Kremis – Deterministic memory graph for AI agents (Rust)
Deterministic graph memory vs. embeddings is clever, but fragmentation of AI memory ecosystems is already painful.
Gliding Horse is a multi-agent orchestration framework built in Rust that supports PDCA scheduling and knowledge graph-based agents, with comprehensive Chinese documentation, and is suitable for building enterprise-level AI agent systems.
MESI coherence for agent memory is clever, but LangGraph and AutoGen already own this space.
Developers building multi-agent AI systems
LangGraph · AutoGen · CrewAI
Deterministic graph memory vs. embeddings is clever, but fragmentation of AI memory ecosystems is already painful.
Unifies siloed agent memory via MCP, but Mem0 and Zep already exist.
15-phase belief scheduler with decay mechanics, but unproven in production agent pipelines.
Trigger-based cognitive architecture for Claude Code loses context anyway without API-level state persistence.
Compaction tree cuts context from 100K tokens to 3K without losing memory.
Local-first AI memory beating Mem0 on speed and privacy with Rust-powered Bayesian beliefs.