by mnemon-dev · Codex Skill · ★ 511
Mnemon English | 中文 LLM-supervised persistent memory for AI agents. LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window. Mnemon gives your agent persistent, cross-session memory — a four-graph knowledge store with intent-aware recall, importance decay, and automatic deduplication. Single binary, zero API keys, one setup command. Experimental beta: this repository also includes , a source-built beta for project-local host-agent lifecycle state.
| Stars | 511 |
| Forks | 65 |
| Language | Go |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 72.2890719343712/100 |
| Open Issues | 14 |
| Last Updated | 2026-08-23 |
| Created | 2026-02-20 |
| Platforms | claude-code, cli, go |
| Est. Tokens | ~19k |
These tools work well together with mnemon for enhanced workflows:
Explore other popular codex skill tools:
mnemon is LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.. It is categorized as a Codex Skill with 511 GitHub stars.
mnemon is primarily written in Go. It covers topics such as agent-framework, agent-memory, ai-agent.
You can find installation instructions and usage details in the mnemon GitHub repository at github.com/mnemon-dev/mnemon. The project has 511 stars and 65 forks, indicating an active community.
mnemon is released under the Apache-2.0 license, making it free to use and modify according to the license terms.