palaia

A local memory system for OpenClaw agents that stores information in SQLite, a file-based database, and supports searchable memories, projects, scopes and automatic capture. It is designed to keep memories after crashes and between sessions.

In plain words
What is it for?
Use it to enable persistent memory, search stored context, separate memories by project or scope and automatically capture information for later sessions.
Why use it?
It prevents an agent from losing useful conversation or project context when a session ends or the process fails.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/byte5ai/palaia/skill
Any agent
npx skills add byte5ai/palaia --skill skill
Clone the repo
git clone --depth 1 https://github.com/byte5ai/palaia

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.08070
Opus 5 $0.00024 $0.04035
Sonnet 5 $0.00010 $0.01614
Haiku 4.5 $0.00005 $0.00807

Measured 3d ago against content hash 42ce9bfc6b68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

palaia scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Claude Code** (`~/.claude/settings.json`):
Origin

This is a copy

100% identical to palaia — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/openclaw-plugin/skill/SKILL.md · 833 lines

How it starts

The opening of the file, as written. The whole thing — 833 lines — stays where its author put it; the contents beside it link to each section on GitHub.

palaia v2.7 — Agent Memory Skill

palaia is the memory system for OpenClaw agents. It gives you persistent, searchable, crash-safe memory across sessions. You don't need to understand how it works — just use the commands below.

First-Time Setup

When a user asks you to "set up palaia", "enable memory", or "remember things across sessions", run these steps:

pip install "palaia[fastembed]"
palaia init

This creates .palaia/ with SQLite storage and automatically configures fastembed for semantic search. No manual configuration needed.

Confirm success to the user: "Memory is ready. I'll automatically remember important context from our conversations."

If pip is not available, try alternatives in this order:

python3 -m pip install "palaia[fastembed]"
uv tool install "palaia[fastembed]"
pipx install "palaia[fastembed]"

Optional extras (install as needed):

pip install "palaia[mcp]"          # MCP server for Claude Desktop, Cursor
pip install "palaia[curate]"       # Knowledge curation

Note: palaia[fastembed] already includes sqlite-vec for native SIMD vector search. No separate install needed.

OpenClaw Plugin Setup (for Auto-Capture and Auto-Recall)

After the CLI is installed, wire it into OpenClaw:

openclaw plugins install @byte5ai/palaia

Then activate the memory slot in OpenClaw config:

// openclaw.json
{
  plugins: {
    slots: { memory: "palaia" }
  }
}

Restart the gateway and verify:

openclaw gateway restart
palaia doctor

Agent Identity (optional)

Single-agent systems work with the default name. For multi-agent setups:

palaia init --agent YOUR_AGENT_NAME

Updating palaia

When the user asks to update, or when palaia status shows a version mismatch:

palaia upgrade

This auto-detects the install method (pip/uv/pipx), preserves all installed extras (fastembed, mcp, sqlite-vec, curate), runs palaia doctor --fix, and upgrades the OpenClaw plugin if installed. No manual steps needed.

Read the full file on GitHub · 833 lines

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.

  1. 3d ago First seen · 833 lines · 48 tokens per session scan B 42ce9bfc6b68

Subscribe to this mod's changes

palaia is a skill published in the GitHub repository byte5ai/palaia (19 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 8,070 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to palaia, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

mission-control

Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.

builderz-labs/mission-control · 34 tokens

codemark

Manage structural code bookmarks that survive refactoring. Use when the user says "remember this", "bookmark this", "save this location", "load my bookmarks", "what do I have bookmarked", "mark this code", "codemark", or when starting a new session and needing to reload context from a previous session. Also use…

DanielCardonaRojas/codemark · 97 tokens

setup

Set up or reconfigure session-recall for the user — install, pick the interaction language, choose a local or cloud embedder, optionally enable team sharing. Trigger when the user asks to "set up session-recall", "настрой session-recall", install it, change its embedder/language, or enable sharing with a colleague.…

AbsoluteMode/session-recall · 84 tokens

memx

Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.

NeoLi00/memX · 26 tokens

session-recall

Search the unified local history of past Claude Code, Codex, and Cursor sessions at the START of a task when the user references a prior bug, feature, decision, file, or piece of work. Use before assuming fresh context for prompts such as "remember when…", "we worked on…", "the X bug", "back to…", "what did we decide…

AbsoluteMode/session-recall · 92 tokens

douyin-video-downloader

Collect and download Douyin videos, cover images, direct music audio, and user-page video lists using a local Node.js CLI and SQLite. Use this skill when the user wants to parse a Douyin share link, inspect video quality or cover candidates, download MP4 video, download direct Douyin music audio, collect public…

chemny/douyin-video-downloader · 94 tokens