Agents
the power of open source, open harnesses, open agents, and communities 🔥 super fun to be a part of a community of builders who share cool w…
the power of open source, open harnesses, open agents, and communities 🔥 super fun to be a part of a community of builders who share cool work like this in the open. also been fun to see builders shar
the power of open source, open harnesses, open agents, and communities 🔥 super fun to be a part of a community of builders who share cool work like this in the open. also been fun to see builders sharing their middlewares that we’re adding to our community docs https://docs.langchain.com/oss/python/integrations/middleware I built deepagents-sandbox — a native Linux sandbox backend for Deep Agents. No Docker. No VM. Agents get a writable /workspace, blocked network by default, memory/PID limits, and timeout enforcement. It uses bubblewrap + cgroups v2 to isolate agent code execution with resource l…
Related
- i agree there should be managed agents, i just think they should be built on open harnesses and open memory standards
- 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
- 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…
- '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 …
- Speed of open source! Anthropic adds advisor strategy yesterday -> Emanuele adds an implementation as middleware less than 24 hours later!
Source: Harrison Chase (X) | 2026-04-25