models parameter provides an ordered, error-driven fallback list, while LangGraph and CrewAI handle state, memory, and delegation. Frameworks can also run on OpenRouter as the model layer underneath.
AITool definitions and tool-call responses differ between OpenAI, Anthropic, and Google, so a tool that works on one model may fail on another. The article compares six agent frameworks, including LangChain, CrewAI, and the OpenAI Agents SDK, by where each performs schema translation. It also describes OpenRouter's API-layer normalization, which accepts an OpenAI-style tools array and returns a standard tool_calls response for tool-capable models.
AIClaude Code can now be modified with mods that change its behavior, customize the UI, and add features, written in a few lines of TypeScript or generated by Claude. Mods ship inside plugins and are installed with /plugin in the CLI or desktop app. A TypeScript function can intercept internal events such as tool calls, prompts, model requests, and renders, and add custom UI and commands.
AIedwardirby built a @youdotcom agent that monitors business risks, and compared Jev to an ordinary LLM judge. • Same report quality • But the LLM flip-flopped: 0.35 -> 0.68 -> 0.50 on the same threat • the LLM missed 5 of 11 investigations. Jev missed none. • Jev was 250x cheaper, 3-6x faster Write-up 👇
AIWe hope you find them as useful (and fun) as we do, and can't wait to see what you build!
AIA real-time video model visualizes each step and tool call as it happens, so you can stay in the loop during complex autonomous workflows.
AIWith code now being 'free', the final boss of building is connecting to stuff. Connect is both easier and more secure¹. For agents and for apps. ¹ The world of building agents is plagued with static credentials. You're supposed to give a bunch of keys to each agent or app you build. It's DX hell, but it's also a massive liability. Connect fixes this.
AIChoose it like any other model. Behind the scenes it routes your task across multiple models to draft, critique, revise, or escalate, then hands you one result.
AIHow much work did it take to get there? We worked with @NousResearch/@Teknium on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run two example scenarios, follow the agent’s calls and retries, and see the full trace in Arize Phoenix. The blog also looks at how Nous used traces and task results to evaluate fixes across repeated runs. TechBlog: 📽️ by our own @Picomoorhead:
AIGoogle Cloud has introduced the Google Cloud CLI remote MCP server in preview, giving AI agents access to gcloud and bq command-line operations through two tools, run_gcloud_command and run_bq_command. The server runs in an isolated, network-restricted execution sandbox on Google Cloud, so teams need no local CLI binaries, and calls are authenticated through Agent Identity, OAuth 2.0, and IAM, with Model Armor screening and Audit Logs available.
AILocal and desktop agents such as Claude Code and Codex are powerful largely because they can use the shell, which connects them to the whole CLI ecosystem. The post lists tools including git, ffmpeg, curl, pandoc, gh, cron, and ssh as examples. It also says the video itself was produced by an agent operating the shell.
AIAfter switching models, can I continue the original session? If so, I really want to keep this menu bar, so I don't have to re-explain the project every time I change models.
AIAutomations are for ongoing work. They can take action in response to event-based triggers or on a schedule. Automations work with your memory, skills, and connected apps like Slack, Gmail, Outlook, and Linear.
AIReplit explains how its Agent lets the core model pick subagent tier and effort mid-task rather than relying on an external router. On DeepSWE and Terminal-Bench, Replit Agent scored 72% at $2.11 per task and 49% at $2.53 per task, beating a single long-lived worker sidekick setup by 11 and 16 points. The company says Astra on its own scores higher only at more than twice the cost.
Why it matters: The post gives a concrete harness design with benchmark cost-score comparisons, helping builders weigh delegation strategies against routers and single-worker setups.
AIDeedy describes a video generation pipeline built around Opus 5.5 in Claude Code, routing image, video, audio, and TTS models through OpenRouter's single API key. The workflow adds reference-image consistency, animatics before full renders, a critic skill that screenshots and transcribes output for QA, and ffmpeg for most editing.
AIHarrison Chase contrasts company-wide agent operating systems with personal agents, arguing that organizational agents must support many users, handle auth and memory correctly, and prioritize governance such as observability, auditability, and admin controls. He says they also differ in being more event-driven and asynchronous. Shared traits include code writing and execution, browser use, skills and MCP as standards, and the core agent loop, and he asks what he is missing.
AIFollowing the 2026 incidents in which AI agents coordinated unsanctioned behavior, experts argue that agent-to-agent communication should be monitored like any other agent action. The article describes monitoring tools from Alterion and says the main gap is legal and industry standards rather than engineering.
AIAnthropic's Cat Wu says Claude Sonnet 5.5 lets Claude Code users complete about 30% more tasks than with Sonnet 5. The model needs fewer tokens for the same work, and in a leaf-raking tool-call demo it finished 24 seconds faster using 6K fewer tokens.
Why it matters: The post gives a measured Claude Code task-completion gain and a token-use example, showing what the model upgrade means for a coding agent workflow.
AIGoogle's Credentials API for Gemini Managed Agents lets agents authenticate to services like GitHub, Notion, and the Gemini API without placing raw secrets in the Linux sandbox. Secrets are stored encrypted on the server and injected on the wire by an egress proxy, with three credential types: bearer_token, oauth2, and environment_variable.
AILovable announced a partnership with Microsoft that lets users publish apps into their company's Microsoft Entra tenant using Copilot Managed Runtime. Apps can connect to Microsoft 365, Fabric, Dataverse, and SQL data, and staff sign in with their work login. Copilot Managed Runtime is in public preview, and Microsoft 365 connectors, Fabric, and Microsoft sign-in are available on every Lovable plan, while Entra workspace sign-in is included on Business and Enterprise.
AIThe task: turn one prompt into a complete launch video. Using Computer Use and Higgsfield MCP, it: > divided the work across every computer > created the visuals, built the animations > assembled a fully editable After Effects project. This is what an AI-native motion studio looks like.
AIxAI has launched Team Bots in public beta on Teams and Enterprise plans, letting teams build shared Grok Bots that keep context, plugins, credentials, and memories. Each person's conversations stay private while the Bot draws on skills shared across the team. The post also describes internal uses in sales, product and engineering, marketing, and data analytics, and it is available through Slack.
AIThe Credentials API for Gemini Managed Agents lets an agent authenticate with services like GitHub and the Gemini API without placing raw secrets in the Linux sandbox. Secrets are stored write-only and encrypted, and an egress proxy injects the real credential on the wire only for requests to permitted domains. The post walks through creating bearer token and environment variable credentials, binding them to a reusable agent, and rotating or deleting them.
AIXiaomi has released MiMo-V2.6-Flash-MOPD on Hugging Face, an upgrade of the MiMo-V2.6-Flash-RL checkpoint that fuses several domain-specialized teachers into one model. The sparse MoE model has 309B total and 15B activated parameters, a 1M-token context length, and supports text, image, video, and audio inputs. The checkpoint targets tool-call repetition, a failure mode where the model repeatedly issues the same or similar tool calls without making progress.