EverOS is a Python library and local-first memory runtime that gives AI agents a portable memory layer across apps, devices, and workflows. It stores conversations, files, and agent activity as readable Markdown while maintaining local indexes for retrieval and reuse. The catalogue add-ons provide commands, skills, hooks, and settings for using EverOS with coding agents.
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.
git clone --depth 1 https://github.com/EverMind-AI/EverOSWrote 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/commands/evermind-ai/everos/ask)<a href="https://agentmods.dev/commands/evermind-ai/everos/ask"><img src="https://agentmods.dev/badge/commands/evermind-ai/everos/ask/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/commands/evermind-ai/everos/ask"><img src="https://agentmods.dev/badge/commands/evermind-ai/everos/ask.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 | $0.00017 | $0.00387 |
| Opus 5.5 | $0.00007 | $0.00155 |
| Sonnet 5.5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
ask 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.
What it actually says
EverMem Ask
Answer a question using both memory search results and current conversation context.
Question
{{question}}
Instructions
-
Search memories using
evermem_searchMCP tool with relevant keywords. Start with 10 results. -
Evaluate results:
- If memories provide useful context, note what you learned
- If more detail needed, search again with different keywords (up to 3 searches)
- If no relevant memories found, that's OK - proceed with what you know
-
Combine sources to answer:
- Memory search results (past sessions)
- Current conversation context (this session)
- Your general knowledge (when applicable)
-
Be honest about sources:
- "Based on our discussion on [date]..." - when citing memory
- "From our current session..." - when citing current context
- "I don't have any recorded information about this" - when memories don't help
- "Based on general best practices..." - when using general knowledge
-
Admit uncertainty:
- If memories are incomplete or unclear, say so
- If you're inferring rather than recalling, make that clear
- It's better to say "I don't know" than to guess
Response Format
Start with a direct answer, then provide supporting context:
[Direct answer to the question]
**From memories:**
- [Relevant points from past sessions, with dates]
**Current context:**
- [Relevant points from this session, if any]
**Note:** [Any caveats or gaps in knowledge]
Now answer the user's question.
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 · 58 lines · 17 tokens per session scan A 488f7e1a60d6
ask is a command published in the GitHub repository EverMind-AI/EverOS (13,467 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 387 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
wiki
LLM wiki knowledge base — understands natural language. Say what you want (use a personal specialist method, edit an external resource through a registered adapter, capture or shape an Idea, add a URL, collect a catalog, track inventory, ask a question, research, audit, or resume work) and it routes to the right…
ingest
Ingest source material into an active wiki. Accepts URLs, file paths, PDFs, freeform text, or processes the inbox. Supports tweets via Grok MCP.
checkpoint
Export, refresh, verify, or import a comprehensive cross-topic Project Knowledge Checkpoint for a repository, with privacy checks.
ll
Extract lessons learned from the current session. Scans conversation for error→fix patterns, user corrections, and discoveries, then saves structured lessons to the wiki.
retract
Remove user-selected data or a source from wiki-controlled local files, including archives and session context. Dry-run first, apply explicitly, then verify.
session
Capture, list, rehydrate, and promote llm-wiki session context. Supports automated hook capture into HUB/.sessions plus explicit promotion into topic raw notes.