← Back to Skills Marketplace
gabe-luv-nancy

hippocampus

by Gabe-luv-Nancy · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
283
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install chronicle-monograph-memory
Description
Photon: AI-enhanced memory system that FIXES human memory flaws. NO DECAY - AI never forgets. Features: tool success tracking, project checkpoints, failure p...
README (SKILL.md)

Hippocampus

"AI is meant to FIX human memory flaws, why learn human decay?"

Philosophy

Traditional memory = Human memory imitation = DECAY = WRONG

Hippocampus FIXES human memory flaws:

  • Forgetting → Perfect recall
  • Fuzzy matching → Precise timestamps
  • Passive triggers → Proactive warnings
  • Importance decay → Never lose anything

Features

Feature Description
No Decay AI never forgets
Micro-Macro Workflows Short command → full workflow
Proactive Triggers Automatically loads relevant memory when keywords appear
Checkpoints Know exactly where project left off
Success Tracking Remember what works / fails
Failure Warning Proactive pattern detection
Knowledge Graph Networked memory

Setup (REQUIRED!)

After installing, run initialization:

cd /path/to/hippocampus
python3 scripts/memory.py init

Then verify:

python3 scripts/memory.py status

Commands

Command Description
/hippo init Initialize DB and directories
/hippo status View memory status
/hippo save Save current context
/hippo recall \x3Ckeyword> Precise recall
/hippo checkpoint Save project state
/hippo warn Check failure patterns
/hippo graph View knowledge graph
/hippo learn-workflow Register a micro→macro workflow
/hippo workflows List all registered workflows
/hippo forget-workflow Remove a workflow
/hippo triggers List keyword triggers
/hippo add-trigger Add a proactive trigger
/hippo remove-trigger Remove a trigger
/hippo readingbetweenthelines 察言观色 status and config
/hippo readingbetweenthelines-stat Show current word counts
/hippo readingbetweenthelines-clear Reset word counts
/hippo add-instant Add instant trigger
/hippo remove-instant Remove instant trigger
/hippo add-threshold Add threshold trigger
/hippo remove-threshold Remove threshold trigger
/hippo config Show / reload config
/hippo analyze Analyze all memory

Micro-Macro Workflows

Teach hippocampus your shortcuts:

/hippo learn-workflow deploy -> When I say "deploy", run: git push, then run tests, then notify team via slack
/hippo learn-workflow send report -> When I say "send report", compile weekly data, format as markdown, send via email

When you later say "deploy" or "send report", hippocampus will retrieve the full workflow automatically.

List all registered workflows:

/hippo workflows

Proactive Keyword Triggers

Configure hippocampus to automatically load relevant memories when you mention certain topics:

/hippo add-trigger database -> database-architecture
/hippo add-trigger api -> api-design

Now when your message contains "database" or "api", hippocampus loads the associated memory before answering — no need to manually recall.

List active triggers:

/hippo triggers

Configure triggers manually in USER_CONFIG.md:

PROACTIVE_KEYWORDS = database->database-architecture,api->api-design

察言观色 — ReadingBetweenTheLines

Proactive memory loading based on sustained conversation patterns. When you discuss a topic repeatedly, hippocampus automatically loads relevant memories.

Two trigger types:

Instant: fires immediately when a high-signal keyword appears (error, deploy, database...) Threshold: fires only after a word appears N times within a sliding window (project→5, api→4, config→4...)

Commands:

/hippo readingbetweenthelines         Show status and config
/hippo readingbetweenthelines-stat    Show current word counts in window
/hippo readingbetweenthelines-clear   Reset word counts
/hippo add-instant error -> error-patterns     Add instant trigger
/hippo add-threshold project -> 5              Add threshold trigger

How it works: Heartbeat runs every N minutes (default 1). Analyzes recent user messages, removes stop words, counts meaningful words. If a trigger keyword meets its condition, the associated memory is loaded before answering.

Configuration (USER_CONFIG.md):

READINGBETWEENTHELINES_ENABLED = true
INSTANT_TRIGGERS = error->error-patterns,database->database-architecture
THRESHOLD_TRIGGERS = project->5,api->4,config->4
TRIGGER_COOLDOWN = 5   # minutes before reloading same memory

Two Memory Types

Chronicle — Temporal memory for everyday interactions

  • Auto-saves session content, indexed by time

Monograph — Important topics with rich metadata

  • Stores significant decisions, workflows, patterns
  • Created via /hippo checkpoint or /hippo recall saves

Proactive Recall (How It Works)

When PROACTIVE_TRIGGERS_ENABLED = true in USER_CONFIG.md:

  1. Before each response, hippocampus scans your message
  2. If a trigger keyword is found, it loads the associated memory file
  3. The loaded memory is prepended to context for this response
  4. You get relevant context without asking for it

This is configured via PROACTIVE_KEYWORDS in USER_CONFIG.md.

Version

1.0.3

Usage Guidance
Before installing or enabling this skill, consider these checks: 1) Inspect scripts/memory.py fully (search specifically for os.system, subprocess, eval, exec, or other code that runs shell commands). If micro→macro workflows are implemented as executable actions, they can run arbitrary commands. 2) Run init and status in an isolated test environment (not your primary workspace) to see what files/directories are created and what network or system actions occur. 3) Review and restrict USER_CONFIG.md FILE_SCAN_PATHS to directories you are comfortable indexing (do not point to / or your home directory) and set FILE_EXCLUDE_PATHS to protect sensitive folders. 4) Do not add the recommended cron jobs until you confirm the script's behavior; if you add them, point them to an isolated environment. 5) If you want stricter safety, disable AUTO_SAVE, PROACTIVE_TRIGGERS, and READINGBETWEENTHELINES before running. 6) If you cannot audit the code or find evidence that workflows execute shell commands, treat the skill as potentially executing actions and limit its filesystem scope and scheduling. If you want, provide the remainder of scripts/memory.py (truncated here) and I can check for command execution and network calls specifically.
Capability Analysis
Type: OpenClaw Skill Name: chronicle-monograph-memory Version: 1.0.3 The Hippocampus skill is a sophisticated memory management system for OpenClaw agents, implementing temporal (Chronicle) and topical (Monograph) storage using SQLite and Markdown. While it requests 'exec' permissions and facilitates the creation of cron jobs for automated tasks (auto-saving and analysis in scripts/memory.py), these behaviors are explicitly documented and directly support the stated purpose of the skill. The 'ReadingBetweenTheLines' and 'Micro-Macro Workflow' features involve automated context injection and instruction expansion based on user-defined triggers, but no evidence of malicious intent, data exfiltration, or unauthorized persistence was found.
Capability Assessment
Purpose & Capability
Name and description match the included files: a local memory system implemented in scripts/memory.py. Asking users to run python3 scripts/memory.py init/status is consistent with the purpose. However, skill.yaml grants 'exec' permission and README examples show micro→macro workflows that mention running system commands (git push, tests, notify via Slack) and cron entries that execute the script — these increase capability beyond passive memory storage and should be expected only if the skill legitimately needs to execute user workflows.
Instruction Scope
The SKILL.md and README instruct the agent/user to initialize and run the included Python script and to configure cron jobs that will run it periodically. The USER_CONFIG and code indicate the skill can scan filesystem paths (FILE_SCAN_PATHS default ./workspace, and that list is user-editable) and auto-save session contents. Proactive triggers/heartbeat will read recent user messages to decide which memories to load. These behaviors are coherent with a memory system but do grant the skill access to local files and ongoing message streams; if the skill executes workflows or shell commands (unclear from truncated code), it could run arbitrary actions. The instructions also allow reloading config automatically after edits — giving the skill runtime control over behavior.
Install Mechanism
There is no install spec — the package is instruction + script based and asks the user to run the Python script manually. That is lower risk than downloading and running remote binaries. The user must run init/status and optionally add cron jobs themselves; nothing is remotely fetched during install.
Credentials
No environment variables or external credentials are requested by the metadata. That is proportionate. However, the skill.yaml requests generic permissions (read, write, exec) and the code is capable of scanning configured filesystem paths and storing indexed memories. The combination of exec permission + examples that run system commands means the skill may be able to execute actions outside mere data storage if the code implements that; verify whether workflows are purely stored metadata or are executed.
Persistence & Privilege
always:false (no forced permanent inclusion). The README encourages adding cron jobs (persistence scheduled by user). That is user-driven rather than automatic. The skill does not declare it will modify other skills or system-wide agent settings, but it does ask to run periodic jobs and has exec permission — review cron setup and make sure it's only added intentionally and pointed to an isolated path.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install chronicle-monograph-memory
  3. After installation, invoke the skill by name or use /chronicle-monograph-memory
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Introduced new "chronicle" and "monograph" memory files in the assets/hippocampus directory. - Added initial SQLite database for temporal memory storage (db.sqlite). - Implemented daily and time-based memory index files for improved recall and organization. - Included sample monograph and daily memory markdown files to support richer metadata and structured memories. - Added updated ROADMAP documentation (ROADMAP_v3.1.md).
v1.0.1
Major update: Photon release radically improves memory accuracy and usability. - Introduces AI-enhanced "Photon" memory: no decay, perfect recall, proactive warnings. - Tracks tool/command successes, project checkpoints, and failure patterns. - Adds knowledge graph feature for networked topics/goals. - New commands: checkpoint, warn, graph, and precise recall. - Cron job setup now auto-creates all needed jobs for seamless automation. - Streamlined philosophy: AI fixes human memory flaws, never forgets. Cuz, you know, AI is better
v1.0.0
Initial release of the chronicl skill. - Introduces a brain-inspired memory system with dual storage: Chronicle (temporal notes in SQLite+Markdown) and Monograph (key topics with structured metadata). - Proactive memory assistant: detects when to save, recall, or search memories without explicit commands. - Offers to create example files and demonstrate formats on first use. - Includes setup commands for initializing, syncing, searching, querying, and configuring memory. - Supports easy setup of cron jobs and session hooks through guided confirmation for automation. - All features are user-configurable via USER_CONFIG.md.
Metadata
Slug chronicle-monograph-memory
Version 1.0.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is hippocampus?

Photon: AI-enhanced memory system that FIXES human memory flaws. NO DECAY - AI never forgets. Features: tool success tracking, project checkpoints, failure p... It is an AI Agent Skill for Claude Code / OpenClaw, with 283 downloads so far.

How do I install hippocampus?

Run "/install chronicle-monograph-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is hippocampus free?

Yes, hippocampus is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does hippocampus support?

hippocampus is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created hippocampus?

It is built and maintained by Gabe-luv-Nancy (@gabe-luv-nancy); the current version is v1.0.3.

💬 Comments