Ebbforge - 10M agent Rust swarm engine, 8 fundamental benchmarks
Rust swarm vs LLM agents is clever positioning, but benchmarks are self-designed and lack third-party validation.
Cognitive memory for AI agents — learns from use, forgets what's irrelevant, strengthens what matters. Single binary, fully offline.
Offline AI memory that learns without LLM calls—Hebbian decay plus vectorization beats mem0 architecture.
AI agent developers, self-hosted AI enthusiasts
mem0 · Cognee · Zep
Rust swarm vs LLM agents is clever positioning, but benchmarks are self-designed and lack third-party validation.
Claims brain-like cognition with zero LLM calls, but zero evidence of actual learning.
Impressive Rust substrate layer, but crate collection without proof of integration or adoption.
ACT-R decay and Hebbian learning as native primitives, not vector hacks.
Python FFI bridge via PyO3 is clever, but tool-calling frameworks are crowded.
24MB peak RAM beats JS agents at 700MB—actual engineering, not marketing.