by adoresever · Codex Skill · ★ 421
graph-memory Knowledge Graph Context Engine for OpenClaw By adoresever · MIT License Installation · How it works · Configuration · 中文文档 What it does When conversations grow long, agents lose track of what happened. graph-memory solves three problems at once: Context explosion — 174 messages eat 95K tokens. graph-memory compresses to 24K by replacing raw history with structured knowledge graph nodes Cross-session amnesia — Yesterday's bugs, solved problems, all gone in a new session.
| Stars | 421 |
| Forks | 60 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 60.516/100 |
| Open Issues | 40 |
| Last Updated | 2026-04-07 |
| Created | 2026-03-10 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~76k |
These tools work well together with graph-memory for enhanced workflows:
Explore other popular codex skill tools:
graph-memory is Openclaw记忆插件Knowledge Graph + Memory;Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse. It is categorized as a Codex Skill with 421 GitHub stars.
graph-memory is primarily written in TypeScript. It covers topics such as agent, claude-code, codex.
You can find installation instructions and usage details in the graph-memory GitHub repository at github.com/adoresever/graph-memory. The project has 421 stars and 60 forks, indicating an active community.
graph-memory is released under the MIT license, making it free to use and modify according to the license terms.