nemori-ai / nemori
A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memory frameworks for conversational tasks.
Why this job: says: episodic memory; topics: ai-memory, context-engineering
What it does
Nemori is a self-organising long-term memory substrate for agentic LLM workflows. It ingests multi-turn conversations, segments them into topic-consistent episodes, distils durable semantic knowledge, and exposes a unified search surface for downstream reasoning. The implementation combines insights from Event Segmentation Theory and Predictive Processing with production-ready concurrency, caching, and pluggable storage.
Get started
pip install -e .- Maintenance
- Inactive
- Last commit 7 months ago
- Stars
- 221
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 5 merged
- 6 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| nossa-y / activity-frames | 531 | 2 months ago | MIT | No downloads |
| plastic-labs / honcho | 8,078 | yesterday | AGPL-3.0 | No downloads |
| memoket / memoket-kite | 233 | 8 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- ai-agents
- ai-memory
- context-engineering
- episodic-memory
- locomo
- memory-system
Project record
- JobAgent memory
- StatusListed
- Commits79
- Forks23
- Watching2
- Stars in 28 days+8
- CreatedJun 30, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026