LangChain ships Managed Deep Agents v0.9 with agent-created schedules and per-run config
LangChain · x · 2026-10-08
LangChain released Managed Deep Agents v0.9 with three notable features:
- Schedules SDK: agents can create reminders, follow-ups, and recurring tasks mid-conversation, running under the requester's permissions with results returned to the same channel.
- Per-run configuration: a single deployment can pick model, skills, MCP servers, and sandbox per run, serving multiple teams or repos.
- Slack reactions: agents acknowledge messages as soon as a run starts.
The updates aim to make internal Slack-resident agents work more like teammates.
More from coding & agent
- LangChain revamps Deep Agents skills as teams adopt them as the standard for agent domain knowledge — LangChain · 2026-10-08
- llama.cpp lands on Windows: Windows ML adds experimental GGUF support as Microsoft showcases local AI — ggerganov · 2026-10-08
- mitchellh Calls His OpenAI Dot to Move Benchmarks Across Machines via Tailscale — charliermarsh · 2026-10-08
- A Developer's Map of the Data Tooling Landscape: Ingestion, Storage, Modeling, Governance — bibryam · 2026-10-08
- Operator-1 launches as autonomous document extraction agent for long tables and sprawling PDFs — ycombinator · 2026-10-08
- good-css: 47 modern CSS techniques that make coding agents actually use :has() and subgrid — mattpocockuk · 2026-10-08