Agents
Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of age…
Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of agent memory to third parties. Memory enables sticky, personali
Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of agent memory to third parties. Memory enables sticky, personalized agentic experiences and creates strong lock-in.
Related
- 'Harnesses are intimately tied to memory, which means that by choosing an open harness you are choosing to own your memory, and not have it …
- Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that onl…
- memory ownership is why we need open harnesses blog about this coming this weekend
- Great piece. The lock-in point is the one nobody talks about enough. If your agent’s memory lives behind someone else’s API, you don’t have …
- The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the entire value layer. Lo…
- managed agents are the right form factor but the lock-in is real if your agent harness lives inside a model provider, you dont own the memor…
Source: Harrison Chase (X) | 2026-04-12