Zep Agent Skills turns verified agent traces into versioned, governed procedural memory
TheTuringPost · x · 2026-11-06
Zep.ai launched Zep Agent Skills (with an arXiv paper), a managed service giving production agents procedural memory by compiling verified successful runs into reusable Skills.
- Each task attempt is recorded as a Trace with ordered events, outcome, and verification strength; only verified attempts become evidence, and every Skill field cites its supporting events.
- A compiler with separate Reflector and Curator roles produces versioned Skills; scan and admission gates control activation, and verified use outcomes adjust search rank.
- Skills use the open Agent Skills format Anthropic donated to the Agentic AI Foundation; retrieval is via lexical search with progressive disclosure over API or MCP.
- On τ³-bench banking, AppWorld, and EnterpriseOps-Gym, Skills compiled from a teacher model's traces notably lift a student model's pass rate.
Related event: Zep launches Agent Skills, compiling proven runs into reusable skills(2 posts)→
More from coding & agent
- Expertise is knowing all the ways projects fail — that's what lets you babysit agents — RexDouglass · 2026-11-06
- Raindrop launches Simulations: auto-test AI agents on every PR with real production scenarios — soleio · 2026-11-06
- MoE Training Handbook Ch.2: A Runbook From Hardware Tests to Your First MoE — Nouamanetazi · 2026-11-06
- 9 copy-paste Claude prompts for code review, meeting notes, blind-spot checks and more — manishkhosiya · 2026-11-06
- RicursiveAI Releases From-Scratch Dense Ripple-65B, Tops 80% on Terminal Bench 2.1 — DZhang50 · 2026-11-06
- Team's 24/7 infra-monitoring agent spots anomalies 'before the fire,' user says — antoine_chaffin · 2026-11-06