dense-mem
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and Neo4j.
- Ask Claude to store and retrieve project decisions with full evidence links and timestamps.
- Generate conflict reports when contradictory technical claims are detected across team knowledge.
- Find related past incidents by searching semantically similar situations in your memory database.
Enables AI agents to maintain persistent, verifiable memory across sessions with built-in conflict detection and evidence tracking—critical for compliance-heavy domains and reducing hallucination risk in production systems.
Engineering teams building stateful AI agents requiring auditable decision trails and consistency across multiple agent instances.
https://github.com/markhuangai/dense-mem
By markhuangai
How to Get It
claude plugins install markhuangai/dense-mem
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Study reveals why smell memories are stronger than other sense memories — Hacker News · 9 pts
- Show HN: Ate – Portable dense memory for AI agents (.mv2 format) — Hacker News · 1 pts
2 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 29 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 29 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.