Releasesby GlyphQwen Code Desktop v0.27.0
Qwen Code Desktop version 0.27.0 shipped bug fixes for channel recovery, review thread context in sandboxed PR verification, and performance optimizations for message parsing and leases.
Coding agents releases
635 Coding agents releases from data and AI companies, newest first
Sunday, November 8, 20261 release
Saturday, November 7, 20263 releases
DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway
DeepSeek V4.1 Flash 1017 Ultrafast is now available in public preview on Vercel AI Gateway. The model supports a 1M-token context window and is optimized for high-speed interactive coding and agentic workflows.
Copilot code review: API management and review overview updates
Users can now manage GitHub Copilot code review settings through REST and GraphQL APIs, including enterprise policies and repository-level configurations. The update also adds explicit attribution for Copilot-generated reviews and provides visibility into the skills and instructions used for comments.
Qwen Code Release v0.27.0
Qwen Code v0.27.0 introduces support for multiple child questions in managed-agent sessions, a task Q&A heatmap in Web Shell, and improved reliability for GitHub channel integrations.
Friday, November 6, 20265 releases
Voice Chat with Agents
Cursor now supports real-time voice interaction with coding agents. Users can describe changes, ask for status updates, and receive progress notes via voice.
@GitHub in Slack and Teams is generally available and more
@GitHub in Slack and Teams is now generally available, allowing users to investigate bugs, create issues, and open pull requests directly from chat. It also includes Canvas integration for reviewing code and implementation plans.
Gemini Enterprise: End of Gemini Code Assist entitlement for existing subscriptions
Bundled Gemini Code Assist entitlements for existing Gemini Enterprise subscriptions will be removed on March 31, 2027. New subscriptions no longer include this entitlement as of October 9, 2026, with users directed to Google Antigravity for coding assistance.
Thursday, November 5, 20263 releases
Build Live Apps in Cursor
Cursor enabled building and deploying web applications directly from the IDE using cloud agents, with automated setup for hosting, Postgres databases, and Cursor SSO authentication.
Mobile Diffs
Linear launched Diffs on iOS and Android, allowing developers to review code changes, manage guided reviews, view previews, and merge approved pull requests directly from mobile devices.
Run Claude Code and Codex in the SSH tunnel
Claude Code and Codex agents can now be run within SSH tunnel sessions in Databricks, using Unity Gateway for authentication.
Wednesday, November 4, 20266 releases
AlloyDB Express is available in Preview for PostgreSQL 18
AlloyDB Express is available in Preview for PostgreSQL 18. Optimized for rapid prototyping and for workflows that use AI coding agents, this configuration provides the following features: Fast provisioning Scale-to-zero compute when idle A monthly free tier for the first 12 months of usage One-click upgrades to AlloyDB for PostgreSQL For more information...
Functions now available in beta
CircleCI launched Functions in beta, allowing developers and AI agents to define, version, pin, and reuse CI environment setup modules via CLI and MCP server.
GitHub Copilot is now available in Xcode’s coding assistant
GitHub Copilot is now available in public preview within Xcode's built-in coding assistant, starting with Xcode 27.3 beta.
Fireworks AI releases Training Cookbook on PyPI and migrates repository
Fireworks AI published fireworks-training-cookbook 2026.11.5.1 on PyPI for Python 3.11+ and migrated its training cookbook to fw-ai-external/cookbook.
Background runs and additional supplementary tools for agents in the Snowflake-managed MCP server
Snowflake added a background boolean parameter to CORTEX_AGENT_RUN and CODING_AGENT tools in its managed MCP server to enable non-blocking, pollable agent executions.
Dreaming: Lovable keeps its memory up to date
Lovable now automatically tidies project memory and AGENTS.md files in the background for paid plans, ensuring project rules remain current.
Tuesday, November 3, 20266 releases
Snowflake CoCo for Excel and Snowflake CoCo for Google Sheets (Preview)
Snowflake CoCo for Excel and Snowflake CoCo for Google Sheets are now available in preview. Each one adds CoCo as a chat pane inside your spreadsheet, connected to your live Snowflake data. From the pane, you can query data with natural language or SQL; build pivot tables, charts, and formulas; and use the semantic views your role can access.
Tencent Hy4 now available on AI Gateway
Hy4 from Tencent is now available on AI Gateway , at 50% off through December 31, 2026. Hy4 supports reasoning , tool calling , structured outputs , and image input, and has a 1M-token context window for work across a codebase or many documents. Hy4 is the first Hy model with vision. It can pick out fine detail in an image and read complex charts.
Diagnose Vercel CLI setup problems with vercel doctor
Vercel CLI now includes vercel doctor , which checks your setup and shows the command that fixes each problem it finds. It checks the CLI version and install, your login and current team, the project link, and your project configuration in vercel.json . It also reports active incidents from the Vercel status page.
GitHub Copilot is now available in JetBrains Air
You can now delegate coding tasks, guide execution, and review results with GitHub Copilot in JetBrains Air . The integration uses the Agent Client Protocol (ACP) and supports tasks in your JetBrains IDE or in the cloud. Use Copilot in Air alongside the GitHub Copilot plugin and choose the workflow that works best for you.
Langfuse 4.73.0
Features - feat(ai-gateway): filter gateway analytics by user and API key - feat(skills): support version automations - feat(rbac): add AI_GATEWAY organization membership role - feat(monitors): add new monitor automation dialog - feat(ai-gateway): add GitHub Copilot CLI and app setup instructions - feat(ai-gateway): invite new gateway team members with the...
Monday, November 2, 20264 releases
CoCo automations (General availability)
CoCo automations are now generally available and are no longer in Preview . Automations let you schedule recurring, unattended CoCo runs that execute in a Snowflake-managed sandbox. Each run creates a Cortex thread that you can open to inspect the agent's messages, tool calls, and results.
LongCat 2.5 now available on AI Gateway
LongCat 2.5 from Meituan is now available on AI Gateway. This model combines native visual understanding with coding and multi-step tool use for agents working across complex codebases and full-project builds.
Vercel MCP now supports Client ID Metadata Documents
Any MCP client can now ask to connect to Vercel MCP . You still log in and approve each connection, but the client no longer has to be reviewed by Vercel first. Previously, Vercel reviewed and allowlisted each client and its redirect URIs by hand, and anything not on the list was rejected.
Haiku 5.5 now available on Kiro in AWS GovCloud (US)
A new Anthropic model is now available in the Kiro IDE and CLI for the AWS GovCloud (US) Regions. With Haiku 5.5, all three Claude 5.5 models are now available in Kiro in AWS GovCloud (US). Claude Haiku 5.5 is the fastest model in the Claude 5.5 family.
Thursday, October 29, 20262 releases
Le Chonk: Built for Coders, Trusted by Defenders
Mistral AI released the open weights for Le Chonk, a 1T parameter multimodal model. It is optimized for coding tasks.
Meta’s Muse Models Are Now Available in Agent Runners
You can now power your Netlify Agent Runners runs with Meta’s Muse family of AI models. Choose Muse for your next run and pick the model that fits the task, from Meta’s most capable Muse Wonder 1.0 for complex software engineering and long-horizon agentic work to Muse Spark 1.3, tuned for agentic workflows and coding.
Wednesday, October 28, 202617 releases
ViBench 2.0: A Benchmark for Long-Horizon Software Building
Replit released ViBench 2.0, a benchmark designed to measure an AI agent's ability to build full software products from scratch.
Particle-1 is now available on AI Gateway
Particle-1, a model post-trained on DeepSeek V4.1 Flash for software engineering tasks, is now available on AI Gateway.
fx is now available in T3 Code
The fx coding agent is now available as a provider in T3 Code, supporting both supervised and auto modes.
GitHub Copilot Fusion now supports selection of local models
GitHub Copilot Fusion now supports experimental local model routing, allowing the system to choose between on-device and cloud models based on the task.
IDE extension v0.25.0 | IDE Extension
The CodeRabbit IDE extension now features a redesigned sidebar that groups findings and nitpicks by file. It also includes improved AI-driven fix capabilities and simplified CLI and skill installation.
Automations
Devin added editing for Slack reaction triggers and clearer error messaging for failed LLM checks in automations.
Cortex Agents Coding Agent thinking effort, system instructions, and stage mounts
The Cortex Agents Coding Agent agent:run API now supports three additional public controls when using the code_toolset_all tool, providing more granular configuration for coding tasks.
Tuesday, October 27, 20264 releases
Unity Gateway Usage Dashboard v1.0
The Unity Gateway Usage Dashboard is now available, providing insights into coding-agent adoption, harness usage, and session spend. It supports tag-based spend attribution and detailed model analysis.
Delta Deep Scans | Continuous coverage | CodeRabbit Cloud
Delta Deep Scans allow for incremental security coverage checks on changed code between full scans. This feature helps maintain security standards by automatically triggering scans when coverage drops.
Vercel Plugin now available in OpenCode
The Vercel Plugin is now available in OpenCode, providing specialist agents for deployment, performance optimization, and AI application design, along with direct management of Vercel environment variables and deployments.
Monday, October 26, 20263 releases
GPT-6.1 Terra in GitHub Copilot
OpenAI's GPT-6.1 Terra model is now available in GitHub Copilot for coding and terminal tasks, offering a balance of performance and cost.
One ChatGPT Plugin To Deploy It All: the official Prisma plugin
The official Prisma plugin for ChatGPT allows users to connect ChatGPT and Codex to Prisma ORM, Prisma Postgres, and Prisma Compute to manage database deployment via prompts.
CoCo Desktop v1.23.0
CoCo Desktop v1.23.0 improves session organization and enables Snowflake Managed MCP servers across all accounts.
Friday, October 23, 20263 releases
Runtime verification for Deep Scan findings | GitHub Cloud | Beta
CodeRabbit's Deep Scan now includes a runtime verification feature that provides a reproducer guide and automated analysis to validate vulnerabilities.
Codex CLI 0.164.0
Codex CLI 0.164.0 adds reusable prompt presets, inline model and permission configuration, and improved enterprise MCP authentication.
GitHub Copilot in Visual Studio , September update
The September update adds Git agent support for pull request exploration and updates the Bring Your Own Model (BYOM) preview feature.
Wednesday, October 21, 20264 releases
Connect coding agents to Fabric notebooks with FNTK (Preview)
The Fabric Notebook Toolkit connects coding agents to Fabric notebooks via CLI, allowing agents to inspect code, execute cells, and validate changes interactively.
Agent Mode for the Auth0 CLI
Agents are increasingly operating the CLI to configure Auth0 on behalf of developers. The CLI wasn't built for that. A misspelled command could exit `0` like nothing went wrong. A routine re-login could hang forever waiting on a browser click that would never come. Finding the right command meant drilling through `--help` one level at a time.
Qwen Code Desktop v0.26.0
Alibaba released Qwen Code Desktop v0.26.0, adding session-targeted Skill and Extension refreshing, workspace file reference support for local and SSH paths, and session warming features.
Tuesday, October 20, 20263 releases
DeepSeek V4.1 Flash is now available in Token Pass
Token Pass now includes DeepSeek V4.1 Flash, alongside Kimi K3 and GLM 5.3, each accessed through its preferred provider, with more models to come. The DeepSeek model uses the latest weights (1017). Token Pass is a $30/month subscription on Pro teams that grants $80 in monthly credit and runs through AI Gateway .
October 2026
Ask Searchable from Slack and Microsoft Teams Searchable's MCP server now accepts sign-ins from Slackbot and Microsoft Copilot Studio, and lets Microsoft 365 Copilot load its interactive cards. The new Slack and Teams guide covers Claude Tag, Slackbot, Copilot Studio and Microsoft 365 Copilot.
Claude Code rules in Code Guidelines | PR Reviews
Claude Code rules in Code Guidelines CodeRabbit now reads your Claude Code rules from .claude/rules/ . A rule with paths frontmatter applies only to the files those globs match. A rule without paths gets the scope CodeRabbit infers from its content, like other guideline files.
Monday, October 19, 20264 releases
Tools for Cortex AI Gateway (Preview)
We are pleased to announce the preview of Tools for Cortex AI Gateway, which connects AI clients to the business tools your organization already uses through the Model Context Protocol (MCP). Supported clients include CoCo Desktop, CoCo CLI, Claude, and Cursor.
Copilot model policy API for enterprise, orgs, and teams
You can now use the REST API to retrieve and update Copilot model policies for enterprises, enterprise teams, enterprise apps, and organizations. What’s new GET and PATCH endpoints are now generally available for model policies at four levels: Enterprise: /enterprises/{enterprise}/copilot/model-policies Enterprise teams...
Bots - Precursor adds Monitor mode
We released Monitor mode at customers' request so they can test Precursor and the Precursor Interstitial without updating bot score. In Security > Settings , the Precursor Status dropdown now offers Off , Monitor , and Arm . Selecting Arm means Precursor detections can affect bot score and Challenge clearance.
Saturday, October 17, 20262 releases
DeepSeek V4.1 Flash 1017 now available on AI Gateway
DeepSeek V4.1 Flash 1017 is now available on AI Gateway . DeepSeek V4.1 Flash 1017 is a minor update to DeepSeek V4.1 Flash that improves reasoning, coding, agentic tasks, and image understanding. The coding gains show up in terminal work and in building and editing whole repositories, and the agentic gains in multi-step automation.
Friday, October 16, 20268 releases
Grok 4.7 and GLM 5.3 models (Preview)
The grok-4.7 and glm-5.3 models are now available in Public Preview in AI Functions, Cortex Inference, Cortex Agents, Snowflake CoWork, and Snowflake CoCo.
Workers, Cloudflare CLI - Search Cloudflare documentation with the Cloudflare CLI
Cloudflare CLI 1.0.0-beta.16 includes cf docs search , so you and your coding agent can find Cloudflare documentation without leaving the terminal. Search for guides, tutorials, and examples across Cloudflare products.
Elorian AI's Glimpse now available on AI Gateway
Glimpse from Elorian is now available on AI Gateway. The visual reasoning model accepts images and video to follow objects through motion, interpret spatial relationships, and connect an action to its physical consequences.
Beam model by Reflection is now available on Amazon SageMaker JumpStart and AWS Trainium
Beam, the first open weight model offered by US-based Reflection, is now available in Amazon SageMaker JumpStart, the model hub in Amazon SageMaker AI. According to Beam, they operate at the frontier of open weight models in its class, with strong performance across reasoning, coding, and agentic benchmarks.
Multi-repo support and other improvements for GitHub Copilot in Slack and Microsoft Teams
Multi-repo support in Slack and Microsoft Teams GitHub Copilot in Slack and Microsoft Teams now supports working across multiple repositories in a single conversation.
Know when the Buildkite CLI is done or needs you, without watching its tab
You can now see when bk preflight or bk build watch finishes or needs you, without switching back to its tab. From Buildkite CLI v3.64.0 , bk tells your terminal what it's doing, so a terminal that supports it can show you while you work somewhere else.
Weights & Biases 0.31.0
Notable Changes - The default API endpoint is now CoreWeave Forge at https://api.forge.coreweave.com, and run links point to https://forge.coreweave.com/wandb. Existing API keys stored for api.wandb.ai keep working without logging in again. Added - Python 3.15 is now supported (@dmitryduev in ) - wandb.init(resume="must") now works for offline runs.