by NanoFlow-io · Codex Skill · ★ 123
Engram engram (n.) — the physical/biochemical trace a memory leaves behind. The thing that makes "remembering" actually possible. Engram is the hybrid long-term memory plugin for OpenClaw agents. It gives your agent a brain that doesn't forget between sessions — backed by SQLite + FTS5 for exact, structured recall and LanceDB for fuzzy semantic search over embeddings. Looking for the right Engram? This is the OpenClaw memory plugin (, npm CLI ). If you came here looking for the code-context compression tool for Cursor/Claude Code/Cline (npm ), that's a different project: NickCirv/engram.
| Stars | 123 |
| Forks | 1 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.4474916853271/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-08 |
| Created | 2026-05-20 |
| Platforms | node |
| Est. Tokens | ~3k |
These tools work well together with engram for enhanced workflows:
Explore other popular codex skill tools:
engram is 🧠 Hybrid long-term memory plugin for OpenClaw agents — SQLite+FTS5 for structured facts, LanceDB for semantic recall. It is categorized as a Codex Skill with 123 GitHub stars.
engram is primarily written in TypeScript. It covers topics such as ai-agents, embeddings, lancedb.
You can find installation instructions and usage details in the engram GitHub repository at github.com/NanoFlow-io/engram. The project has 123 stars and 1 forks, indicating an active community.
engram is released under the MIT license, making it free to use and modify according to the license terms.