zep-eval-harness

zep-eval-harness is a skill for Claude Code from getzep/zep. It costs 139 tokens per session (3,028 once invoked), scanned A, original, Apache-2.0.

An evaluation framework for Zep memory search and question answering. It loads conversations, usage data, and documents into Zep knowledge graphs, then tests whether questions retrieve useful context and produce accurate answers.

In plain words
What is it for?
Use it to split and summarize documents, ingest users and documents, run single-search evaluation cases, inspect graphs, and analyze retrieval and answer results.
Why use it?
It provides a repeatable way to measure memory retrieval quality instead of judging answers manually or relying only on whether data was successfully loaded.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to split and summarize documents, ingest users and documents, run single-search evaluation cases, inspect graphs, and analyze retrieval and answer results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getzep/zep/zep-eval-harness
About the project

getzep/zep is a repository of examples, framework integrations, ingestion tools, and evaluation utilities for building agent memory with Zep Cloud, a managed service for storing and retrieving information used by AI agents. It is for developers integrating Zep Cloud into agent applications and workflows. The catalogue skills and MCP entry are add-ons for working with that ecosystem.

getzep/zep · 4,895 stars · on GitHub · help.getzep.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add getzep/zep --skill zep-eval-harness
Clone the repo
git clone --depth 1 https://github.com/getzep/zep

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zep-eval-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/getzep/zep/zep-eval-harness/github.svg)](https://agentmods.dev/skills/getzep/zep/zep-eval-harness)
Your own site
<a href="https://agentmods.dev/skills/getzep/zep/zep-eval-harness"><img src="https://agentmods.dev/badge/skills/getzep/zep/zep-eval-harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for zep-eval-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/getzep/zep/zep-eval-harness"><img src="https://agentmods.dev/badge/skills/getzep/zep/zep-eval-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00139 $0.03028
Opus 5 $0.00069 $0.01514
Sonnet 5 $0.00028 $0.00606
Haiku 4.5 $0.00014 $0.00303

Measured 9d ago against content hash c79db57eff47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

zep-eval-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

zep-eval-harness/.claude/commands/zep-eval-harness/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zep Eval Harness

An end-to-end evaluation framework for testing Zep's memory retrieval and question-answering capabilities. The pipeline ingests user conversations, telemetry, and documents into Zep knowledge graphs, then evaluates retrieval quality by searching those graphs with test questions and grading the results against golden answers.

The pipeline has four steps:

  1. Chunk documents — split documents and generate LLM-based summaries + contextualizations
  2. Ingest users — create Zep users, add conversations and telemetry to user graphs
  3. Ingest documents — send pre-chunked documents to a standalone Zep document graph
  4. Evaluate — for each test case: search graphs → assess context completeness → generate LLM response → grade answer accuracy

Scope: Single-Shot Retrieval

The harness evaluates single-shot retrieval only. Every test case issues one retrieval from the raw test question via auto search (config/evaluation_config/retrieval_strategy.py), then hands the resulting context block to the response model in a single turn — no second retrieval round, no query reformulation. This mirrors deterministic/programmatic retrieval, not the tool-based pattern where an agent is handed Zep search tools (e.g. search_graph from the Zep MCP server) and decides when and what to search.

That makes the harness a clean instrument for the ingestion and search configuration, but it says nothing about agent tool-use behavior. A tool-based agent may do better (several targeted searches, reformulating after a weak result) or worse (never searching, poorly phrased queries, running out of turns). When reporting results, scope conclusions to the config under test and never present them as a prediction of production agent performance.

Evaluation Metrics

Context Completeness (PRIMARY) — Did Zep retrieve sufficient information to answer the question?

  • COMPLETE: All necessary information present in the retrieved context
  • PARTIAL: Some relevant information, but incomplete
  • INSUFFICIENT: Missing critical information

Read the full file on GitHub · 228 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 228 lines · 139 tokens per session scan A c79db57eff47

Subscribe to this mod's changes

zep-eval-harness is a skill published in the GitHub repository getzep/zep (4,895 stars, last pushed 5d ago), licensed Apache-2.0. It adds 139 tokens to every session and 3,028 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

mem0ai/mem0 · 47 tokens

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…

mem0ai/mem0 · 146 tokens

peek

Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.

mem0ai/mem0 · 52 tokens

mine

Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.

MemPalace/mempalace · 21 tokens

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens