Agent skill

Memora

A skill your agent uses when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

MITAuto-check passedAgent Workflows

Install Memora

skills CLI

$ npx skills add agentic-box/memora --skill memora -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install agentic-box/memora memora --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-plugin/skills/memora .claude/skills/memora && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .claude/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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

$skill-installer install https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora

Type 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.

skills CLI

$ npx skills add agentic-box/memora --skill memora -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install agentic-box/memora memora --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-plugin/skills/memora .agents/skills/memora && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .agents/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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.

skills CLI

$ npx skills add agentic-box/memora --skill memora -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install agentic-box/memora memora --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-plugin/skills/memora .cursor/skills/memora && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .cursor/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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

$ gemini skills install https://github.com/agentic-box/memora.git --path claude-plugin/skills/memora

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add agentic-box/memora --skill memora -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install agentic-box/memora memora --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-plugin/skills/memora .gemini/skills/memora && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .gemini/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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.

GitHub CLI

$ gh skill install agentic-box/memora memora

Installs 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).

skills CLI

$ npx skills add agentic-box/memora --skill memora -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-plugin/skills/memora .github/skills/memora && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .github/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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.

skills CLI

$ npx skills add agentic-box/memora --skill memora -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install agentic-box/memora memora --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/agentic-box/memora.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-plugin/skills/memora .opencode/skills/memora && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "memora" agent skill from https://github.com/agentic-box/memora/tree/main/claude-plugin/skills/memora into .opencode/skills/memora/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memora", 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: memora
GitHub stars: 731
Token cost: ~813 tokens
SKILL.md length: 314 words
Files: 1
Skills in repo: 1
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

Works in 6 steps: Search before creating - avoid duplicates → Use metadata for structured data… → Tag consistently - use hierarchical tags → …
Working with persistent memory across sessions
SKILL.md covers When to Use, Core Tools, Tag Conventions and Best Practices, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memora is an agent skill from agentic-box/memora. Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent memory and MCP servers. It works with Model Context Protocol, Cloudflare and SQLite. The repository describes itself as: Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP. The licence is MIT.

When your agent uses it

Working with persistent memory across sessions
Storing/retrieving knowledge
Managing TODOs/issues
Context from previous sessions would be helpful

Example prompts

“/memora”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Search before creating - avoid duplicates
Use metadata for structured data (section, subsection, project)
Tag consistently - use hierarchical tags
Boost important memories - they rank higher in searches
Use hybrid search as default - it combines keyword + semantic
Review insights periodically - find stale items and consolidation opportunities

What it can do on your machine

Read from SKILL.md and the folder at commit c5624e8. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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.

Context cost

Memora loads about 813 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 314 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~813

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 agentic-box/memora at commit c5624e8, republished under its MIT licence (© agentic-box). 314 words, ~813 tokens.

Download SKILL.mdSave it as .claude/skills/memora/SKILL.md (or your agent's skills folder).

name: memora
description: Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
version: 0.2.20

Memora - Persistent Semantic Memory

Memora is the persistent memory system for this environment. Use memora MCP tools to store, search, and organize knowledge across sessions.

When to Use

Session start: Relevant memories are auto-injected via hook
Storing decisions: Use memory_create to save architectural decisions, patterns, preferences
Finding context: Use memory_hybrid_search to find relevant past work
Tracking work: Use memory_create_todo / memory_create_issue for task tracking
Organizing knowledge: Use memory_hierarchy to browse organized memories

Core Tools

Creating Memories

memory_create - Store a new memory (auto-deduplicates, suggests hierarchy)
memory_create_todo - Create a TODO with priority (high/medium/low)
memory_create_issue - Create an issue with severity (critical/major/minor)
memory_create_section - Create organizational headers
memory_create_batch - Bulk create multiple memories

Searching

memory_hybrid_search - Best search: combines keyword + semantic (use this by default)
memory_semantic_search - Pure vector similarity search
memory_list - List/filter by tags, dates, metadata
memory_list_compact - Lightweight listing (id, preview, tags only)

Organizing

memory_hierarchy - View memories in section/subsection tree
memory_tags - List allowed tags
memory_tag_hierarchy - View tag namespace tree
memory_link - Create typed relationships between memories
memory_clusters - Detect related memory clusters

Maintenance

memory_find_duplicates - Find and review potential duplicates (LLM-powered)
memory_merge - Merge two memories together
memory_insights - Get activity summary, stale items, patterns
memory_stats - Database statistics
memory_boost - Increase a memory's importance ranking

Visualization

Knowledge graph available at http://localhost:8765 when running
memory_export_graph - Export as interactive HTML file

Tag Conventions

Use hierarchical tags with / separators:

memora/knowledge - General knowledge
memora/todos - Task items
memora/issues - Bug/issue tracking
memora/auto-capture - Auto-captured content
memora/sections - Organizational headers
project-name/topic - Project-specific tags

Best Practices

Search before creating - avoid duplicates
Use metadata for structured data (section, subsection, project)
Tag consistently - use hierarchical tags
Boost important memories - they rank higher in searches
Use hybrid search as default - it combines keyword + semantic
Review insights periodically - find stale items and consolidation opportunities

Auto-Capture

When MEMORA_AUTO_CAPTURE=true is set, the PostToolUse hook automatically captures:

Git commits (appended to per-project commit log)
Test results (failures become issues)
Web research (GitHub repos, documentation)
Documentation edits (README, CHANGELOG, etc.)

Files

Just SKILL.md in claude-plugin/skills/memora of agentic-box/memora.

Open the folder on GitHubat commit c5624e8

Compare with similar skills

Memora 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.

Memora compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Memora this skillagentic-box/memora	731	—	~813	Automated safety check: Pass	MIT	9 days ago
Marm InitLyellr88/marm-memory	419	—	~7.5k	Automated safety check: Notes	Apache-2.0	today
remindb Read Pathradimsem/remindb	129	—	~2.7k	Automated safety check: Pass	MIT	2 mo ago
Rememberradimsem/remindb	129	—	~728	Automated safety check: Pass	MIT	2 mo ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	9 days ago
MemPalace Setup and OperationMemPalace/mempalace	59k	—	~2.2k	Automated safety check: Pass	MIT	yesterday

Similar skills

Marm Init
Lyellr88/marm-memory
Guided MARM MCP setup. An agent skill from Lyellr88/marm-memory.
419 GitHub stars~7.5k tokensUpdated today
Agent WorkflowsAuto-check: notes
remindb Read Path
radimsem/remindb
Covers the read-side tools of the remindb MCP server, a SQLite-backed agent memory, for orienting, searching, resyncing and tracing relations.
129 GitHub stars~2.7k tokensUpdated 2 mo ago
Agent WorkflowsAuto-check passed
Remember
radimsem/remindb
Front door for long-term memory backed by a remindb MCP server.
129 GitHub stars~728 tokensUpdated 2 mo ago
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
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.
59k GitHub stars~2.2k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
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.
29k GitHub stars~1k tokensUpdated yesterday
Agent WorkflowsAuto-check: notes

Works with

Questions about Memora

What does Memora do?

A skill your agent uses when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful. Memora is an agent skill from agentic-box/memora. Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

When should I use Memora?

Memora fits situations like: working with persistent memory across sessions; storing/retrieving knowledge; managing TODOs/issues; context from previous sessions would be helpful.

How do I install Memora in Claude Code?

Run `npx skills add agentic-box/memora --skill memora -a claude-code`. Or copy the skill folder (claude-plugin/skills/memora in agentic-box/memora) into .claude/skills/memora in your project. Claude Code loads it when a task matches its description.

How do I install Memora in Codex?

Run `npx skills add agentic-box/memora --skill memora -a codex`. Or copy the skill folder (claude-plugin/skills/memora in agentic-box/memora) into .agents/skills/memora in your project. Codex loads it when a task matches its description.

Can I use Memora 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 agentic-box/memora --skill memora -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memora, .gemini/skills/memora, .github/skills/memora and .opencode/skills/memora in your project.

What does Memora need to run?

SKILL.md names no scripts, command-line tools or credentials: Memora is instructions for the agent only.

Does Memora access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memora 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 Memora use?

Memora is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memora use?

About 813 tokens (SKILL.md is roughly 3.3k 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 Memora?

Skills that share tags, products or a category with Memora: Marm Init (Lyellr88/marm-memory, 419 stars), remindb Read Path (radimsem/remindb, 129 stars), Remember (radimsem/remindb, 129 stars) and MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memora?

agentic-box (a GitHub organization) maintains it in agentic-box/memora, which has 731 GitHub stars. The repository was last updated on September 28, 2026.

Source: agentic-box/memora on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Memora

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Memora - Persistent Semantic Memory

When to Use

Core Tools

Creating Memories

Searching

Organizing

Maintenance

Visualization

Tag Conventions

Best Practices

Auto-Capture

Files

Compare with similar skills

Similar skills

Marm Init

remindb Read Path

Remember

MCP Server Builder

MemPalace Setup and Operation

agentmemory Setup and Diagnostics

Related

Questions about Memora