Zep launches Agent Skills: compile verified agent runs into reusable skills
TheTuringPost · x · 2026-11-06
Zep introduced Agent Skills, a procedural memory system that turns verified, successful agent runs into reusable Skills. The pipeline:
- Tracing: records agent actions, tool calls, and outcomes as a Trace; Traces can be imported from Braintrust and LangSmith.
- Verification: checks whether the task actually succeeded using independent evidence, not the agent's own claims.
- Compilation: a Reflector proposes reusable instructions while a Curator validates them against evidence; each Skill field links back to specific Trace events.
- Admission: security scans and quality gates decide whether a new Skill version is admitted.
Related event: Zep launches Agent Skills, compiling proven runs into reusable skills(2 posts)→
More from coding & agent
- Approved action ran twice in 3 agent frameworks: crash-resume test — KaleidoscopeNew9259 · 2026-11-06
- Melite open-sources agentic ComfyUI: agents that generate and extend their own harness — data-cypher-000 · 2026-11-06
- Crash test: LangGraph, Pydantic AI and OpenAI Agents SDK all double-charge payments — KaleidoscopeNew9259 · 2026-11-06
- 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