LangChain ships Managed Deep Agents 0.8 with HTTP channels and user-scoped memory
LangChain · x · 2026-10-01
LangChain launched Managed Deep Agents 0.8, adding HTTP channels so agents can receive requests from any webhook, not just Slack — enabling use in internal tools, customer portals, and support systems.
Other additions:
- Identity-scoped auth and memory: user-owned credentials and per-user memory, so agents act with the right permissions and remember caller-specific context
- Built-in web search powered by Parallel
- File transfer in Slack
Managed Deep Agents is a code-first project layout (agent.py, instructions.md, identity/memory modules) that bundles production infrastructure — auth, memory, channels, tool management — so teams focus on agent behavior. The post demos an SMS expense agent by @ndrezn: text a receipt and it gets logged automatically.
Related event: LangChain Releases Managed Deep Agents 0.8(2 posts)→
More from coding & agent
- Google AI proposes RRSI to stop recursive self-improving agents from overfitting benchmarks — burkov · 2026-10-01
- DevDay demo: Codex builds Minecraft for 30-year-old Game Boy hardware via ModRetro plugin — pvncher · 2026-10-01
- Full Talking Video From One Image in 30 Minutes for ~$5 — gorkem · 2026-10-01
- tldraw launches ChatGPT plugin: sketch your app's logic and Codex builds it — DavidKPiano · 2026-10-01
- Storing Claude's Memory Inside a Notes Repo With Auto-Commits — theshawwn · 2026-10-01
- Investment banker builds M-Terminal financial platform with Claude in 2 months of evenings — nikhil_pratap · 2026-10-01