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.
npx agentmods add instructions/memtensor/memos/agents-mdgit clone --depth 1 https://github.com/MemTensor/MemOSWhat 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 | $0.02750 | $0.02750 |
| Opus 5 | $0.01375 | $0.01375 |
| Sonnet 5 | $0.00550 | $0.00550 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade C, and why
MemOS AGENTS.md scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Do not run wide-scope `rm -rf` outside `src/`; do not `git push --force` or `git reset --hard origin/*`. How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Single source of truth for the project across AI runtimes. Claude Code, Codex, Cursor, Copilot, etc. all defer to this file. Runtime-specific adaptation belongs in each runtime's own file (Claude reads
CLAUDE.md); do not mix it in here.
Project Overview
MemOS / MemoryOS: a memory operating system for LLM agents. Python library plus a FastAPI service, providing multiple memory types (textual / tree / preference / skill / KV cache / LoRA parametric) plus scheduling, version management, and vector & graph storage.
- Repository: https://github.com/MemTensor/MemOS
- Documentation: https://memos-docs.openmem.net/home/overview/
- PyPI: https://pypi.org/project/MemoryOS/
- License: Apache-2.0
- Top-level package:
src/memos/. Distribution nameMemoryOS; import namememos. - CLI:
memos(entrymemos.cli:main) - API service:
memos.api.start_api:app
Repository Layout
| Path | Purpose |
|---|---|
src/memos/mem_os/ |
MOS / MOSCore — top-level Memory OS entry |
src/memos/mem_cube/ |
GeneralMemCube — memory container aggregating multiple memory types |
src/memos/memories/ |
Memory implementations: textual/, activation/, parametric/ |
src/memos/mem_scheduler/ |
Memory scheduler + monitors + ORM + task scheduling |
src/memos/mem_user/ |
User / multi-tenant management (MySQL / Redis backends) |
src/memos/mem_chat/ mem_reader/ mem_agent/ mem_feedback/ multi_mem_cube/ |
Chat sessions, ingest pipeline, agent integration, feedback channel, multi-cube routing |
src/memos/llms/ embedders/ vec_dbs/ graph_dbs/ chunkers/ parsers/ reranker/ |
Provider implementations (base.py + factory.py + each backend) |
src/memos/api/ |
FastAPI service (routers / handlers / middleware / MCP server) |
src/memos/configs/ |
All pydantic configuration classes (one-to-one with the modules above) |
src/memos/context/ |
Cross-thread context (trace_id / user / env) |
tests/ |
pytest cases, subdirectories mirror src/memos/ |
apps/ |
Independent sub-projects, each with its own README; not part of the main Harness flow |
extensions/ |
Official plugin examples |
docker/ docs/ evaluation/ scripts/ |
Deployment, documentation, evaluation, helper scripts |
.claude/agents/, .codex/agents/ |
Project-recommended AI sub-agent definitions |
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.
- 2d ago First seen · 156 lines · 2,750 tokens per session scan C 2eac7cfe6bb9
MemOS AGENTS.md is an instructions file published in the GitHub repository MemTensor/MemOS (11,091 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,750 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mem0 AGENTS.md
AGENTS.md instructions for mem0ai/mem0, covering agents.md, do not, where to look, repository map and setup.
ReMe AGENTS.md
Instructions for agentscope-ai/ReMe, covering agents.md, project principles, sources of truth, repository map and development setup.
PixelRAG CLAUDE.md
Instructions for StarTrail-org/PixelRAG, covering pixelrag, layout and conventions.
MemMachine AGENTS.md
Instructions for MemMachine/MemMachine, covering memmachine agent guide, repository orientation, environment setup, build, lint, and test commands and python (repo root).
chunkhound AGENTS.md
AGENTS.md instructions for chunkhound/chunkhound, covering chunkhound llm context, projectidentity, modificationrules, keycommands and development.
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.