What is zylos-memory?

A persistent memory system that stores information from conversations in organized Markdown files. It keeps identity, current work, user preferences, project references, and session history across separate sessions.

Use it to synchronize conversations into structured memory, rotate session notes, consolidate older information, and save context for future work.

It reduces the need to repeat important context after a session ends. It also gives the agent a way to organize current state, review past sessions, and move older information into an archive.

zylos-memory — Skill for Claude Code by zylos-ai/zylos-core

About the project

Zylos is open-source infrastructure that gives an AI agent persistent memory, scheduled activity, communication channels, and the ability to maintain and extend itself. Individuals and teams use it with Claude Code or Codex through Telegram, Lark, or a web console. Its catalogue add-ons define settings, instructions, and skills for operating the agent.

zylos-ai/zylos-core · 1,160 stars · on GitHub · zylos.ai

Install

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.

Any agent

npx skills add zylos-ai/zylos-core --skill zylos-memory

Clone the repo

git clone --depth 1 https://github.com/zylos-ai/zylos-core

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zylos-ai/zylos-core/zylos-memory/github.svg)](https://agentmods.dev/skills/zylos-ai/zylos-core/zylos-memory)

Your own site

<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/zylos-memory"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/zylos-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/zylos-memory"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/zylos-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,405 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 63
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Output Handling · line 180
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.02405
Opus 5.5	$0.00027	$0.00962
Sonnet 5.5	$0.00014	$0.00481
Haiku 4.5	$0.00007	$0.00241

Measured 2mo ago against content hash e164ddf87903, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zylos-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 2mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/consolidate.js, scripts/daily-commit.js, scripts/memory-status.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/zylos-memory/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory System

Maintains persistent memory across sessions via tiered markdown files. This skill must be run via a runtime-appropriate background subagent mechanism. For Claude, use the Task tool (subagent_type: general-purpose, model: sonnet, run_in_background: true). For Codex, prefer the session's native subagent tools spawn_agent/wait_agent (host session tools — they do not appear in codex --help) with a Codex-supported model; do not hardcode sonnet.

Architecture

~/zylos/memory/
├── identity.md              # Bot soul + digital assets (always loaded)
├── state.md                 # Active working state (always loaded)
├── references.md            # Pointers to config files (always loaded)
├── users/
│   └── <id>/profile.md      # Per-user preferences
├── reference/
│   ├── decisions.md         # Key decisions with rationale
│   ├── projects.md          # Active/planned projects
│   ├── preferences.md       # Shared team preferences
│   └── ideas.md             # Uncommitted plans and ideas
├── sessions/
│   ├── current.md           # Today's session log
│   └── YYYY-MM-DD.md        # Past session logs
└── archive/                 # Cold storage

Memory Sync

Priority

Memory Sync is the highest-priority internal maintenance task. When triggered, run it before handling queued user messages.

Memory Sync is maintenance-only. A sync subagent must not reply through C4, process user-facing tasks, modify business/project repositories, install or upgrade components, restart services, or apply runtime changes outside the sync flow below.

Trigger Paths

Session init: if C4 unsummarized count is over threshold, launch memory sync.
Scheduled context check: if context usage is high, launch memory sync.

Both launch a background subagent using the current runtime's supported subagent mechanism with this file's Sync Flow as the prompt.

Codex Background Execution

In Codex, use the session's native subagent tools: spawn_agent to launch the sync subagent and wait_agent to collect its result. These are host session tools — they do not appear in codex --help. For a single long-running command, an async exec session (exec_command + write_stdin) also works. Bare nohup ... & does NOT survive the tool-call boundary and must never be used for sync. Never use PM2 for sync — do not create PM2 services, run pm2 start ... codex exec ..., or fork an extra codex exec sidecar: one-shot sync processes leave stopped services piling up in the PM2 list. If the session exposes no native background-agent capability, run the sync inline as a last resort and note that in the handoff/status.

Read the full file on GitHub · 210 lines

Files

What ships with it

29 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.

Changes

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.

2mo ago First seen · 210 lines · 68 tokens per session scan A e164ddf87903

Subscribe to this mod's changes

zylos-memory is a skill published in the GitHub repository zylos-ai/zylos-core (1,160 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,405 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 2026-08-30.

Memory and context ai ai-worker own-your-data personal-ai-assistant self-evolving team-collaboration

zylos-memory next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zylos-memoryzylos-ai/zylos-core	Skill	1.2k	yesterday	MIT	A	68	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
knowledge-meeting-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	44	Claude Code, Codex
knowledge-claim-consolidationopenclaw/openclaw	Skill	394k	yesterday	MIT	A	98	Claude Code, Codex
knowledge-correctopenclaw/openclaw	Skill	394k	yesterday	MIT	A	55	Claude Code, Codex
knowledge-captureopenclaw/openclaw	Skill	394k	yesterday	MIT	A	51	Claude Code, Codex
knowledge-entitiesopenclaw/openclaw	Skill	394k	yesterday	MIT	A	43	Claude Code, Codex