Agent skill

Hippo Project Memory

by kitfunso in kitfunso/hippo-memory

Gives the agent a long-term project memory through the Hippo CLI: load context at session start, record lessons and errors, and recall them later.

MITAuto-check passedAgent Workflows

Install Hippo Project Memory

skills CLI
$ npx skills add kitfunso/hippo-memory --skill memory -a claude-code

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

GitHub CLI
$ gh skill install kitfunso/hippo-memory memory --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/kitfunso/hippo-memory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/extensions/claude-code-plugin/skills/memory .claude/skills/memory && 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/

Facts

Skill name
memory
GitHub stars
773
Token cost
~478 tokens
SKILL.md length
150 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Gives the agent a long-term project memory through the Hippo CLI: load context at session start, record lessons and errors, and recall them later.

  • Starting a session on a project that already has notes from earlier work
  • SKILL.md covers At session start (MANDATORY), When you learn something…, When you hit an error or… and After completing work…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • After finding the cause of a confusing error

What it does

This skill puts the Hippo memory CLI into the agent's routine so lessons carry across sessions. At the start of every session the agent loads relevant context with hippo context under a token budget, and during work it records non-obvious lessons with hippo remember and a tag. Errors are stored with an error flag that doubles a memory's half-life, since memories otherwise decay unless they are retrieved.

The remaining commands cover the rest of the loop. Outcome marks recalled memories good or bad after a task, recall with the why option digs through memory when the agent is stuck, decide stores an architectural decision that stays active until superseded, and invalidate retires memories about a tool you have migrated away from. After a long coding session, hippo learn with the git option scans recent commits for lessons and for replaced tools. Memories can be exported as JSON or Markdown, and hippo status checks their health.

When your agent uses it

  • Starting a session on a project that already has notes from earlier work
  • After finding the cause of a confusing error
  • Recording an architectural decision so it resurfaces when relevant
  • After switching libraries, so memories about the old one stop misleading

Example prompts

  • “Load the project memory before we start on the billing refactor.”
  • “Record that we chose Postgres over MongoDB and why.”
  • “Scan the last few commits for lessons and export the memories as Markdown.”

Requirements

  • The Hippo CLI (`hippo`) installed

What it can do on your machine

Read from SKILL.md and the folder at commit bfcbc29. 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 (its code samples are bash).

    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

Hippo Project Memory loads about 478 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 150 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~478

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 kitfunso/hippo-memory at commit bfcbc29, republished under its MIT licence (© kitfunso). 150 words, ~478 tokens.

Download SKILL.mdSave it as .claude/skills/memory/SKILL.md (or your agent's skills folder).
name
memory
description
Project memory powered by Hippo. Use when starting a session, after learning something, after hitting an error, or when the user mentions memory/remember/recall. Auto-invoked at session start.

Hippo Memory

Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. Memories decay over time unless retrieved. Errors stick longer. Sleep consolidates.

At session start (MANDATORY)

Before doing any work, load relevant context:

bash
hippo context --auto --budget 1500

Read the output. These are things the project has learned from past sessions.

When you learn something non-obvious

bash
hippo remember "<the lesson in 1-2 sentences>" --tag <category>

When you hit an error or unexpected failure

bash
hippo remember "<what failed, why, and how you fixed it>" --error

The --error flag doubles the half-life. Hard lessons don't fade quietly.

After completing work successfully

bash
hippo outcome --good

If the recalled memories were irrelevant:

bash
hippo outcome --bad

When stuck or hitting repeated errors

bash
hippo recall "<what's going wrong>" --budget 2000 --why

When making an architectural decision

bash
hippo decide "<decision>" --context "<why>"

Decisions get a recall boost so they surface when relevant, and stay active until superseded.

When migrating or replacing a tool

bash
hippo invalidate "<old tool>" --reason "migrated to <new tool>"

Or let hippo learn --git detect it automatically from migration commits.

After significant coding sessions

bash
hippo learn --git

This scans recent commits, auto-extracts lessons, and invalidates memories about replaced tools.

Export memories

bash
hippo export memories.json
hippo export --format markdown memories.md

Check memory health

bash
hippo status

© kitfunso, MIT. 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 extensions/claude-code-plugin/skills/memory of kitfunso/hippo-memory.

Open the folder on GitHubat commit bfcbc29

Compare with similar skills

Hippo Project 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.

Hippo Project Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hippo Project Memory this skillkitfunso/hippo-memory773—~478Automated safety check: PassMIT
Coding Agent Session Findercode-yeongyu/oh-my-openagent70k1 repos~2.8kAutomated safety check: PassCustom licence
Claude-Mem Cloud Syncthedotmack/claude-mem98k1 repos~1kAutomated safety check: NotesApache-2.0
Cognee CLI Memory Commandstopoteretes/cognee32k1 repos~2.2kAutomated safety check: NotesApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Claude-Mem Searchthedotmack/claude-mem98k1 repos~511Automated safety check: PassApache-2.0

Similar skills

  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub starsUsed in 1 repo~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude-Mem Cloud Sync

    thedotmack/claude-mem

    Checks claude-mem cloud sync status and guides you through connecting a cmem.ai Pro account without the sync token ever passing through the chat.

    98k GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes
  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub starsUsed in 1 repo~2.2k tokens
    Agent WorkflowsAuto-check: notes
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Claude-Mem Search

    thedotmack/claude-mem

    Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.

    98k GitHub starsUsed in 1 repo~511 tokens
    Agent WorkflowsAuto-check passed
  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

Categories

Questions about Hippo Project Memory

What does Hippo Project Memory do?

Gives the agent a long-term project memory through the Hippo CLI: load context at session start, record lessons and errors, and recall them later. This skill puts the Hippo memory CLI into the agent's routine so lessons carry across sessions. At the start of every session the agent loads relevant context with hippo context under a token budget, and during work it records non-obvious lessons with hippo remember and a tag.

When should I use Hippo Project Memory?

Hippo Project Memory fits situations like: starting a session on a project that already has notes from earlier work; after finding the cause of a confusing error; recording an architectural decision so it resurfaces when relevant; after switching libraries, so memories about the old one stop misleading.

How do I install Hippo Project Memory in Claude Code?

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

How do I install Hippo Project Memory in Codex?

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

Can I use Hippo Project 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 kitfunso/hippo-memory --skill 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/memory, .gemini/skills/memory, .github/skills/memory and .opencode/skills/memory in your project.

What does Hippo Project Memory need to run?

SKILL.md names no scripts, command-line tools or credentials: Hippo Project Memory is instructions for the agent only. Our summary lists: The Hippo CLI (`hippo`) installed.

Does Hippo Project Memory 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 Hippo Project 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 Hippo Project Memory use?

Hippo Project Memory 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 Hippo Project Memory use?

About 478 tokens (SKILL.md is roughly 1.9k 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 Hippo Project Memory?

Skills that share tags, products or a category with Hippo Project Memory: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Claude-Mem Cloud Sync (thedotmack/claude-mem, 98k stars), Cognee CLI Memory Commands (topoteretes/cognee, 32k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hippo Project Memory?

kitfunso (a GitHub user) maintains it in kitfunso/hippo-memory, which has 773 GitHub stars. The repository was last updated on October 7, 2026.

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