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 skills add acnlabs/OpenPersona --skill memorygit clone --depth 1 https://github.com/acnlabs/OpenPersonaWrote 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/skills/acnlabs/openpersona/memory)<a href="https://agentmods.dev/skills/acnlabs/openpersona/memory"><img src="https://agentmods.dev/badge/skills/acnlabs/openpersona/memory/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/skills/acnlabs/openpersona/memory"><img src="https://agentmods.dev/badge/skills/acnlabs/openpersona/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01578 |
| Opus 5.5 | $0.00000 | $0.00631 |
| Sonnet 5.5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
memory 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Faculty — Cognition
Cross-session memory that lets your persona remember, recall, and learn from past interactions. Memories persist across conversations and shape how you engage with the user over time.
Supported Providers
| Provider | Env Var for Key | Best For | Status |
|---|---|---|---|
| Local | (none, default) | Zero-dependency, file-based, full privacy | ✅ Built-in |
| Mem0 | MEMORY_API_KEY |
Managed memory service, automatic extraction | ⚠️ Experimental |
| Zep | MEMORY_API_KEY |
Structured memory with temporal awareness | ⚠️ Experimental |
Note: Only the local provider is bundled. External providers require their SDK to be installed and
MEMORY_PROVIDERset accordingly. The local provider stores memories as JSON lines in~/.openclaw/memory/persona-<slug>/.
The provider is set via MEMORY_PROVIDER environment variable: local (default), mem0, or zep.
When to Store (Automatic)
Store memories proactively during conversation — don't wait for the user to say "remember this":
- Preferences: "I'm vegetarian", "I prefer dark mode", "I hate mornings"
- Personal facts: names, relationships, jobs, locations, birthdays
- Recurring topics: if the user brings up a subject 2+ times, it's worth remembering
- Emotional moments: breakthroughs, frustrations, celebrations
- Milestones: relationship stage transitions, achievement moments (→ also log as evolution event)
- Explicit requests: "Remember that I..." or "Don't forget..."
Do NOT store:
- Casual filler ("how's it going", "thanks")
- Content the user explicitly marks as private or asks you to forget
- Secrets, passwords, API keys, or sensitive credentials (→ use Body credential management instead)
When to Recall (Automatic)
Retrieve memories proactively when they're relevant — don't wait to be asked:
- User mentions a topic you have memories about → recall and weave in naturally
- Start of a new conversation → retrieve recent memories for context continuity
- User seems to repeat themselves → check if you already know this, acknowledge it
- Emotional callback → "Last time you mentioned X, you seemed Y — how's that going?"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 161 lines · 0 tokens per session scan A 1a70273e2a37
memory is a skill published in the GitHub repository acnlabs/OpenPersona (54 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,578 tokens. 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.
Other skills, from other repositories
clawdi
API keys, tokens, memory, sessions, Projects, integrations. Use Clawdi when a task needs passwords or safe credential storage/provision, missing user memory or Project/Vault context, past conversations, Clawdi share URLs, or connected-service fallback such as Gmail, GitHub, Notion, Drive, or Calendar. Do not invoke…
memory-consolidate
A memory-maintenance skill that stores a small number of durable, searchable facts and keeps the main memory file concise.
company-agent-infrastructure
Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…
lobu
Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.
add-compact
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
add-qmd
Add QMD (Query Markup Documents) as an advanced memory search backend. Upgrades the built-in grep-based memorysearch with hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed. Triggers on "add qmd", "qmd memory", "semantic memory search", "upgrade memory".