LangChain ships Managed Deep Agents 0.8 with user-scoped memory, auth, and HTTP channels
LangChain · x · 2026-10-01
LangChain released Managed Deep Agents 0.8, targeting four production pain points: memory, auth, channels, and tool management.
- Identity-scoped auth and memory: user-owned credentials and per-user memory let agents act with the right permissions and remember caller-specific context
- HTTP channels: agents can now receive requests from any webhook source — internal tools, portals, support systems — not just Slack; demoed via an expense agent that logs receipts from a text message
- Built-in web search powered by Parallel, plus file transfer in Slack
Managed Deep Agents bundles the Deep Agents harness with production infrastructure, organized as a code-first repo layout (agent.py, instructions.md, identity.py, memory.py).
Related event: LangChain Releases Managed Deep Agents 0.8(2 posts)→
More from coding & agent
- One prompt, 30 minutes: NVIDIA VSS Blueprint 3.3 builds production-line vision AI agents — NVIDIAAI · 2026-10-01
- Developer runs decision models locally on Ollama's new Nimble for sensitive data — ollama · 2026-10-01
- 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