Persis implements biologically inspired memory for Claude through 15 tools running compiled Rust via WASM on Cloudflare's edge. The core cycle is lucian_record to store patterns (gated by a 6-factor significance model), lucian_recall to retrieve by context, and lucian_reinforce to strengthen or weaken memories based on feedback. Patterns decay naturally using Ebbinghaus curves, and 8 behavioral drives (curiosity, mastery, coherence, etc.) modulate agent personality over time. Useful when you want Claude to remember past code review failures, build research expertise across weeks, or develop institutional knowledge about your infrastructure without manually curating what stays or goes. Memory is per-user isolated via Durable Objects with sub-millisecond recall at scale.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent