AI.info
AI Tools Updates — Page 123
What changed in the AI tools this week — dated, from the makers’ own changelogs.
Em inglês
- Kilo Code — v7.7.6 (release)
Reintroduced automatic session cleanup and added creating Git projects and cloning repositories from Agent Manager.
- Tonic Structural — v1872
Bug fixes and other internal updates.
- Palantir AIP — AI FDE now includes tools to read and create or replace cover pages for Projects.
- Fern SDK Generator — 3.96.0
Object types with XML encoding metadata are generated as classes with toXml(), a static fromXml() parser, and a fluent Builder.
- Lovable — Use your connected tools from Lovable in Telegram
Lovable in Telegram can work in connected tools; it reads without asking and asks for approval before it creates, sends, or changes anything.
- Lovable — Jev for typed decisions in your app’s AI features
Use Jev Latest to return a category, a score, or a yes/no probability instead of generated text.
- Lovable — Chat with Lovable across your workspace or inside a project
Chat without changing code, ask about apps and workspace, work in connected tools, create files, and send work to a project.
- Lovable — Manage agent permissions from your account settings
Review and change every agent permission from one page, for each connector available in your workspace and for creating or editing projects from a chat.
- Lovable — Set a default design system for each group
Workspace admins and owners can set a default design system for a group; members get it pre-selected when they create a project.
- Hugging Face — tokenizers v1: encode, decode and scaling, measured
tokenizers v1 covers encode, decode, and scaling.
- ElevenLabs — ElevenAgents
Added enable_parallel_tool_calls, gpt-6-astra, Slack alerting, phone number search, GPT Image 2.5 models and cascade_timeout_seconds.
- ChatGPT — Privacy Center in ChatGPT
Privacy Center brings together information about chat privacy, memory, personalization, data use, connected apps, and account security.
- Benchling Insights — Benchling expands its Asia footprint with Kyowa Kirin AI rollout in Japan
Benchling expands its Asia footprint with Kyowa Kirin AI rollout in Japan.
- Benchling R&D Cloud — Benchling expands its Asia footprint with Kyowa Kirin AI rollout in Japan
Benchling rolled out AI with Kyowa Kirin in Japan.
- Taskade — v6.254.0: Clearer Taskade EVE Chats & Email Attachments
Taskade EVE runs fold into a summary line, and email attachments sent to a Mailhook address save to workspace Media.
- Napkin AI — v1.2.0 (2026-09-20)
Failed visual endpoint calls return JSON errors; X-API-Version is sent on every response; 429 errors use a code.
- Letta — Release v0.32.14
Removed the /remember command.
- Higgsfield AI — Grok 4.7 in Supercomputer
Grok 4.7 is now available in Supercomputer.
- Typefully — Choose Who Can Reply to Your X Posts
Added settings to choose who can reply to X posts published with Typefully.
- Open Interpreter — Open Interpreter 0.0.45
Adds DeepSeek Flash and DeepSeek V4 Pro to the model picker; DeepSeek Flash supports image input and a 1M-token context window.
- Keploy — v3.6.67
Replay now reports offline coverage and what each replay proved; generic exchange boundaries use the wire clock.
- Keploy — v3.6.68
- Lovable — Organize project files into collections
Group files into collections, upload files or drag them onto the tab, and see new files appear as Lovable creates them.
- LiteLLM — v1.102.0
Auto router controls, native OCR, gateway reliability
- LM Studio — Bionic 1.1.4
The agent can now read messages earlier in its own history; Supports @ referencing other sessions.
- GLM Coding Plan — Release v3.14.0
Added dynamic workflows that use a single script to orchestrate multiple sub-agents collaborating on complex tasks.
- LiteLLM — Auto router controls, native OCR, gateway reliability
- Taskade — v6.253.0 — Taskade EVE Memory Controls & Voice Input
- Factory Droids — CLI v0.223.0, Desktop v0.180.0: Session forking, PyCharm, Databricks connector, streaming chat tables, and custom model credential fixes
Added session forking, Databricks setup, PyCharm, and hook risk settings; changed streaming chat tables and default autonomy.
- LiteLLM — v1.102.0: Auto Router Controls, Native OCR & Gateway Reliability
Auto router controls, native OCR, gateway reliability
- LM Studio — Bionic 1.1.5
Qwen3.8 inference using a new engine: Splash (by Inco AI); prompt-processing status for models without percentage progress.
- Claude Code — 2.1.278
Changed auto mode to default to the server-side classifier for API, Enterprise, and listed provider users; /status now shows classifier location.
- Unsloth — Docker + Multi User + AMD Support
Adds a Docker image with NVIDIA and AMD support, multi-user accounts, diffusion support, ARM64 Windows CUDA support, and RDNA1/2 support.
- Lovable — Cleaner transcripts when you dictate a prompt
When you dictate a message, Lovable removes filler words, cleans up the text as it transcribes, and recognizes product names.
- RunPod Pods — Request pricing for global volumes
Global volumes charge for request operations separately from storage.
- Abnormal Inbound Email Security — Weekly Detection Enhancements - Week of September 18
Strengthened internal account takeover detection using sender-behavior signals; enhanced detection of file-share phishing abusing SharePoint
- Google AI Studio — Gemini 2.5 models access update :
We are limiting access to the 2.5 models to users who have actively used them in the past.
- Botpress — September 18, 2026
Agents can set ticket language; API callers can request OpenAI fast tier; Google Sheets supports selecting multiple spreadsheets.
- Abnormal Account Takeover Protection — This Week in Detection
Strengthened detection of internal account takeover, using sender-behavior signals to catch hijacked accounts blasting phishing links to unfamiliar domains
- Abnormal Inbound Email Security — This Week in Detection
Strengthened detection of internal account takeover; enhanced detection of file-share phishing from unknown senders that abuse SharePoint.