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 Ships Managed Deep Agents 0.8 with User Memory and HTTP Channels(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16