“agent memory”

Compartment

MaxFreedomPollard

Durable agentic memory, encrypted at rest.

Zettelkasten-based agent memory system with bidirectional links

Persistent memory for AI agents.

Agentic memory manager.

Local-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid retrieval.

Coding agent memory — one local MCP server for every project.

Markdown knowledge base as agent memory.

Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting.

ZeroDB agent-memory MCP — 18 tools: memory + write-back to Slack, Gmail, Calendar, GitHub.

Private Agent memory and governed shared knowledge.

Decentralized agent memory for the Lightning economy.

Persistent memory infrastructure for AI agents.

Two-layer memory for AI agents with an immune system.

Local code graph and solution memory for coding agents via CLI and MCP.

Persistent memory, coordination, and learning for AI agents.

Independent, reproducible benchmark harness for agent-memory backends.

Persistent memory for AI agents — 55 MCP tools, spreading activation recall.

Self-hosted agent memory: redaction before write, append-only audit, local embeddings.

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

Graph + vector memory for agents: recall, ingest, search, distill.

18 tools: agent memory, API drift detection, and HMAC-signed trust receipts

Persistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.

Anti-poisoning memory for agents: provenance, conflicts, quarantine gate.

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.