LangChain roadmap: every major player converging on persistent agents
hwchase17 · x · 2026-11-21
A chart from LangChain's "The Future of Agents" event lays out the LLM evolution ladder: LLMs → Tool Calling → Reasoning Models → Coding Agents → Persistent Agents, with "we are here" marking the shift to persistent agents.
- Whether you call them persistent, always-on, proactive, or Replit's Missions, every major player is converging on the same bet: autonomous agents that remember context and act on your behalf.
- The takeaway: intelligence is everywhere now — the winner will be whoever nails trust.
More from coding & agent
- Inkling 2 Mini runs locally in 16GB RAM: 5.4B-active MoE tops its size class — simonguozirui · 2026-11-21
- Thinking Machines' Inkling 2 Mini: 26B looped transformer tops open-model coding boards — victormustar · 2026-11-21
- Replit engineer: 'I no longer need anything locally for my job' — amasad · 2026-11-21
- Replit Agent lands in Microsoft Teams to turn chats into action — amasad · 2026-11-21
- Dev shares a simple local Claude Code combo: use another frontier model as a second pair of eyes — DavidWells · 2026-11-21
- PageIndex: vectorless RAG with no embeddings or chunking hits 98.7% on FinanceBench — dr_cintas · 2026-11-21