No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by kevin-hs-sohn · Codex Skill · ★ 159
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hipocampus safe to install? View the security audit →
hipocampus Drop-in memory harness for AI agents. Zero infrastructure — just files. 3-tier memory architecture with a 5-level compaction tree, auto-loaded ROOT.md topic index, and optional hybrid search via qmd. One command to set up, works immediately with Claude Code, OpenCode, and OpenClaw bots. Install As a Claude Code Plugin Then run for full setup (directories, templates, search, hooks). Standalone (npm) This creates the full memory structure in your project: It also:
| Stars | 159 |
| Forks | 9 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.8938226411299/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-08 |
| Created | 2026-03-15 |
| Platforms | claude-code, node |
| Est. Tokens | ~24k |
These tools work well together with hipocampus for enhanced workflows:
Looking for a hipocampus alternative? If you're comparing hipocampus with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo
The memory + security kernel for AI agents. Strata: a signed append-only log, receipts on every write, exact-h
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular codex skill tools:
hipocampus is Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.. It is categorized as a Codex Skill with 159 GitHub stars.
hipocampus is primarily written in JavaScript. It covers topics such as agent-memory, ai-agent, ai-memory.
You can find installation instructions and usage details in the hipocampus GitHub repository at github.com/kevin-hs-sohn/hipocampus. The project has 159 stars and 9 forks, indicating an active community.
hipocampus is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hipocampus on Agent Skills Hub include Ori-Mnemos, lucid-memory, claude-mem-lite. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: