The daily firehose — everything the toolchain shipped today, already filtered.
// HOW THIS ISSUE IS MADE
We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.
Continue 1.16.0 adds Mercury Apply endpoint support, invokable markdown rules, tilde path resolution, and recommended models for tools.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds Mercury Apply endpoint support to the Inception LLM integration.
Continue config-yaml 1.21.0 adds Mercury Apply endpoint support to the Inception LLM provider.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds Mercury Apply endpoint support to the Inception LLM provider.
Qwen Code v0.0.12-nightly.2 adds skipLoopDetection config, vision model support, and an enhanced /init confirmation prompt.
└──▷ GET THIS VERSION
$ git clone --branch v0.0.12-nightly.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.0.12-nightly.2
└──▷ USE IT
Disable loop detection when running long autonomous agent tasks that would otherwise be interrupted by false positives.
json
{
"skipLoopDetection": true
}
›Adds skipLoopDetection configuration option to allow users to disable agent loop detection.
›Adds vision model support for Qwen-OAuth authentication flows.
›Enhances the /init command with a confirmation prompt before initializing.
›Enables tool call type coercion so mismatched argument types in tool calls are automatically corrected.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
CrewAI 0.193.0 makes RAG/knowledge/memory search params fully configurable and enables ChromaDB OpenAI embeddings.
└──▷ GET THIS VERSION
$ git clone --branch 0.193.0 https://github.com/crewAIInc/crewAI.git
# already have the repo? check out this version:$ git checkout 0.193.0
›Makes search parameters for RAG, knowledge, and memory fully configurable.
›Enables ChromaDB to use OpenAI API as an embedding function.
›Adds deeper observability tools for user-level insights.
LangChain 1.0.0a6 adds dynamic system prompt middleware, improved HITL patterns, and PEP 604 union support in tool node error handlers.
└──▷ GET THIS VERSION
$ git clone --branch langchain==1.0.0a6 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain==1.0.0a6
›Adds create_agent with middleware support, enabling pre/post processing layers to be composed into agent graphs.
›Adds dynamic system prompt middleware, allowing system prompts to be resolved at runtime within the middleware pipeline.
›Supports PEP 604 (| union) type syntax in tool node error handlers, enabling modern Python type annotations for error handler signatures.
›Introduces improved Human-in-the-Loop (HITL) patterns for agentic workflows.
›Adds stuff and map-reduce chains to the v1 package.
+1 moreshow less
›Drops Python 3.9 support; Python 3.10+ is now required for langchain v1.
└──▷ BREAKING ON UPGRADE
!create_react_agent is renamed to create_agent; existing code calling create_react_agent will break.
!Python 3.9 is no longer supported; running langchain v1 on Python 3.9 will fail.
browser-use 0.7.9 adds Actor mode for direct element interaction and a cloud browser integration.
└──▷ GET THIS VERSION
$ git clone --branch 0.7.9 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:$ git checkout 0.7.9
└──▷ USE IT
Use Actor mode to precisely locate and fill a specific page element by natural-language prompt, then hand off to an Agent for higher-level task completion.
python
from browser_use import Browser, Agent
from browser_use.llm.openai import ChatOpenAI
async def main():
llm = ChatOpenAI(api_key="your-api-key")
browser = Browser()
await browser.start()
page = await browser.new_page("https://github.com/login")
email_input = await page.must_get_element_by_prompt("username field", llm=llm)
await email_input.fill("your-username")
agent = Agent(browser=browser, llm=llm)
await agent.run("Complete login and navigate to my repositories")
await browser.stop()
›Adds Actor usage pattern via page.must_get_element_by_prompt() on Browser page objects, enabling precise LLM-guided element targeting and interaction without a full agent loop.
›Adds cloud_browser feature for connecting to cloud-hosted browser sessions.
›Logs the browser-use pip version on agent start for easier debugging and version tracing.