LocalAI is an inference server that runs language, vision, voice, image, and video models through compatible APIs on local hardware. It is used to operate models privately across different hardware, including CPU-only systems, and supports applications, agents, and multi-user services. The catalogue contains instructions for using LocalAI.
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 mudler/LocalAI --skill memory-check-own-filesgit clone --depth 1 https://github.com/mudler/LocalAIWrote 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/mudler/localai/memory-check-own-files)<a href="https://agentmods.dev/skills/mudler/localai/memory-check-own-files"><img src="https://agentmods.dev/badge/skills/mudler/localai/memory-check-own-files/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/mudler/localai/memory-check-own-files"><img src="https://agentmods.dev/badge/skills/mudler/localai/memory-check-own-files.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 | $0.00076 | $0.00465 |
| Opus 5.5 | $0.00030 | $0.00186 |
| Sonnet 5.5 | $0.00015 | $0.00093 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
memory-check-own-files 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 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.
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.
What it actually says
Check what you can read
Say what you know and where it comes from. Do not guess and do not invent notes.
What you can read
- The index of the short memory, in your prompt under "Notes you can consult". It has up to three parts: the user's notes, the notes of this saved agent, and the notes of this conversation.
- The details of a topic, with
context_read. Give the topic and, when you know it, the scope. - The agent profile, in your prompt under "Agent profile", when this chat runs a saved agent. It holds the user's standing rules for the agent.
- The files your file tools reach, if you have any. A saved agent may reach one folder only. Do not say that a file does not exist because you cannot reach it; say that you cannot see it.
You cannot read the notes of another agent or another conversation. You cannot change a file. Saving is a proposal that the user confirms.
When the user asks what you remember
- Read every index line in your prompt.
- For each topic that matters to the question, call
context_readand read it. - Answer in plain words, grouped as "about you", "about how I work for you" and "about this conversation". Leave a group out when it is empty.
- Say that the user can read, edit and delete the notes on the Memory tab of their account, and that you can propose a change for them to confirm.
- If you hold nothing, say so and offer to remember something.
Before you answer a personal question
Read the index and the topic that matches, then the profile. If they disagree, the user's current request wins; say what the note says and ask which one is right. If a note may be old, say that it may be old.
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 · 30 lines · 76 tokens per session scan A efcf3bcc0cb7
memory-check-own-files is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 465 once invoked, about $0.0003 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 2026-11-04.
memory-check-own-files compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| memory-check-own-filesmudler/LocalAI | Skill | 50k | yesterday | MIT | A | 76 | Claude Code, Codex |
| llm-deploymentoyi77/1ai-skills | Skill | 17 | yesterday | MIT | B | 44 | Claude Code |
| llm-integrationLuuOW/meridian-mcp | Skill | 0 | 24d ago | MIT | A | 29 | Claude Code, Codex |
| mem0-vercel-ai-sdkmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 146 | Claude Code, Codex |
| pausemem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 30 | Claude Code |
| mineMemPalace/mempalace | Skill | 60k | yesterday | MIT | A | 21 | Claude Code |
| agent-carnetyamadashy/repomix | Skill | 29k | yesterday | MIT | A | 67 | Claude Code, Codex |