Agentmemory Forget
rohitg00/agentmemory
Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes.
Deletes Mem0 memories found by search query or memory ID, listing the matches and requiring explicit confirmation before anything is removed.
Install Mem0 Forget
$ npx skills add mem0ai/mem0 --skill forget -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mem0ai/mem0 forget --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/mem0ai/mem0.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .claude/skills/forget && 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 "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .claude/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forgetType 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 mem0ai/mem0 --skill forget -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mem0ai/mem0 forget --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mem0ai/mem0.git skills-src && mkdir -p .agents/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .agents/skills/forget && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .agents/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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 mem0ai/mem0 --skill forget -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mem0ai/mem0 forget --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mem0ai/mem0.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .cursor/skills/forget && 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 "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .cursor/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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/mem0ai/mem0.git --path integrations/pi-agent-plugin/skills/forget--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 mem0ai/mem0 --skill forget -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mem0ai/mem0 forget --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mem0ai/mem0.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .gemini/skills/forget && 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 "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .gemini/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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 mem0ai/mem0 forgetInstalls 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 mem0ai/mem0 --skill forget -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mem0ai/mem0.git skills-src && mkdir -p .github/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .github/skills/forget && 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 "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .github/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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 mem0ai/mem0 --skill forget -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mem0ai/mem0 forget --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mem0ai/mem0.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/integrations/pi-agent-plugin/skills/forget .opencode/skills/forget && 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 "forget" agent skill from https://github.com/mem0ai/mem0/tree/main/integrations/pi-agent-plugin/skills/forget into .opencode/skills/forget/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forget", 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
forget- GitHub stars
- 67k
- Token cost
- ~360 tokens
- SKILL.md length
- 153 words
- Files
- 1
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Deletes Mem0 memories found by search query or memory ID, listing the matches and requiring explicit confirmation before anything is removed.
- Works in 5 steps: Parse input → Find memories → Confirm → …
- Removing outdated or incorrect memories
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Deleting sensitive information that was stored in memory
What it does
The skill takes either a search query or a memory ID through /mem0-forget and asks what to forget if you give neither. For an ID, it looks the memory up and shows the start of its content with the created date. For a query, it searches and shows a numbered list of matches with their category and short ID.
Before deleting anything, it asks which memories to remove, accepting numbers, all or cancel, or a yes or no for a single ID, and it states that nothing is deleted without confirmation because deletion is destructive. Each confirmed memory is removed through the mem0_memory tool, and the agent reports how many were deleted along with any failures and their reasons.
When your agent uses it
- Removing outdated or incorrect memories
- Deleting sensitive information that was stored in memory
- Cleaning up memories left behind by an experiment
Example prompts
- “Forget everything we stored about the old staging database.”
- “Find the memories about my travel plans and let me pick which ones to delete.”
- “Clean up the memories from yesterday's experiment, and ask me before deleting anything.”
Requirements
- The mem0_memory tool, used here for search and delete
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit b7ad69a. 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
Mem0 Forget loads about 360 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 153 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 mem0ai/mem0 at commit b7ad69a, republished under its Apache-2.0 licence (© mem0ai). 153 words, ~360 tokens.
Download SKILL.mdSave it as
.claude/skills/forget/SKILL.md (or your agent's skills folder).- name
- forget
- description
- Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated information, incorrect memories, sensitive data, or cleaning up after experiments.
Forget
Delete specific memories from Mem0.
Execution
Step 1: Parse input
The user provides either:
- A search query:
/mem0-forget travel plans - A memory ID:
/mem0-forget <memory_id>
If no argument, ask: "What should I forget? Provide a search query or memory ID."
Step 2: Find memories
If memory ID provided (looks like a UUID or hex string):
- Use
mem0_memorytool withaction="search"and the ID as query, or look it up directly. - Show:
Found: "<memory content first 120 chars>" (created <date>)
If search query provided:
- Use
mem0_memorytool withaction="search",query=<user's query>. - Show numbered list:
Found <N> memories matching "<query>": 1. <content, 120 chars> [<category>] [ID: <short_id>] 2. ...
Step 3: Confirm
Ask: "Delete which memories? Enter numbers (e.g., 1,3,5), 'all', or 'cancel'."
For a single memory ID, ask: "Delete this memory? [y/N]"
Never delete without confirmation. This is destructive.
Step 4: Delete
For each confirmed memory, use mem0_memory tool with action="delete" and the memory ID.
Step 5: Report
Deleted <N> memories.If any deletions failed, report which ones and why.
© mem0ai, 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 integrations/pi-agent-plugin/skills/forget of mem0ai/mem0.
Open the folder on GitHubat commit b7ad69a
Compare with similar skills
Mem0 Forget 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 |
|---|---|---|---|---|---|---|
| Mem0 Forget this skillmem0ai/mem0 | 67k | — | ~360 | Automated safety check: Pass | Apache-2.0 | |
| Agentmemory Forgetrohitg00/agentmemory | 29k | — | ~612 | Automated safety check: Pass | Apache-2.0 | |
| Open Source Maintainernumman-ali/n-skills | 1.1k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Agentic Harness Design and ReviewNateBJones-Projects/OB1 | 4.7k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Agenticx Memory ArchitectDemonDamon/AgenticX | 294 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Hyperspacedb MemoryYARlabs/hyperspace-db | 161 | — | ~880 | Automated safety check: Pass | MIT |
Similar skills
Open Source Maintainer
numman-ali/n-skills
End-to-end GitHub repository maintenance for open-source projects.
Agentic Harness Design and Review
NateBJones-Projects/OB1
Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.
Agenticx Memory Architect
DemonDamon/AgenticX
Guide for setting up and using the AgenticX memory system including Mem0 integration, long-term memory, context management, and memory-enhanced agents.
Hyperspacedb Memory
YARlabs/hyperspace-db
Zero-overhead cognitive long-term and episodic memory for AI agents (Mem0 drop-in and mcp-hyperspace-memory).
Forget Personal Information
win4r/MuseAI-Skills
Removes a personal fact or past event from Muse's memory and from reminders, summaries and scheduled work that could bring it back, after you confirm a plan.
More from mem0ai/mem0
All 26 skills in this repoMem0 Platform SDK
mem0ai/mem0
Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.
Mem0 CLI Memory Commands
mem0ai/mem0
Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.
Mem0 Provider for Vercel AI SDK
mem0ai/mem0
Adds persistent memory to Vercel AI SDK apps with the Mem0 provider, using a wrapped model or standalone retrieve and store utilities.
Mem0 Memory Deletion
mem0ai/mem0
Finds and deletes specific mem0 memories by search query or ID, always asking for confirmation first, and can undo the most recent memories added this session.
Mem0 Remember Command
mem0ai/mem0
Saves a fact, decision or preference the user states into mem0 as written, labeled with a memory type such as decision, convention or user_preference.
Mem0 Memory Scope
mem0ai/mem0
Shows or changes the default Mem0 memory scope, project, session or global, which decides where memories are saved and searched.
Related
Works with
Categories
Questions about Mem0 Forget
What does Mem0 Forget do?
Deletes Mem0 memories found by search query or memory ID, listing the matches and requiring explicit confirmation before anything is removed. The skill takes either a search query or a memory ID through /mem0-forget and asks what to forget if you give neither. For an ID, it looks the memory up and shows the start of its content with the created date.
When should I use Mem0 Forget?
Mem0 Forget fits situations like: removing outdated or incorrect memories; deleting sensitive information that was stored in memory; cleaning up memories left behind by an experiment.
How do I install Mem0 Forget in Claude Code?
Run `npx skills add mem0ai/mem0 --skill forget -a claude-code`. Or copy the skill folder (integrations/pi-agent-plugin/skills/forget in mem0ai/mem0) into .claude/skills/forget in your project. Claude Code loads it when a task matches its description.
How do I install Mem0 Forget in Codex?
Run `npx skills add mem0ai/mem0 --skill forget -a codex`. Or copy the skill folder (integrations/pi-agent-plugin/skills/forget in mem0ai/mem0) into .agents/skills/forget in your project. Codex loads it when a task matches its description.
Can I use Mem0 Forget 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 mem0ai/mem0 --skill forget -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forget, .gemini/skills/forget, .github/skills/forget and .opencode/skills/forget in your project.
What does Mem0 Forget need to run?
SKILL.md names no scripts, command-line tools or credentials: Mem0 Forget is instructions for the agent only. Our summary lists: The mem0_memory tool, used here for search and delete.
Does Mem0 Forget 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 Mem0 Forget 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 Mem0 Forget use?
Mem0 Forget is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Mem0 Forget use?
About 360 tokens (SKILL.md is roughly 1.4k 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 Mem0 Forget?
Skills that share tags, products or a category with Mem0 Forget: Agentmemory Forget (rohitg00/agentmemory, 29k stars), Open Source Maintainer (numman-ali/n-skills, 1.1k stars), Agentic Harness Design and Review (NateBJones-Projects/OB1, 4.7k stars) and Agenticx Memory Architect (DemonDamon/AgenticX, 294 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mem0 Forget?
mem0ai (a GitHub organization) maintains it in mem0ai/mem0, which has 66,788 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 7, 2026.
Source: mem0ai/mem0 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.