MemPalace Setup and Operation
MemPalace/mempalace
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
Persistent memory for AI coding agents. An agent skill from omega-memory/omega-memory.
Install Omega Memory
$ npx skills add omega-memory/omega-memory --skill omega-memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install omega-memory/omega-memory omega-memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omega-memory .claude/skills/omega-memory && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .claude/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add omega-memory/omega-memory --skill omega-memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install omega-memory/omega-memory omega-memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/omega-memory .agents/skills/omega-memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .agents/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add omega-memory/omega-memory --skill omega-memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install omega-memory/omega-memory omega-memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/omega-memory .cursor/skills/omega-memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .cursor/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/omega-memory/omega-memory.git --path skills/omega-memory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add omega-memory/omega-memory --skill omega-memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install omega-memory/omega-memory omega-memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/omega-memory .gemini/skills/omega-memory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .gemini/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install omega-memory/omega-memory omega-memoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add omega-memory/omega-memory --skill omega-memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/omega-memory .github/skills/omega-memory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .github/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add omega-memory/omega-memory --skill omega-memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install omega-memory/omega-memory omega-memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omega-memory/omega-memory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/omega-memory .opencode/skills/omega-memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "omega-memory" agent skill from https://github.com/omega-memory/omega-memory/tree/main/skills/omega-memory into .opencode/skills/omega-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omega-memory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
omega-memory- GitHub stars
- 220
- Token cost
- ~1.6k tokens
- SKILL.md length
- 629 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Persistent memory for AI coding agents. An agent skill from omega-memory/omega-memory.
- Works in 7 steps: Vector similarity — Embedding search… → Full-text search — FTS5 with BM25 scoring → Strong signal short-circuit — Skip… → …
- Tasks that involve Agent memory
- SKILL.md covers Setup, Core Tools, Retrieval Architecture and Best Practices, plus 2 more sections
- Calls pip3
What it does
Omega Memory is an agent skill from omega-memory/omega-memory. Persistent memory for AI coding agents. Teaches agents how to use OMEGA's MCP tools for storing decisions, querying context, coordinating multi-agent workflows, and resuming tasks across sessions.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Python 3.11+, Claude Code, Cursor, Windsurf, Zed
It sits in Agent Workflows, covering Agent memory and MCP servers. It works with Model Context Protocol. The repository describes itself as: Persistent memory for AI coding agents. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Agent memory
- Tasks that involve MCP servers
Example prompts
- “/omega-memory”
Requirements
- Python 3
- Compatibility (from SKILL.md): Python 3.11+, Claude Code, Cursor, Windsurf, Zed
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Vector similarity — Embedding search (bge-small-en-v1.5, 384-dim) via sqlite-vec
- Full-text search — FTS5 with BM25 scoring
- Strong signal short-circuit — Skip expensive phases when FTS5 finds an exact match
- Score fusion — Reciprocal Rank Fusion combines vector + text scores
- Contextual boosting — Boost results matching current file, project, or tags
- Cross-encoder reranking — ms-marco-MiniLM-L-6-v2 rescores top candidates
- Assembly — Dedup, normalize, apply minimum relevance threshold
What it can do on your machine
Read from SKILL.md and the folder at commit 3840290. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pip3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
omegamax.copypi.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Python 3.11+, Claude Code, Cursor, Windsurf, Zed
From compatibility in the SKILL.md frontmatter.
Context cost
Omega Memory loads about 1.6k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 629 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from omega-memory/omega-memory at commit 3840290, republished under its Apache-2.0 licence (© omega-memory). 629 words, ~1,639 tokens.
Download SKILL.mdSave it as
.claude/skills/omega-memory/SKILL.md (or your agent's skills folder).- name
- omega-memory
- description
- Persistent memory for AI coding agents. Teaches agents how to use OMEGA's MCP tools for storing decisions, querying context, coordinating multi-agent workflows, and resuming tasks across sessions.
- compatibility
- Python 3.11+, Claude Code, Cursor, Windsurf, Zed
- license
- Apache-2.0
- metadata.category
- memory
- metadata.pypi
- omega-memory
- metadata.github
- omega-memory/omega-memory
OMEGA Memory
Persistent memory for AI coding agents. OMEGA gives your agent a knowledge graph it can query, learn from, and coordinate through across sessions.
This skill teaches you how to use OMEGA's MCP tools effectively.
Setup
pip3 install omega-memory[server]
omega setup # auto-configures your editor + downloads embedding model
omega doctor # verify everything worksWorks with Claude Code, Cursor, Windsurf, Zed, and any MCP client.
Core Tools
OMEGA provides 12 MCP tools. Here's when to use each one.
Storing Memories
omega_store(content, event_type, metadata?, entity_id?)
Store decisions, lessons, and context that should persist across sessions.
| Event Type | When to Use | TTL |
|---|---|---|
decision | Architectural choices, technology selections | 90 days |
lesson_learned | Debugging insights, patterns that worked/failed | 90 days |
user_preference | Code style, workflow preferences, tool choices | Permanent |
error_pattern | Recurring errors and their fixes | 30 days |
task_completion | Completed work with outcomes | 14 days |
checkpoint | Mid-task state for resumption | 7 days |
omega_store("Switched from REST to GraphQL for the dashboard API — reduces N+1 queries", "decision")
omega_store("User prefers early returns, max 2 levels of nesting", "user_preference")
omega_store("pytest fixtures with db cleanup must use function scope, not session scope", "lesson_learned")Don't store: Raw code output, tool results, transient status updates, anything shorter than a sentence.
Querying Memories
omega_query(query, mode?, limit?, entity_id?)
Search memories by meaning, not just keywords. Uses hybrid retrieval: vector similarity + full-text search + cross-encoder reranking.
| Mode | When to Use |
|---|---|
semantic (default) | Find memories by meaning — "how did we handle auth?" |
phrase | Exact substring match — find a specific term or identifier |
timeline | Recent memories grouped by day — "what happened this week?" |
browse | List by type, session, or recency — explore what's stored |
omega_query("database migration strategy")
omega_query("what decisions were made about the API", mode="timeline", days=7)
omega_query("pytest", mode="phrase")
omega_query(mode="browse", browse_by="type")Pro tip: Query before starting work. Prior decisions and lessons save time and prevent repeating mistakes.
Session Management
omega_welcome(project?) — Call at session start. Returns recent context, active reminders, and project state. This is how your agent picks up where it left off.
omega_checkpoint() — Save current task state mid-session. If the session ends unexpectedly, the next omega_welcome restores this context.
omega_resume_task(task_id) — Resume a previously checkpointed task with full context.
Memory Maintenance
omega_reflect() — Analyze memory quality: duplicates, contradictions, coverage gaps.
omega_maintain(action) — Run maintenance operations: consolidation, compaction, health checks.
Retrieval Architecture
OMEGA's query pipeline runs 7 phases to find the most relevant memories:
- Vector similarity — Embedding search (bge-small-en-v1.5, 384-dim) via sqlite-vec
- Full-text search — FTS5 with BM25 scoring
- Strong signal short-circuit — Skip expensive phases when FTS5 finds an exact match
- Score fusion — Reciprocal Rank Fusion combines vector + text scores
- Contextual boosting — Boost results matching current file, project, or tags
- Cross-encoder reranking — ms-marco-MiniLM-L-6-v2 rescores top candidates
- Assembly — Dedup, normalize, apply minimum relevance threshold
This hybrid approach achieves 95.4% on LongMemEval (500-question benchmark).
Show full SKILL.md (245 more words)Show less
Best Practices
What to Store
- Architectural decisions with reasoning ("chose X because Y")
- Debugging insights that took effort to discover
- User preferences stated explicitly ("always use..." / "never...")
- Cross-session context that future sessions need
What NOT to Store
- Information already in the codebase (read the code instead)
- Transient state (build output, test results)
- Anything shorter than a meaningful sentence
- Speculative conclusions from reading a single file
Query Patterns That Work
- Before starting a task:
omega_query("prior decisions about [feature area]") - Before modifying a file:
omega_query(context_file="/path/to/file.py") - After debugging:
omega_store("[root cause and fix]", "lesson_learned") - When user says "remember":
omega_store("[what they said]", "user_preference")
Anti-Patterns
| Don't | Do Instead |
|---|---|
| Store every tool result | Store only insights and decisions |
| Query with single words | Use natural language questions |
Skip omega_welcome at session start | Always call it — it loads critical context |
Store without event_type | Always specify type for proper TTL and dedup |
| Guess from stale memory | Query OMEGA to verify current state |
How It Works Under the Hood
- Storage: SQLite with WAL mode. Single file at
~/.omega/omega.db. - Embeddings: bge-small-en-v1.5 via ONNX Runtime (~90MB RAM). LRU cache (512 entries).
- Vector search: sqlite-vec extension for ANN similarity search.
- Text search: FTS5 with BM25 ranking.
- Dedup: Jaccard similarity with per-type thresholds (0.70-0.90). Content-level and embedding-level.
- Memory evolution: Similar memories merge (Zettelkasten-style) instead of creating duplicates.
- TTL: Automatic expiry based on event type. Permanent for preferences, 7-90 days for others.
- Privacy: Everything stays local. No cloud, no telemetry. Apache-2.0 licensed.
Links
- PyPI: omega-memory
- GitHub: omega-memory/omega-memory
- Docs: omegamax.co/docs
- Benchmarks: omegamax.co/benchmarks
© omega-memory, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/omega-memory of omega-memory/omega-memory.
Open the folder on GitHubat commit 3840290
Compare with similar skills
Omega Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Omega Memory this skillomega-memory/omega-memory | 220 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| MemPalace Setup and OperationMemPalace/mempalace | 59k | — | ~2.2k | Automated safety check: Pass | MIT | |
| agentmemory Setup and Diagnosticsrohitg00/agentmemory | 29k | — | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Qmdbreferrari/obsidian-mind | 5k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Memori MCP Memory UsageMemoriLabs/Memori | 17k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Shared Agent Knowledge Commonsmozilla-ai/cq | 1.3k | — | ~6.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
agentmemory Setup and Diagnostics
rohitg00/agentmemory
Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.
Qmd
breferrari/obsidian-mind
Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.
Memori MCP Memory Usage
MemoriLabs/Memori
Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.
Shared Agent Knowledge Commons
mozilla-ai/cq
Queries a shared knowledge store before acting, proposes newly discovered insights, and confirms or flags existing entries, so agents stop rediscovering the same failures.
Save to Atlas Memory
pacifio/atlas
Saves the decisions, facts, failures and architecture notes from a conversation into Atlas's shared memory so other agents and later sessions can reuse them.
More from omega-memory/omega-memory
Omega Memory
omega-memory/omega-memory
Persistent memory for AI coding agents. An agent skill from omega-memory/omega-memory.
Related
Works with
Categories
Questions about Omega Memory
What does Omega Memory do?
Persistent memory for AI coding agents. An agent skill from omega-memory/omega-memory. Omega Memory is an agent skill from omega-memory/omega-memory. Persistent memory for AI coding agents.
When should I use Omega Memory?
Omega Memory fits situations like: tasks that involve Agent memory; tasks that involve MCP servers.
How do I install Omega Memory in Claude Code?
Run `npx skills add omega-memory/omega-memory --skill omega-memory -a claude-code`. Or copy the skill folder (skills/omega-memory in omega-memory/omega-memory) into .claude/skills/omega-memory in your project. Claude Code loads it when a task matches its description.
How do I install Omega Memory in Codex?
Run `npx skills add omega-memory/omega-memory --skill omega-memory -a codex`. Or copy the skill folder (skills/omega-memory in omega-memory/omega-memory) into .agents/skills/omega-memory in your project. Codex loads it when a task matches its description.
Can I use Omega Memory in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add omega-memory/omega-memory --skill omega-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omega-memory, .gemini/skills/omega-memory, .github/skills/omega-memory and .opencode/skills/omega-memory in your project.
What does Omega Memory need to run?
Going by SKILL.md and its folder, Omega Memory needs the command-line tools its instructions call (pip3). Our summary lists: Python 3. Compatibility (from SKILL.md): Python 3.11+, Claude Code, Cursor, Windsurf, Zed.
Does Omega Memory access the network?
SKILL.md names 2 domains. As links in the text: omegamax.co and pypi.org. This is read from the text; nothing was executed.
Is Omega Memory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Omega Memory use?
Omega Memory is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Omega Memory use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Omega Memory?
Skills that share tags, products or a category with Omega Memory: MemPalace Setup and Operation (MemPalace/mempalace, 59k stars), agentmemory Setup and Diagnostics (rohitg00/agentmemory, 29k stars), Qmd (breferrari/obsidian-mind, 5k stars) and Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Omega Memory?
omega-memory (a GitHub user) maintains it in omega-memory/omega-memory, which has 220 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.
Source: omega-memory/omega-memory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.