Timeline page 25/26 · 768 total
Aider v0.86.0 Aider v0.86.0
EN Added support for all GPT-5 models. Added support for Grok-4 via xai/grok-4 and openrouter/x-ai/grok-4 model names. Added support for gemini/gemini-2.5-flash-lite-preview-06-17 model, by Tamir Zahavi-
python-v0.7.2 python-v0.7.2
EN What's Changed Update website 0.7.1 by @ekzhu in #6869 Update OpenAIAssistantAgent doc by @ekzhu in #6870 Update 0.7.1 website ref by @ekzhu in #6871 Remove assistant related methods from OpenAIAgent
Improved Agent tools, steerability, and usage visibility Improved Agent tools, steerability, and usage visibility
EN Sending messages while Cursor is working now does a better job of steering the agent. Messages will run at the next ideal time, usually after a tool call, versus waiting until the generation completes
Providing ChatGPT to the Entire U.S. Federal Workforce Providing ChatGPT to the Entire U.S. Federal Workforce
EN Today, OpenAI for Government is announcing a new partnership with the U.S. General Services Administration (GSA) to launch a transformative initiative. For the next year, ChatGPT Enterprise will be av
Choosing measurement frameworks to fit your organizational goals Choosing measurement frameworks to fit your organizational goals
EN Measuring software development effectiveness requires choosing the right framework to match your organizational goals. This guide explores popular frameworks like SPACE, DevEx, and DORA, offering prac
Shared terminal with Agent, context usage in chat, and faster edits Shared terminal with Agent, context usage in chat, and faster edits
EN Agents can now use your native terminal. A new terminal will be created when needed and runs in the background if one isn't already open. Click Focus to bring it up front where you can see Agent comma
python-v0.7.1 python-v0.7.1
EN What's New OpenAIAgent supports all built-in tools Feat/OpenAI agent builtin tools 6657 by @tejas-dharani in #6671 Support nested Team as a participant in a Team Supporting Teams as Participants in a
Announcing OpenAI DevDay 2025 Announcing OpenAI DevDay 2025
EN We’re hosting our third annual OpenAI DevDay on October 6, 2025 at Fort Mason in San Francisco.
pyautogen-v0.10.0 pyautogen-v0.10.0
EN Setup publishing for pyautogen package ( #6813 )
python-v0.6.4 python-v0.6.4
EN What's New More helps from @copilot-swe-agent for this release. Improvements to GraphFlow Now it behaves the same way as RoundRobinGroupChat , SelectorGroupChat and others after termination condition
Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models
EN Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models
Agent Planning, Better Context & Faster Tab Agent Planning, Better Context & Faster Tab
EN Agents now plan ahead with structured to-do lists, making long-horizon tasks easier to understand and track.
python-v0.6.2 python-v0.6.2
EN What's New Streaming Tools This release introduces streaming tools and updates AgentTool and TeamTool to support run_json_stream . The new interface exposes the inner events of tools when calling run_
Background Agents in Slack Background Agents in Slack
EN You can now launch Background Agents directly from Slack by mentioning **@Cursor**. Agents can read the thread, understand what's going on, and create PRs in GitHub, all without leaving the conversati
Bugbot, Background Agent access to everyone, and one-click MCP install Bugbot, Background Agent access to everyone, and one-click MCP install
EN Cursor 1.0 is here!
Announcing Gemma 3n preview: Powerful, efficient, mobile-first AI Announcing Gemma 3n preview: Powerful, efficient, mobile-first AI
EN Gemma 3n is a cutting-edge open model designed for fast, multimodal AI on devices, featuring optimized performance, unique flexibility with a 2-in-1 model, and expanded multimodal understanding with a
Simplified Pricing, Background Agent and Refreshed Inline Edit Simplified Pricing, Background Agent and Refreshed Inline Edit
EN Introducing unified request-based pricing, Max Mode for all top models, and Background Agent for parallel task execution. Plus, improved context management with `@folders` support, refreshed Inline Ed
Rules generation, improved agent terminal and MCP images Rules generation, improved agent terminal and MCP images
EN You can now generate rules directly from a conversation using the `/Generate Cursor Rules` command. This is useful when you want to capture the existing context of a conversation to reuse later.
New funding to build towards AGI New funding to build towards AGI
EN Today we’re announcing new funding—$40B at a $300B post-money valuation, which enables us to push the frontiers of AI research even further, scale our compute infrastructure, and deliver increasingly
Chat tabs, Custom modes & Faster indexing Chat tabs, Custom modes & Faster indexing
EN Other (6)
Reliability, Keyboard Shortcuts & Early access opt-in Reliability, Keyboard Shortcuts & Early access opt-in
EN Patches (11)