Skip to contentSkip to stories

Updated

Agents

Showing low-relevance items too. Hide low-relevance items

Sep 29

Sep 29Tue
  1. Mastra BlogOfficialAI score42

    Mastra adds memory hooks to monitor and transform agent observations

    AIMastra says it now lets developers add lifecycle and transform hooks to its observational memory system. Lifecycle hooks log cycle starts and ends with token usage, while transform hooks can modify observations and reflections before they are stored. The release also includes skillResultRedactor(), which replaces skill file contents in tool results with a placeholder so the agent still remembers the skill.

  2. Manus BlogOfficialAI score50

    Manus Flex lets users connect their own API keys to the Manus workspace

    AIManus is launching Manus Flex, a module that lets users power Manus agents with their own API key from a supported inference provider. Model inference is billed directly by that provider, while other services used in Manus tasks still consume Manus credits. OpenRouter, Fireworks, and Modal are announced as initial inference partners for the Flex Inference Partner Program.

  3. OpenAI API ChangelogOfficialAI score62

    OpenAI adds computer use to its Agents API

    AIOpenAI added computer use to the Agents API, letting agents complete tasks in an OpenAI-hosted browser. Website access approvals and sign-in are handled by the developer's application.

    Why it matters: The changelog specifies that browsing runs in an OpenAI-hosted browser while the developer's application handles approvals and sign-in, which clarifies responsibility for integrations.

  4. OpenAI API ChangelogOfficialAI score65

    OpenAI releases GPT-6.1 Sol for complex coding and professional work

    AIOpenAI has released GPT-6.1 Sol (gpt-6.1-sol) for complex coding and professional work, at a lower cost than GPT-6 Astra. For prompts up to 272K input tokens, standard pricing is $2 per 1M input tokens, $0.10 cached input, $2.50 cache write, and $10 output. The model also supports Multi-agent in beta, letting it delegate work to subagents in a Responses API request.

    Why it matters: The changelog gives per-token pricing and a multi-agent beta, showing how the model compares in cost with GPT-6 Astra for developers planning coding workloads.

Sep 28

Sep 28Mon
  1. Latent.SpaceXAI score43

    Thariq Shihipar on Claude Code's future, mods, and multiplayer agents

    AIAnthropic's Thariq Shihipar discusses why prompting remains a high-leverage agentic coding skill and why Claude.md may eventually disappear. He also covers Claude Mods for customizing the Claude Code harness, mutable software, multiplayer agents, and Claude Tag, plus security concerns raised when agents hacked Hugging Face.

    Video from @latentspacepod's post
  2. DatabricksOfficialAI score38

    Claude Sonnet 5.5 now available on Databricks across AWS, Azure, GCP

    AIDatabricks now offers Anthropic's Claude Sonnet 5.5 on AWS, Azure, and GCP, governed through Unity Gateway. The post says Sonnet 5.5 is more efficient than Sonnet 5 for coding and agentic use and reaches Opus 5-level accuracy on document understanding, parsing, and search. It joins Claude Opus 5.5, Claude Fable 5.1, and 60+ other open-source and frontier models on the platform.

    Video from @databricks's post
  3. Lydia Hallie ✨XAI score22

    Claude Code Projects default effort level and override setting

    AIAnthropic's Lydia Hallie asks users who raised the main chat's effort in Claude Code Projects to explain why, since the default is low because it mainly coordinates threads. She notes the defaults can be overridden in Project settings, where Sonnet 5.5 is also available.

    Image from @lydiahallie's post
  4. IEEE Spectrum · AINewsAI score25

    Charlie Kemp Builds Assistive Mobile Robots to Help People Live Independently

    AICharlie Kemp, cofounder and chief technology officer of Hello Robot, develops mobile manipulators with arms to physically assist older adults and people with disabilities in homes and workplaces. His work began with humanoid robots at MIT and led to assistive robotics research, including a collaboration with Henry Evans through the Robots for Humanity effort. The profile is part of IEEE Spectrum's "A Day in the Life of a Roboticist" series.

  5. Grok BotOfficialAI score45

    SpaceXAI launches Team Bots public beta for Teams and Enterprise

    AISpaceXAI says its Team Bots, which prep account teams, coordinate engineering work, answer data questions, triage customer feedback, and run hiring loops, are now in public beta for Teams and Enterprise customers. The post links to a full announcement at

  6. Andrew NgXAI score46

    Andrew Ng says OpenWorker will use Nvidia OpenShell for sandboxed AI agents

    AIAndrew Ng says OpenWorker, his open-source agent harness for cybersecurity workflows, will run each agent's commands inside a sandbox built on Nvidia OpenShell. The sandbox limits files to those relevant to the task and keeps secret API keys, browser login credentials, and arbitrary website access out of the agent by default. Restrictions are enforced in deterministic code rather than by prompting an LLM, and all actions are logged for monitoring and audit.

  7. Perplexity DevelopersOfficialAI score44

    Perplexity adds reusable custom agents to its Agent API

    AIPerplexity says developers can now build custom reusable agents in its Agent API using Profiles, Skills, and managed connectors. Agents are configured once in the API Portal and can then be reused across applications and workflows.

    Video from @perplexitydevs's post
  8. Google AIOfficialAI score44

    Google Labs expands experimental CC agent into a family group assistant

    AIGoogle Labs has expanded Project CC, its experimental AI productivity assistant, into a group agent designed to streamline family household logistics. CC has its own verified Google account and email, so families can share documents and calendars and auto-forward selected emails without sharing passwords or exposing their full inboxes. The post says CC runs on the latest Gemini models in isolated cloud environments, and it is available via a waitlist.

  9. catXAI score72

    Claude Sonnet 5.5 Lifts Claude Code Task Completion by About 30%

    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.

    Video from @_catwu's post
  10. RadixArkOfficialAI score46

    RadixArk releases Miles v0.1.1 with multi-LoRA and new model support

    AIRadixArk says Miles v0.1.1 adds multi-LoRA with Tinker API compatibility, which lets multiple training jobs share one base model. The release also adds native agentic training with Claude Code and Harbor tasks in sandboxes such as AgentENV, Daytona, E2B, and Modal. It states validated support for larger-model training on NVIDIA and AMD GPUs with lower memory use, and adds Qwen3.8-Flash-Next, GLM-5.3-Flash, and Kimi-K3 to the stable version.

    Image from @radixark's post
  11. Artificial IgnoranceBlogAI score42

    OpenAI Engineer Argues Voice Agents Should Act, Not Only Talk

    AIAn OpenAI developer experience team member argues voice agents need not always speak back, outlining speech-to-speech, speech-to-action, and event-to-speech as emerging design modes. He cites form filling, creative tools, and computer use as examples of speech-to-action, which he calls among the most underexplored areas. He says event-to-speech is still very exploratory, with hands-free recipe guidance and proactive alerts as examples.

  12. Google WorkspaceOfficialAI score34

    Gemini in Gmail can turn email threads into structured briefs

    AIGoogle Workspace says users can prompt Gemini directly in Gmail to extract goals, timelines, and next steps from email threads. Gemini then generates a formatted Doc automatically based on the user's current work, while they keep working through their inbox.

    Video from @GoogleWorkspace's post
  13. Google · Gemini appOfficialAI score38

    See what 4 builders are making with Gemini 3.8 Flash

    AIGoogle says Gemini 3.8 Flash, its most intelligent workhorse model, improves on 3.7 Flash in software engineering, agentic tasks, and multistep reasoning by running extra reasoning steps and calling tools iteratively. The post highlights four community builds, including a model rocket simulation, an animated ink-painting effect, a 3D dinosaur skeleton, and an interactive automatic transmission simulation. Developers can try the model through Google Antigravity and Google AI Studio.

  14. clem 🤗XAI score49

    Hugging Face proposes egress usage monitoring for OpenShell agent sandboxes

    AIHugging Face is contributing egress usage monitoring to NVIDIA's OpenShell, part of the newly launched Open Agent Safety Platform, arguing that allowlists alone restrict where agents can go but not what they do. The proposed features include per-sandbox network budgets for requests, writes, and bytes, drift detection against each sandbox's baseline and cohort, and a fleet view that flags many sandboxes writing to one host even when every request is allowed.

    Video from @ClementDelangue's post
  15. Philipp SchmidXAI score36

    Gemini Managed Agents' Credentials API keeps secrets out of sandboxed code

    AIGoogle's Credentials API for Gemini Managed Agents injects secrets on the wire only for trusted domains, so sandboxed code cannot read raw tokens. It supports environment variables, CLIs, and MCP servers. Passing API keys as plain environment variables lets any sandboxed dependency read and potentially leak them.

  16. Philipp SchmidXAI score52

    Gemini Managed Agents adds a Credentials API that keeps secrets out of sandboxes

    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.

  17. Sierra BlogOfficialAI score34

    Sierra's Ghostwriter becomes a proactive Slack and Teams teammate for AI agents

    AISierra has turned its Ghostwriter tool into an always-on teammate in Slack and Teams that proactively suggests ideas, flags problems, and proposes experiments. Ghostwriter reviews recent customer calls, recommends which changes to try first, runs experiments, and reports when results are statistically significant. Sierra said it will begin rolling the feature out more broadly next week.

  18. Higgsfield AI 🧩OfficialAI score34

    Claude Opus 5.5 Drives 12 Laptops to Produce a Launch Video

    AIHiggsfield AI gave Claude Opus 5.5 access to 12 laptops, and from one prompt it split the work across machines using Computer Use and Higgsfield MCP. The system generated the visuals, built the animations, and assembled a fully editable After Effects project.

    Video from @higgsfield's post
  19. NVIDIAOfficialAI score34

    NVIDIA launches Open Agent Safety Platform to control AI agent access

    AINVIDIA has launched the Open Agent Safety Platform to help teams control what AI agents can access and do. NVIDIA OpenShell enforces permissions around agent work, while BlueField-4 and DOCA add independent monitoring and security controls in the infrastructure beyond the agent's reach. Together, these components aim to give organizations defined permissions, oversight, and protection for long-running agent tasks.

    Image from @nvidia's post
  20. Together AIOfficialAI score34

    Together AI Launches as Partner for NVIDIA Open Agent Safety Platform

    AITogether AI is a launch partner for NVIDIA's Open Agent Safety Platform, which brings together OpenShell and Sentry with over 100 industry partners. Together AI says it has built platform capabilities for secure agent development and deployment and will keep investing in this area, including its work with NVIDIA on OpenShell.

  21. KhazixXAI score31

    Solo developer rewrites AIHOT with multi-model AI workflow in three days

    AIThe developer behind AIHOT rewrote the entire project over three days, then launched it after a 12-step AI-assisted workflow. The process used Claude Opus 5.5, Claude Fable 5.1, and GPT-6 Astra for distillation, rewriting, audits, testing, and a six-hour shadow-system rehearsal before cutover. The post frames this as an amateur's experience and includes a quoted suggestion to distill the source project into a feature document and rewrite it directly with the latest models.

    Image from @Khazix0918's post
  22. Import AIBlogAI score52

    Import AI 474 covers Michael Levin's mind-pattern paper, robot post-training, Google's space TPUs, and Zhipu's self-improvement loop

    AIImport AI 474 is a research newsletter by Jack Clark that surveys four developments and one fiction piece. It covers Michael Levin's paper proposing minds as patterns that ingress into bodies, Stanford researchers' call for a universal post-training recipe for robotics, Google's plan to send TPUs to space with Planet, and Zhipu's use of GLM-5.3 to speed up its own inference infrastructure.

  23. SenseTimeOfficialAI score20

    CHunye's solo short drama DUHAI, made entirely with SenseTime's Seko agent

    AICreator CHunye produced the Japanese-style zombie short drama DUHAI entirely on his own from Episode 3 onward using SenseTime's Seko AI video creation agent. The series reportedly passed 74 million cumulative views on Douyin and beyond by Episode 9, with Seko handling workflows, characters, scenes, and props on one canvas.

    Video from @SenseTime_AI's post
  24. Jensen HuangXAI score42

    NVIDIA releases open agent safety platform combining OpenShell and Sentry

    AINVIDIA's Open Agent Safety Platform Reference Design combines NVIDIA OpenShell and NVIDIA Sentry to secure AI agents. OpenShell, an open-source secure runtime, enforces clear boundaries and policy on agent actions while tracing them as they work. NVIDIA Sentry adds hardware-based enforcement on NVIDIA BlueField, continuously monitoring agent activity and enabling millisecond-scale containment and quarantine.

    Image from @JensenHuang's post