by kevin-hs-sohn · Codex Skill · ★ 159
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:
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.