I don't know why Pierre's post is dead, but I wanted to ask if it is accurate to describe Pixelagent as an MCP-compatible memory layer, and what its competitors are.<p>If memory is the centerpiece, I suggest leading with it, rather than the ambiguous "Your AI Data Infrastructure".
Your readme doesn't mention any example of multiple agents. We don't need another wrapper to anthropic/openai/*. Without being able to select between multiple tools/agents - you only need 2 lines of code to achieve llm calls, and another 2 lines for state management.<p>That said the interface is more idiomatic that others agent frameworks that show up here.<p>It also wasn't clear where the last N messages is being persisted. Db/file/adapters/?<p>Good luck!
Exciting to see a fellow builder in the space! Love how memory management and observability is built-in.<p>Today, I just re-implemented Google's AlphaEvolve for Perlin noises using my own minimal agentic framework (<a href="https://toolkami.com/alphaevolve-toolkami-style/" rel="nofollow">https://toolkami.com/alphaevolve-toolkami-style/</a>), will probably steal a trick or two from you.
I'll just leave this here: <a href="https://github.com/The-Pocket/PocketFlow">https://github.com/The-Pocket/PocketFlow</a>
100 lines of code agent lib that's not tied to a commercial offering