Deep Agents
LangChain brings asynchronous background workers to Deep Agents
LangChain has introduced async subagents for Deep Agents, separating user-facing coordination from background work on long-running tasks. The company says the…
AI21 Labs launches Teel, a Python runtime for faster agent workflows
AI21 Labs has introduced Teel, an open source Python runtime designed to overlap independent, IO-bound calls in ordinary sequential Python code. The company says Teel…
LangChain opens Managed Deep Agents in public beta on LangSmith Cloud
LangChain has put Managed Deep Agents into public beta on LangSmith Cloud. The service runs the open-source Deep Agents harness and the production runtime around it, so…
LangChain: OpenWiki memory made an agent 5x more accurate on cross-source questions
LangChain says an agent using OpenWiki, its open-source wiki compiler, as a memory layer was roughly 5x more accurate than one relying on search alone on questions that…
LangChain: Open Models GLM-5 and MiniMax M2.7 Now Rival Closed Rivals on Agent Tasks
LangChain says open weight models such as GLM-5 and MiniMax M2.7 now perform similarly to closed frontier models on core agent tasks like file operations, tool use and…
LangChain releases Open SWE, an open-source framework for internal coding agents
LangChain has released Open SWE, an open-source framework for building internal coding agents that work inside tools such as Slack, Linear and GitHub. According to…
LangChain launches Deep Agents deploy, an open rival to Claude Managed Agents
LangChain has launched Deep Agents deploy in beta, a single-command way to put a model agnostic, open source agent harness into production. The company positions it as…
LangChain Adds ScaleDown Models to Cut Cost of Long-Running Agents
LangChain has released a langchain-scaledown integration and added ScaleDown support to the LangSmith LLM Gateway, aiming to make context management in long-running…
LangChain Revamps Skills in Deep Agents with Tool Binding and Pinning
LangChain has revamped skills support in Deep Agents, adding the ability to bind tools to skills, pin skills at runtime and reload skills in the middle of a thread.…