AGENTS.md@ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphitiA

AGENTS.md@ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphiti from hidorakai002/ai-workspace-archive is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add hidorakai002/ai-workspace-archive/ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphiti/AGENTS.md@git:20260415.5cb4040

Pins git:20260415.5cb4040 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
hidorakai002/ai-workspace-archive
Path
ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphiti/AGENTS.md
Versions recorded
1
Latest version
git:20260415.5cb4040, committed Apr 15, 2026
Size
5,911 bytes
Repository stars
38
License
none declared

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Graphiti Memory

This directory contains the Graphiti-backed memory integration for CoPilot.
This file is developer documentation only — it is NOT injected into LLM prompts.
Runtime prompt instructions live in `prompting.py:get_graphiti_supplement()`.

## Scope

- Keep Graphiti and FalkorDB-specific logic in this package.
- Prefer changes here over scattering Graphiti behavior across unrelated copilot modules.

## Debugging

- Use raw FalkorDB queries to inspect stored nodes, episodes, and `RELATES_TO` facts before changing retrieval behavior.
- Distinguish user-provided facts, assistant-generated findings, and provenance/meta entities when evaluating memory quality.

## Design Intent

- Preserve per-user isolation through `group_id`-scoped databases and clients.
- Be careful about memory pollution from assistant/tool phrasing; extraction quality matters as much as ingestion success.
- Keep warm-context and tool-driven recall resilient: failures should degrade gracefully rather than break chat execution.

## Query Cookbook

Run everything from `autogpt_platform/backend` and use `poetry run ...`.

Get the `group_id` for a user:

```bash
poetry run python - <<'PY'
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hidorakai002/ai-workspace-archive/ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphiti/AGENTS.md@sha256:fb40834e0d6bf231

The line at the top of this page pins the label git:20260415.5cb4040, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_muganioiwfxwfvxm.svg)](https://markdownregistry.com/a/art_muganioiwfxwfvxm)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Apr 15, 2026.

versioncommittedcommitsizeaudit
git:20260415.5cb4040 latest2026-04-15 5cb4040 5,911 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (5911 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

hidorakai002/ai-workspace-archive · 38 stars · license none declared · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_muganioiwfxwfvxm
GET https://markdownregistry.com/api/v1/resolve?ref=hidorakai002/ai-workspace-archive/ai_agent_frameworks/major_frameworks/AutoGPT/autogpt_platform/backend/backend/copilot/graphiti/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/fb40834e0d6bf2319e25d3cd98c7c2eb62433a3c8edea45f098abc44554b4080

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from hidorakai002/ai-workspace-archive

open-pr SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/open-pr/SKILL.md · Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR…
v1.0.0 · audit A · 38 stars
orchestrate SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/orchestrate/SKILL.md · Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare…
v6.0.0 · audit A · 38 stars
pr-address SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/pr-address/SKILL.md · Address PR review comments and loop until CI green and all comments resolved. TRIGGER when user asks to address…
v1.0.0 · audit A · 38 stars
pr-polish SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/pr-polish/SKILL.md · Alternate /pr-review and /pr-address on a PR until the PR is truly mergeable — no new review findings, zero unresolved…
v1.0.0 · audit A · 38 stars
pr-review SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/pr-review/SKILL.md · Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check…
v1.0.0 · audit A · 38 stars
pr-test SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/pr-test/SKILL.md · E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to…
v2.1.0 · audit A · 38 stars
setup-repo SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/setup-repo/SKILL.md · Initialize a worktree-based repo layout for parallel development. Creates a main worktree, a reviews worktree for PR…
v1.0.0 · audit A · 38 stars
AGENTS.md@ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/vercel-react-best-practices AGENTS.md file
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/vercel-react-best-practices/AGENTS.md
git:20260404.656d1be · audit B · 38 stars
vercel-react-best-practices SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/vercel-react-best-practices/SKILL.md · React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing…
v1.0.0 · audit A · 38 stars
worktree SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/worktree/SKILL.md · Set up a new git worktree for parallel development. Creates the worktree, copies .env files, installs dependencies, and…
v3.0.0 · audit A · 38 stars
write-frontend-tests SKILL.md skill
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/.claude/skills/write-frontend-tests/SKILL.md · Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write…
v1.0.0 · audit A · 38 stars
AGENTS.md@ai_agent_frameworks/major_frameworks/AutoGPT AGENTS.md file
hidorakai002/ai-workspace-archive · ai_agent_frameworks/major_frameworks/AutoGPT/AGENTS.md
git:20260408.c85708c · audit A · 38 stars

Every file in hidorakai002/ai-workspace-archive

Browse by kind, by grade A, or by owner.