This looks very similar to what I've seen with a different harness - https://github.com/AMAP-ML/LongHorizon-Harness. It's critique pattern looks like another version of lh-harness without looping toward an overarching…
How is this different from headroom? Mcptoon seems like it's specific to tool calls. https://github.com/headroomlabs-ai/headroom
I'm surprised no one has mentioned Cambridge Analytica.
There's even a community plugin MCP that makes this easier. Afaik the hot reload is the only thing that "beats" this but I haven't had issues with Agents interacting with obsidian through the MCP - I'm not sure how much…
This looks very similar to what I've seen with a different harness - https://github.com/AMAP-ML/LongHorizon-Harness. It's critique pattern looks like another version of lh-harness without looping toward an overarching…
How is this different from headroom? Mcptoon seems like it's specific to tool calls. https://github.com/headroomlabs-ai/headroom
I'm surprised no one has mentioned Cambridge Analytica.
There's even a community plugin MCP that makes this easier. Afaik the hot reload is the only thing that "beats" this but I haven't had issues with Agents interacting with obsidian through the MCP - I'm not sure how much…