mnemon-dev/mnemon
#713 of 803 by Stars among GitHub repos
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.
About
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 mnemon-harness, a source-built beta for project-local host-agent lifecycle state. It is separate from the stable mnemon CLI, not production-ready, and may make breaking changes at any time. See…
Excerpted from github.com/mnemon-dev/mnemon
Latest metrics
| Stars | 572 | 2026-09-12 |
|---|---|---|
| Forks | 68 | 2026-09-12 |
| Commits | 1.4k | 2026-09-12 |
| Releases | 27 | 2026-09-12 |
| Watchers | 2 | 2026-09-12 |
| Open issues | 7 | 2026-09-12 |
| Open PRs | 4 | 2026-09-12 |