palaia 2.4

Local, cloud-free memory for OpenClaw agents.

Palaia — The Knowledge System for AI Agent Teams

Your agents forget. Palaia doesn't.

---

What Palaia Does

AI agents are stateless by default. Every session starts from scratch — no memory of past decisions, no shared knowledge between agents, no context that survives a restart.

Palaia gives your agents a persistent, searchable knowledge store. They save what they learn. They find it again by meaning, not keyword. They share it across tools and sessions — automatically.

---

What Palaia Is Not

• Not a chatbot or prompt manager
• Not a cloud service (everything runs locally)
• Not a vector database you manage yourself (it manages itself)
• Not limited to one tool — works with OpenClaw, Claude Desktop, Cursor, and any MCP client

---

What You Get

Capability	What it means
Agents remember across sessions	Knowledge survives restarts, tool switches, and team handoffs
Find anything by meaning	Hybrid BM25 + vector search across 6 embedding providers
Zero-config local setup	SQLite with native SIMD vector search — no separate database process
Works everywhere via MCP	One memory store for OpenClaw, Claude Desktop, Cursor, and more
Multi-agent ready	Private, team, and public scopes — agents see what they should
Crash-safe by default	SQLite WAL mode survives power loss, kills, OOM
Fast	Embed server keeps model in RAM — CLI queries ~1.5s, MCP/Plugin <500ms
Scales when needed	Swap to PostgreSQL + pgvector for distributed teams, no code changes

---

Comparison

Feature	Palaia	claude-mem	Mem0	Stock Memory
Local-first	Yes	Yes	No (cloud)	Yes
Cross-tool (MCP)	Yes (any MCP client)	No (Claude Code only)	No	No
Native Vector Search	sqlite-vec / pgvector	ChromaDB (separate)	Cloud	No
Structured Types	memory/process/task	decisions/bugfixes	No	No
Multi-Agent Scopes	private/team/public	No	Per-user	No
Smart Tiering	HOT/WARM/COLD	No	No	No
Embedding Providers	6 (configurable)	1 (fixed)	Cloud	None
Open Source	MIT	AGPL-3.0	Partial	N/A
Crash-safe (WAL)	Yes	Partial	N/A	No

---

Install

Recommended: Tell your agent

Paste this into your OpenClaw agent (works for install AND update):

Install or update the Palaia memory skill from ClawHub to the latest version (even if already present). Read the SKILL.md completely and follow it step by step. Run palaia init, then palaia doctor --fix and resolve all warnings — don't stop until the doctor report is clean. Set up completely.

The agent handles everything: ClawHub skill install, pip setup, plugin config, and verification.

Manual Setup

pip install "palaia[fastembed]"
palaia init
palaia doctor --fix

Optional extras:

pip install "palaia[mcp]"          # MCP server for Claude Desktop, Cursor
pip install "palaia[curate]"       # Knowledge curation
pip install "palaia[postgres]"     # PostgreSQL + pgvector backend

Note: palaia[fastembed] already includes sqlite-vec for native vector search and the embed-server auto-starts on first query. No manual optimization needed.

Upgrading? palaia upgrade — auto-detects install method, preserves extras, runs doctor.

MCP Setup (Claude Desktop, Cursor, Claude Code — no OpenClaw needed)

pip install "palaia[mcp,fastembed]"
palaia init

Add to your MCP config:

• Claude Desktop: ~/.config/claude/claude_desktop_config.json
• Cursor: .cursor/mcp.json
• Claude Code: ~/.claude/settings.json

{
  "mcpServers": {
    "palaia": {
      "command": "palaia-mcp"
    }
  }
}

Quick Start

palaia write "API rate limit is 100 req/min" \
  --type memory --tags api,limits                   # Save knowledge
palaia query "what's the rate limit"                # Find it by meaning
palaia status                                        # Check health

---

Documentation

Document	Description
Getting Started	Installation, first steps, quick tour
Storage & Search	SQLite, PostgreSQL, sqlite-vec, pgvector, embedding providers
MCP Server	Setup for Claude Desktop, Cursor, tool reference, read-only mode
Embed Server	Performance optimization, socket transport, daemon mode
Multi-Agent	Scopes, agent identity, team setup, aliases
Configuration	All config keys, embedding chain, tuning
CLI Reference	All commands with flags and examples
Migration Guide	Import from other systems, flat-file migration
Architecture	Module map, data flows, design decisions
SKILL.md	Agent-facing documentation (what agents read)
Contributing	Versioning, release process, development setup
Changelog	Release history

---

Development

git clone https://github.com/byte5ai/palaia.git
cd palaia
pip install -e ".[dev]"
pytest

Links

• palaia.ai — Homepage
• PyPI — Package registry
• ClawHub — Install via agent skill
• OpenClaw — The agent platform Palaia is built for
• CHANGELOG — Release history

---

MIT — (c) 2026 byte5 GmbH