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/mem9-ai/mem9/agents-mdgit clone --depth 1 https://github.com/mem9-ai/mem9Wrote 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/mem9-ai/mem9/agents-md)<a href="https://agentmods.dev/instructions/mem9-ai/mem9/agents-md"><img src="https://agentmods.dev/badge/instructions/mem9-ai/mem9/agents-md.svg" alt="Measured on agentmods" 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 | $0.03034 | $0.03034 |
| Opus 5 | $0.01517 | $0.01517 |
| Sonnet 5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
mem9 AGENTS.md scanned grade A with 2 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` calls use explicit timeouts. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
python3 -c 'from pathlib import Path; import re, subprocess; text = Path("AGENTS.md").read_text(); paths = re.findall(r"`([^`]+/AGENTS\.md)`", text); tracked = set(subprocess.check_output(["git", "ls-files", "*AGENTS.md" How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this repo is
mnemos is shared, cloud-persistent memory for coding agents. The core system is a Go REST server backed by TiDB/MySQL, plus four agent integrations, a standalone CLI, and a small Astro site.
Cross-repo relationship: mem9 and mem9-node
mem9-nodeis a sibling repository at../mem9-node. It is not a directory inside this repo.dashboard/appin this repo is the frontend half of the dashboard product. In day-to-day discussion, "the dashboard backend" usually refers to code inmem9-node, especiallyapps/apiandapps/worker.dashboard/app/src/api/analysis-client.tscallsmem9-nodeendpoints forv1/analysis-jobs,v1/deep-analysis/*, and taxonomy/deep-analysis workflows.mem9-node/apps/api/src/mem9-source.service.tsdepends on this repo's Go API as the mem9 source of truth. ItsMEM9_SOURCE_API_BASE_URLdefaults tohttp://127.0.0.1:8080/v1alpha2/mem9s.dashboard/app/src/api/provider-http.tsstill sends the dashboard's standard/your-memory/api/...data requests to this repo's Go server (/v1alpha2/mem9s/...) usingX-API-KeyandX-Mnemo-Agent-Id.- When a task touches dashboard UI and backend behavior together, inspect both repos before assuming the implementation belongs only under
server/in this repo.
High-level modules
| Path | Role |
|---|---|
server/ |
Go API server, business logic, TiDB SQL, tenant provisioning, runtime usage |
cli/ |
Standalone Go CLI for exercising mnemo-server endpoints |
dashboard/app/ |
React dashboard SPA; frontend half of the dashboard product |
openclaw-plugin/ |
OpenClaw memory plugin (kind: "memory") |
opencode-plugin/ |
OpenCode plugin (@mem9/opencode) |
claude-plugin/ |
Claude Code plugin (hooks + skills) |
codex-plugin/ |
Codex plugin (hooks + $mem9:* skills) |
dsh-plugin/ |
DeepSeek Harness DSH/Cordis bundle |
docs/design/ |
Architecture/proposal notes and design drafts |
site/ |
Astro static site — deployed to Netlify from main branch |
e2e/ |
Live end-to-end scripts against a running server |
benchmark/MR-NIAH/ |
Benchmark harness for OpenClaw memory evaluation |
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.
- 4d ago First seen · 253 lines · 3,034 tokens per session scan A 12177ba456f2
mem9 AGENTS.md is an instructions file published in the GitHub repository mem9-ai/mem9 (1,202 stars, last pushed 9d ago), licensed Apache-2.0. It adds 3,034 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
EchoBird AGENTS.md
AGENTS.md instructions for edison7009/EchoBird, covering agents.md — echobird, project shape, ci gates (must pass locally before pushing), lesson (learned the hard way) and verification habits.
Agentkey AGENTS.md
Instructions for chainbase-labs/Agentkey, covering agents.md, what this repo is, directory structure, key commands and test a local edit against every detected agent.
superdesign-skill AGENTS.md
Instructions for superdesigndev/superdesign-skill, covering project agent memory, what this repo is, skill flow invariant: two entry paths, ground truth for cli behavior and plugin packaging & release.
seektty AGENTS.md
Instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.
causal-memory CLAUDE.md
Instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.
dsh-deepread AGENTS.md
Instructions for xiehuan123/dsh-deepread, covering agents.md, upstream authority, plugin identities and source files, release documentation and harness lifecycle rules.