Graphiti is a framework for building knowledge graphs that record facts, relationships, source provenance, and changes over time. Developers use it to give AI agents queryable context from conversations, enterprise data, documents, and external information. The catalogue instructions support working with Graphiti.
Borrowing it
Nothing to install: this file belongs to getzep/graphiti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getzep/graphiti/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/getzep/graphitiWrote 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.
[](https://agentmods.dev/instructions/getzep/graphiti/copilot-instructions)<a href="https://agentmods.dev/instructions/getzep/graphiti/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/getzep/graphiti/copilot-instructions/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.
<a href="https://agentmods.dev/instructions/getzep/graphiti/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/getzep/graphiti/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00528 | $0.00528 |
| Opus 5.5 | $0.00211 | $0.00211 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
graphiti copilot-instructions.md 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for Graphiti
Graphiti is a Python library for temporal knowledge graphs. The core package is
graphiti_core/. The REST service is server/, and the MCP server is
mcp_server/. AGENTS.md describes the layout, the commands, and the
conventions in detail. Read it before you review or change code.
Code review
A maintainer requests a Copilot review on a pull request. Copilot does not
review a pull request without a request. Review the diff against the criteria
below, and comment only when a criterion is not met. Do not comment on style
that ruff already enforces.
Required
- Every Python file starts with the copyright header
(
Copyright <year>, Zep Software, Inc.and the Apache 2.0 notice). Any year is acceptable. - Strings use single quotes, and lines are at most 100 characters
(
pyproject.toml). - No secret, credential, API key, or customer data is in the code or in the tests.
- Logging does not include sensitive data: no prompts, no episode content, no credentials.
- New behavior has tests. Core tests are under
tests/, server tests are underserver/tests/, and MCP server tests are undermcp_server/tests/. A test file istest_<feature>.py, and a test function istest_<behavior>. - A test that needs a database is in a file with the
_intsuffix and is marked@pytest.mark.integration. - A change to a public interface updates the docs or the examples.
Check for
- Side effects outside
graphiti_core/driver,graphiti_core/cross_encoder, andgraphiti_core/utils. Other modules are pure helpers. - A change to a Cypher query that works on Neo4j only. The drivers for FalkorDB and Neptune must keep working.
- A change to the bi-temporal fields (
valid_at,invalid_at,created_at,expired_at) that breaks the ordering rules. - A Pydantic model in
graphiti_core/modelswithout explicit type hints. - An async function that blocks the event loop.
Do not flag
- Code that
make formatormake lintalready accepts. - Missing docstrings on private helpers.
- The use of AI assistance by the contributor. AI assistance is acceptable in this repository.
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.
- 1mo ago First seen · 51 lines · 528 tokens per session scan A dbf8daa45087
graphiti copilot-instructions.md is an instructions file published in the GitHub repository getzep/graphiti (32,318 stars, last pushed today), licensed Apache-2.0. It adds 528 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-09-29.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.