New AI Tools — Products, CLIs & IDE Features

The newest AI tools, products, CLIs and IDE features — what shipped, who it's for, and how to try it tonight, in plain English.

418 releases tracked

• SoL-Pi — NVIDIA's harness extension cuts coding-agent tokens by about halfNVIDIA · 2026-09-17 · major

  Four efficiency tricks, picked by an automated research loop out of 152 candidates, packaged as a drop-in Pi extension.

• Astra for Law — OpenAI ties GPT-6 Astra to a 230M-URL legal indexOpenAI · 2026-09-17 · major

  OpenAI's GPT-6 Astra, wired to a searchable index of US law and 26 legal vendor plugins.

• Bend 2 — a language that makes an AI prove its code obeys your lawsBend · 2026-09-17 · major

  Declare the rules your program must never break, and Bend 2 refuses to compile an edit that cannot prove it kept them.

• BrowserSkill 0.3.0 — Tencent's agent bridge gets canvas and remote gatewaysTencent · 2026-09-17 · major

  Your agent borrows a window in the browser you are already logged into, then hands it back.

• Google Home MCP — any MCP agent can now run your smart homeGoogle · 2026-09-16 · major

  Google's smart home platform now speaks MCP, so the agent you already use can read and control your Nest devices.

• Cowork folds into Claude — Anthropic adds Claude Docs and Claude SlidesAnthropic · 2026-09-16 · major

  Anthropic removed the line between Claude chat and Claude Cowork, and put document and slide editing inside the conversation.

• OpenAI Sponsored Agents — ChatGPT ads you can talk back toOpenAI · 2026-09-16 · major

  ChatGPT ads become two-way: OpenAI is testing agents that answer questions on a business's behalf.

• Firefox Smart Window runs on Mistral Small 4 — and opens in FranceMistral AI · 2026-09-16 · major

  Mozilla's browser assistant adds Mistral Small 4 as a model option and opens its beta to France.

• Claude Code 2.1.273 — a subshell could hide a dangerous rm in bypass modeAnthropic · 2026-09-15 · major

  Claude Code 2.1.273 closes two permission-checker gaps and stops the context meter double-counting advisor-tool turns.

• Open Code Review v1.12.3 — secrets and .env files stay out of the reviewAlibaba · 2026-09-16 · major

  Alibaba's open-source code reviewer now refuses to send secret paths and per-environment .env files to the model.

• Ollama 0.34.1 — MLX safetensors leave experimental, GGUF needs llama.cppOllama · 2026-09-14 · major

  Ollama 0.34.1 promotes MLX safetensors model creation out of experimental and hands GGUF conversion to llama.cpp tooling.

• dbt Charts — dashboards as YAML, so an agent can write themdbt Labs · 2026-09-14 · major

  One YAML file describes a whole interactive dashboard, so charts live in Git next to the models they read.

• Claude Code 2.1.271 — a sandboxed command only reaches its own hostsAnthropic · 2026-09-14 · major

  Network permission moves from the whole session down to the single command that asked for it.

• LiteLLM v1.101.0 — smarter complexity routing and a semantic MCP searchBerriAI · 2026-09-15 · major

  The gateway gets a second-generation complexity router, a circuit breaker for its classifier, and semantic search over MCP tools.

• llama.cpp v0.4.1 — Maple 20B-A1B and Tencent Hy 4 now run locallyggml-org · 2026-09-14 · major

  Three new model architectures land in the local inference engine, and three old loading flags are taken out.

• Siri AI ships in iOS 27 — Apple's rebuilt assistant goes live in betaApple · 2026-09-14 · major

  The rebuilt Siri is now on shipping software: onscreen awareness, personal context and systemwide app actions, in English first.

• Pion — Andon Labs opens a cloud platform where agents run a businessAndon Labs · 2026-09-14 · notable

  Andon Labs opens Pion, where persistent agents run a real company with a terminal, email, phone, banking and a browser.

• Lema AI Governance — third-party AI found, assessed and monitoredLema AI · 2026-09-11 · notable

  Lema AI Governance finds the AI a vendor added after you approved it, scores the exposure it creates, and watches it for drift.

• OpenClaw 2026.9.4 — plugins and skills install from the Control UIOpenClaw · 2026-09-11 · major

  OpenClaw 2026.9.4 gives plugins and skills one workspace in the Control UI, and lets a failed update roll itself back.

• Google ADK 2.9.0 — agents fail over to a backup model automaticallyGoogle · 2026-09-10 · major

  Agents keep running when a model errors, and ADK now speaks over the phone through LiveKit.

• Cursor Projects — a coordinator agent that delegates to thousands of subagentsCursor · 2026-09-10 · major

  A project-level agent in Cursor that plans, delegates to parallel subagents, and keeps working in the cloud after you close your laptop.

• Gemini for Windows — Google's desktop app opens over your work with Alt + SpaceGoogle · 2026-09-10 · major

  Google's Gemini assistant ships as a native Windows app, one Alt + Space away from whatever you are working on.

• Claude Code 2.1.269 — claude plugin eval scores a plugin against a baselineAnthropic · 2026-09-11 · major

  A built-in eval runner for Claude Code plugins, with a no-plugin baseline that shows what the plugin actually contributes.

• DeepSeek Recipe — the official prompt encoder for V4 and V4.1DeepSeek · 2026-09-10 · major

  DeepSeek's own library for turning API requests into V4 and V4.1 prompts, and streamed output back into responses.

• Claude Managed Agents add 'auto' mode — the server checks every tool callAnthropic · 2026-09-10 · major

  A third permission policy lets Anthropic's server decide, call by call, whether an agent's tool runs, stops, or waits for you.

• OpenAI Agents API — the Codex harness opens up to developersOpenAI · 2026-09-10 · major

  The harness behind Codex, now a managed API: OpenAI runs the agent loop, your app brings the tools.

• Premiere's Generative Media Tool — five AI video models in the timelineAdobe · 2026-09-08 · major

  Premiere editors can now generate clips and sound effects on the timeline itself, choosing between Adobe's model and four rivals.

• Codex CLI 0.154.0 — GPT-6 Astra in the picker and git worktree sessionsOpenAI · 2026-09-09 · notable

  Codex sessions can now run in their own git worktree, so parallel agents stop fighting over one checkout.

• Claude Code 2.1.267 — one setting caps effort on every providerAnthropic · 2026-09-09 · major

  Claude Code 2.1.267 lets an admin cap effort level everywhere at once and spends most of its changelog repairing prompt-cache reuse.

• Desert Ant Labs — 18 small AI models that run offline inside your appDesert Ant Labs · 2026-09-08 · major

  Eighteen small models that run fully offline inside iOS, Android and web apps, with no token bill.

• TeamAI CLI — Tencent ships one AI setup for a whole teamTencent · 2026-09-09 · major

  One git repo holds a team's agent skills, rules and MCP servers, and every member's coding agent pulls them automatically.

• Muse — Meta's personal AI agent runs in its own secure virtual machineMeta · 2026-09-08 · major

  Meta's Muse takes an errand end to end — shopping, bookings, forms — from an ordinary chat thread.

• MCP Python SDK 2.2.0 — idle sessions now close after 30 minutesModel Context Protocol · 2026-09-07 · major

  The official Python SDK for MCP tightens session handling and OAuth checks, with the same fixes backported to the 1.x line.

• Humanizer v3.0.0 — the AI-writing cleanup skill drops 35 patterns to 25blader · 2026-09-06 · major

  An agent skill that strips the 25 habits which make text read as AI-written, without changing the facts.

• LiteLLM v1.100.0 — Vertex AI Interactions API and shared team budgetsBerriAI · 2026-09-06 · major

  The LLM gateway's newest release widens provider coverage and moves budget enforcement from single keys to shared groups.

• Ollama 0.34 — local models now run inside ChatGPT DesktopOllama · 2026-09-05 · major

  Ollama 0.34 wires local open models into ChatGPT Desktop, set up from the Ollama app on macOS.

• OpenClaw 2026.9.2 — GPT-6 Astra support and swarms on by defaultOpenClaw · 2026-09-05 · major

  OpenClaw's September release picks up GPT-6 Astra on day one and switches concurrent sub-agent swarms on for everyone.

• llama.cpp v0.4.0 — Qwen3.8-Flash-Next support and lazy tensor loadingggml-org · 2026-09-04 · major

  The local LLM runtime picks up two new model architectures and learns to read weights from disk on demand.

• LangChain 1.4.0 — a built-in MCP adapter for agent toolsLangChain · 2026-09-03 · major

  LangChain agents can reach Model Context Protocol servers through a first-party adapter.

• SGLang v0.5.19 — beam search arrives, plus 786 merged pull requestsSGLang · 2026-09-05 · major

  SGLang's September release adds beam search, nine more models, and an AMD attention kernel that fills idle compute units.

• Soup v0.74.0 — a dtype bug was doubling every fine-tune's memorySoup · 2026-09-04 · notable

  A missing dtype argument meant Soup loaded the frozen base model at twice its checkpoint precision, on every single fine-tune.

• Shunt — Spotify's Claude Code plugin cuts token use by 90%Spotify · 2026-09-03 · major

  A Claude Code plugin that hands bulk file reads to a cheap model, which Spotify measured at about 90% fewer tokens.

• Claude Code 2.1.261 — /skill-doctor shows which skills waste your contextAnthropic · 2026-09-04 · major

  Claude Code 2.1.261 adds a skill audit, much bigger inline output limits, and a stricter rm -rf safety check.

• Project HydraFusion — GitHub Copilot picks the model workflow for youGitHub · 2026-09-04 · major

  GitHub's router sends each coding task to the cheapest workflow that still clears the quality bar.

• Gemini Spark connects to Google Photos — it can edit, sort and share for youGoogle · 2026-09-03 · major

  Google Photos becomes a connected app for Gemini Spark, so one prompt can search, edit, album and share across a whole library.

• Qwen3.8-27B on Cerebras — 1,500 tokens per second at $0.99 per millionCerebras · 2026-09-03 · major

  Cerebras added Qwen3.8-27B to its public endpoints, running Alibaba's 27B dense multimodal model at roughly 1,500 tokens per second.

• Claude Code 2.1.260 — a live diff panel and a permission-rule security fixAnthropic · 2026-09-03 · major

  Claude Code 2.1.260 puts a live diff beside the conversation and repairs permission rules that quietly left folders writable.

• Claude Content Checker — see if a file carries Claude's signed credentialAnthropic · 2026-09-02 · notable

  A free in-browser page that reads Claude's C2PA Content Credential out of a file's metadata.

• Codex CLI 0.153.0 — install plugins straight from remote marketplacesOpenAI · 2026-09-03 · notable

  Codex CLI 0.153.0 brings a plugin marketplace client, Vim undo and redo, and session reconnection that keeps your draft.

• Cursor self-hosted machines — cloud agents run inside your own networkCursor · 2026-09-02 · major

  Cursor Cloud Agents can now do their tool calls on hardware you control, while the model still runs in Cursor's cloud.

• Claude Code 2.1.259 — admins can push MCP servers to every userAnthropic · 2026-09-02 · major

  The 2.1.259 release moves MCP configuration up to the administrator, and gives headless runs a way to refuse prompts instead of hanging.

• Slotstream v0.2.0 — a 104GB model on a 48GB Mac, plus speculative decodingCarlos Galarza · 2026-09-01 · major

  Slotstream streams a 125B model's experts off SSD so a Mac with 48 GB of RAM can run a 104 GB checkpoint.

• Google Pics — an AI image tool in Workspace where you start from a promptGoogle · 2026-09-01 · major

  Google Pics turns a written description into a poster or graphic, then lets you edit one object at a time.

• ChatGPT connects to Epic — clinicians can pull chart context into the chatOpenAI · 2026-09-01 · major

  Hospitals can wire their Epic records into ChatGPT, and clinicians get a plugin for nine official public health data sources.

• Agentic video in Gemini — the model loads only the clips it needsGoogle · 2026-09-01 · major

  Gemini can now walk a video on its own, pulling only the segments a question needs instead of every frame at a fixed rate.

• Claude Code 2.1.257 — Claude Fable 5.1 becomes the default Fable modelAnthropic · 2026-09-01 · major

  Claude Code 2.1.257 switches its default Fable model to Claude Fable 5.1 and stops auto mode waving through container-escape moves.

• ChatGPT Mil and Grok for Government — the Pentagon's AI portal adds two modelsPentagon · 2026-08-31 · major

  The Pentagon's GenAI.mil portal now runs ChatGPT Mil and Grok for Government next to Google's Gemini.

• Codex CLI 0.152.0 — the planning tool is now off by defaultOpenAI · 2026-09-01 · notable

  Codex CLI 0.152.0 turns the planning tool off by default and tightens how MCP tools return output.

• OpenClaw 2.0 — the largest release yet for the open-source AI assistantOpenClaw · 2026-08-30 · major

  OpenClaw 2.0 rebuilds installation, memory, skills, the browser and team access in one release built from over 16,000 merged pull requests.

• Claude for Teachers reaches districts — a free Enterprise plan for U.S. K-12Anthropic · 2026-08-28 · major

  Schools can now hand out Claude for Teachers centrally instead of asking each teacher to sign up alone.

• Cursor cloud agents start without a repo — and preview in the browserCursor · 2026-08-27 · major

  Cursor Cloud Agents can now open a brand-new project with nothing connected — no GitHub, no local checkout, no repo of your own.

• Experiential — an open-source model gateway that takes no token markupExperiential Labs · 2026-08-28 · notable

  Experiential puts self-hosted, frontier and open-source models behind one OpenAI-compatible API, and charges no markup on top of provider prices.

• Codex CLI 0.151.0 — extensions can rewrite MCP tool resultsOpenAI · 2026-08-29 · notable

  An extension can now sit between an MCP tool and the model in Codex CLI, reading or replacing the result before it reaches the context.

• Lemmalog — agent memory as a Datalog database, not a pile of textJordy Zomer · 2026-08-28 · notable

  Lemmalog swaps an agent's vector-store memory for a Datalog database that tracks why every fact is still believed.

• Claude Code 2.1.251 — hooks that can block a model switchAnthropic · 2026-08-28 · major

  Claude Code 2.1.251 lets a hook step in when the model changes, and closes several symlink and path-traversal holes.

• Microduck — Hugging Face's $399 open-source robot you train with RLHugging Face · 2026-08-27 · major

  Microduck is a 25 cm biped robot from Hugging Face that ships with seven reinforcement learning policies you can retrain yourself.

• Claude Code 2.1.248 — a restricted mode that strips the tools that run codeAnthropic · 2026-08-27 · major

  Claude Code 2.1.248 adds a restricted mode that takes away the tools which run commands or code.

• Model Hardware Standard — Anthropic's spec for agents that run lab equipmentAnthropic · 2026-08-27 · major

  Anthropic opened a research preview of MHS, a shared standard that lets AI agents drive lab and factory hardware safely.

• OpenAI Admin plugin — ChatGPT Work admins run the workspace in chatOpenAI · 2026-08-25 · major

  OpenAI's Admin plugin lets a ChatGPT Work administrator ask a question and act on the answer in the same chat.

• Portable Computer — Perplexity's agent runs fully on your own GPUPerplexity · 2026-08-25 · major

  Perplexity's full agent runtime now runs on a DGX Spark or a 24GB RTX GPU, with no cloud dependency.

• Claude memory works everywhere — one memory across chat and CoworkAnthropic · 2026-08-25 · major

  Claude and Claude Cowork now draw on the same memory, and every saved topic is a file you can open and change.

• Claude Code 2.1.246 — gateway API keys are no longer sent to AnthropicAnthropic · 2026-08-25 · major

  A security-heavy Claude Code release: credentials stay on their own host, and auto mode's rules finally get an editor.

• Jalapeño first results — OpenAI's inference chip posts 1.9x more work per wattOpenAI · 2026-08-25 · major

  OpenAI's first custom inference chip now has measured numbers, and they favour tokens per watt over tokens per chip.

• Apple M6 and M5 Ultra — 2nm silicon and 512GB for on-device LLMsApple · 2026-08-25 · major

  Apple's first 2nm chip and its first quad-die M-series part, both aimed squarely at running big models on your desk.

• Claude Code 2.1.243 — the install drops from 340 MB to 75 MBAnthropic · 2026-08-24 · major

  A lighter Claude Code: 75 MB to install, 40-70 MB less memory per session, plus four new settings for organizations.

• Tempus ECG-PH — FDA clears AI that spots pulmonary hypertension in a routine ECGTempus AI · 2026-08-24 · major

  An FDA-cleared AI that reads a routine ECG and flags patients who may have pulmonary hypertension.

• NVIDIA Groq 3 LPX — the agent inference chip enters full productionNVIDIA · 2026-08-24 · major

  NVIDIA's Groq 3 LPX accelerator is in full production, built to decode tokens fast enough to keep AI agents responsive.

• MoneyPrinterTurbo v1.3.5 — Claude joins the one-click short-video makerMoneyPrinterTurbo · 2026-08-22 · notable

  MoneyPrinterTurbo builds a finished vertical short from a keyword, and v1.3.5 adds Claude, two more voice engines and API-key auth.

• LiteLLM v1.98.0 — reserved capacity gets flat-cost billing, not per-tokenBerriAI · 2026-08-23 · major

  LiteLLM v1.98.0 teaches the open-source AI gateway to bill reserved capacity and to test routing changes before adopting them.

• Claude Code 2.1.239 — a proxy bug that doubled Bedrock API calls is fixedAnthropic · 2026-08-21 · major

  Anthropic's 2.1.239 build closes a Bedrock proxy bug that silently doubled the API calls you were billed for.

• SGLang v0.5.18 — cold starts get 2.38x faster, seven model families landSGLang · 2026-08-22 · major

  SGLang v0.5.18 overlaps weight loading with CUDA graph capture, cutting a large-model cold start from 85 seconds to 36.

• Bot Preference Sync — Cloudflare writes your robots.txt to match your bot rulesCloudflare · 2026-08-21 · major

  Cloudflare builds your robots.txt out of the AI bot policy you already set in its dashboard.

• LLM 0.33 — Simon Willison's CLI moves to the OpenAI Python 3.x librarySimon Willison · 2026-08-22 · notable

  LLM 0.33 rebases Simon Willison's model CLI on the OpenAI Python 3.x library and adds per-call embedding keys.

• Claude browser use tool — Anthropic's agent APIs are now generally availableAnthropic · 2026-08-20 · major

  Anthropic's agent building blocks leave preview, joined by a browser tool that targets page elements instead of pixels.

• OpenAI regional processing — pick an inference region per API requestOpenAI · 2026-08-21 · major

  One API key, ten regional domains — choose where each OpenAI request is processed.

• NoBuzz — a Claude Code skill that rewrites Claude's replies in plain Englishadnanakil · 2026-08-21 · notable

  NoBuzz hands Claude's answer to a second model and prints the plain-English rewrite instead.

• Codex CLI 0.149.0 — a dashboard for every running agent taskOpenAI · 2026-08-20 · major

  Codex CLI 0.149.0 puts every agent task behind one searchable dashboard you can drive with shortcuts.

• Claude Code 2.1.238 — plugin marketplaces can mint their own auth headersAnthropic · 2026-08-20 · major

  Private plugin marketplaces can now hand Claude Code a fresh token for every catalog fetch.

• Waymo's custom AI chip — a 5nm ASIC that runs 1,000+ TOPS in the carWaymo · 2026-08-20 · major

  Waymo now designs the silicon that turns its robotaxi's sensor data into driving decisions.

• Slack Code — AI coding agents get a channel the whole team can watchSlack · 2026-08-20 · major

  Slack Code gives a coding agent its own project channel, so planning, diffs and sign-off all happen in front of the team.

• Antigravity IDE Extensions — Google's agent moves into VS Code and JetBrainsGoogle · 2026-08-20 · major

  Google's agent-first coding platform now installs as a normal extension in the editor you already use.

• Apple Messages plugin — ChatGPT can read and send texts on a MacOpenAI · 2026-08-20 · major

  ChatGPT can now open your Mac's Messages app, search old threads and send a reply you approve.

• Huzzah — an editor where you write pseudocode and an LLM fills in the codeDaniel Vaughn · 2026-08-20 · notable

  Write pseudocode instead of a paragraph of English, and Huzzah syncs it into working code.

• Vomit — a local model rewrites Claude Code's replies before you read themZach Ahn · 2026-08-19 · notable

  Vomit pipes Claude Code's output through a small local model so the prose comes back plain.

• Ramp Router — an LLM gateway that cut customer inference bills 40% on averageRamp · 2026-08-19 · major

  Ramp Router takes one API call and forwards it to the model that meets your quality bar at the lowest price.

• NeuroQuant PET — FDA clears automated amyloid scoring for dementiaCortechs.ai · 2026-08-18 · major

  Cortechs.ai's NeuroQuant PET can now be used on real patients to score amyloid brain scans automatically.

• Mistral Agentic Search — models search, open and grep their way through docsMistral AI · 2026-08-20 · major

  Mistral's retrieval layer lets an agent search, open and grep a document set until it can actually answer.

• Meta AI for Mac — a native desktop app with screen sharing and dictationMeta · 2026-08-19 · major

  Meta's assistant gets a real Mac app that can read your screen and type for you anywhere.

• Binance Agent OS — an MCP server that lets AI agents place real tradesBinance · 2026-08-20 · major

  Binance opens its trading, wallet and payment stack to AI agents through a single MCP server.

• ChatGPT Ads reach Europe — 31 markets get labeled ads on Free and GoOpenAI · 2026-08-19 · major

  OpenAI takes ChatGPT Ads into 31 European markets, with GDPR consent choices and no ads on paid plans.

• ai-memory v1.29.0 — long-term memory that follows agents across CLIsAkitaOnRails · 2026-08-19 · major

  A local, git-versioned wiki of what your coding agent already figured out, readable by whichever agent you open next.

• fx — Vercel Labs open-sources a 6 MB coding agent written in ZigVercel Labs · 2026-08-17 · major

  A tiny native coding agent from Vercel Labs, built to be embedded anywhere a shell can run.

• Gemini study tools — 3D simulations and a free year of Google AI for studentsGoogle · 2026-08-19 · major

  Google gives verified college students a free year of its paid AI plans and adds study tools across Gemini, Search and Lens.

• Cursor Subscriptions — cloud agents watch a PR and drive it to doneCursor · 2026-08-19 · major

  Cursor's cloud agents can now subscribe to a PR, a Slack thread or a schedule and keep going on their own.

• oMLX 0.6.2 — the Mac LLM server now tunes its own ANE/GPU splitoMLX · 2026-08-18 · notable

  Instead of shipping one ANE/GPU ratio for every Mac, oMLX now measures the best split on the machine in front of you.

• Palomar — a registry that machine-checks Lean proofs, human or AILean FRO · 2026-08-18 · major

  A searchable registry of Lean formalizations whose proofs are replayed through two independent kernels before they are listed.

• Claude Playground — Anthropic retires Workbench for an API-exact consoleAnthropic · 2026-08-18 · notable

  Playground replaces Workbench in the Claude Console and shows you the exact API request your prompt turns into.

• Warp Factories — cloud agent pipelines for the whole dev cycleWarp · 2026-08-18 · major

  Warp Factories turns a backlog ticket into a reviewed pull request using fleets of cloud coding agents.

• Claude Code keeps 50% higher weekly limits — extended through August 31Anthropic · 2026-08-18 · major

  Claude Code's 50% weekly limit boost, first added in May, now runs through August 31, 2026.

• ChatGPT for Teens — OpenAI's age-gated mode for 13-to-17-year-oldsOpenAI · 2026-08-18 · major

  OpenAI's teen mode locks down sensitive topics, steers homework into Study Mode, and hands parents a Quiet Hours switch.

• Cursor Origin — a Git forge for agents opens in early betaCursor · 2026-08-17 · major

  Cursor now hosts your code as well as writing it, with pull requests and GitHub sync in the same tab.

• Claude Code 2.1.233 — GitLab merge requests, marketplaces and token redactionAnthropic · 2026-08-14 · major

  GitLab teams get first-class Claude Code support: merge request worktrees, plugin marketplaces and token redaction.

• Gemini watermarks become optional — Google adds an off switch for AI mediaGoogle · 2026-08-14 · major

  Google makes Gemini's visible AI watermark a user choice, while invisible SynthID and C2PA provenance stay in every file.

• Computer History — ChatGPT builds a memory from your Mac activityOpenAI · 2026-08-13 · major

  ChatGPT for Mac can now build memories from what you do in your apps, using interaction events instead of screenshots.

• Credentio — Google open-sources the C++ library behind its content credentialsGoogle · 2026-08-13 · major

  Google's C++ library checks C2PA Content Credentials on the device, with nothing sent to a server.

• HEIR — Google's compiler runs AI models on encrypted dataGoogle · 2026-08-14 · major

  Google's HEIR compiler takes a normal trained model and rebuilds it to run on data the server can never read.

• Suno Studio 2.0 — browser music workstation adds MIDI and a chat barSuno · 2026-08-13 · major

  Suno's browser music workstation now takes MIDI, and a chat bar builds instruments, effects and synth presets on request.

• Cursor Builds — cloud agents fork a warm dev environment instead of setupCursor · 2026-08-13 · major

  Cursor keeps warm copies of your development environment ready, so a cloud agent skips setup and starts working almost immediately.

• Ultrafast mode — GPT-5.6 Sol at 750 tokens per second on CerebrasOpenAI · 2026-08-13 · major

  OpenAI's new API tier runs GPT-5.6 Sol on Cerebras hardware at up to 750 output tokens per second.

• DeepSeek Harness — open-source agent framework built entirely from pluginsDeepSeek · 2026-08-13 · major

  An MIT-licensed agent framework from DeepSeek where models, tools, sandboxes and even the interface are swappable plugins.

+ 298 more in the sitemap.

← All releases · Learn AI