by nvandessel · MCP Server · ★ 23
f(eedback)loop Every correction you give an AI agent is a lesson that dies at the end of the session. floop makes it stick. A correction becomes a behavior. Behaviors connect into a graph. The graph uses spreading activation — the same model cognitive science uses to describe how human memory retrieves associations — to find the right behaviors for your current context. Connections strengthen through Hebbian learning. The result is an agent that gets better over time instead of starting from zero every mornin
| Stars | 23 |
| Forks | 5 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.9979070364943/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-20 |
| Created | 2026-01-26 |
| Platforms | claude-code, cli, codex, go, mcp |
| Est. Tokens | ~187k |
Explore other popular mcp server tools:
floop is Spreading activation memory for AI coding agents - corrections in, context-aware behaviors out.. It is categorized as a MCP Server with 23 GitHub stars.
floop is primarily written in Go. It covers topics such as ai-agents, ai-coding, behavior-learning.
You can find installation instructions and usage details in the floop GitHub repository at github.com/nvandessel/floop. The project has 23 stars and 5 forks, indicating an active community.
floop is released under the Apache-2.0 license, making it free to use and modify according to the license terms.