StackMap
Subscribe
Explore / linearmemory
jucelioalencar

linearmemory

Legible persistent agent memory: records observable execution events, consolidates only validated knowledge and explains every relation — MCP server on PostgreSQL 17 with a web explorer.

1 HTML MITupdated today
memoryknowledge-graphs
View on GitHubDispute this mapping →
Curator's take

Interesting for one design choice: memory is a chronological sequence of small observable events (reads, tool calls, decisions, errors, corrections) plus consolidated facts, decisions, procedures and outcomes — never the agent's raw reasoning transcript. Every graph edge carries direction, type, evidence, confidence and a human-readable explanation; humans browse the same store as a story, a relation map or a 3D graph. Postgres is authoritative, the graph projection is rebuildable, Docker Compose brings it up. NOT proven: one star, one author, no benchmark, no adopters yet. Watch it; don't bet on it.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside linearmemory. Ranked by curator confidence.

alternativealternativealternativehindsightshepherdagent-memorylinearmemory
pairs wellalternativebuilt withpick a node for the why · open it from the panel
Weekly digest
README.md1 min read
LinearMemory logo

LinearMemory

Agentic Knowledge Explorer

Durable, observable, and human-readable memory for AI agents.

Build and release Latest release License MCP PostgreSQL Docker TypeScript

Track LinearMemory on Trendshift

Known Vulnerabilities Snyk Vulnerabilities Known Vulnerabilities

Snyk Security Snyk Security ## LinearMemory in action

Explore agent histories, consolidated knowledge, execution replays, and cross-agent relationships in the interactive web interface.

LinearMemory Agentic Knowledge Explorer interactive demo

Make agent memory understandable

LinearMemory is a persistent memory system for AI agents. It records observable execution events, consolidates validated knowledge, and connects related memories without turning an agent's internal reasoning into an opaque transcript.

Agents access memory through a self-describing MCP server. Humans explore the same knowledge as a chronological story, a relationship map, or an interactive 3D graph.

Key features

  • Human-readable history — follow agent activity as a chronological sequence of small, observable events.
  • Durable knowledge — consolidate only validated facts, decisions, procedures, artifacts, and outcomes.
  • Multi-agent memory — keep each agent identifiable while connecting knowledge across agents and workspaces.
  • Explained relationships — every graph edge has a direction, relation type, evidence, confidence, and human-readable explanation.
  • Interactive 3D explorer — inspect timelines, replay executions, focus filters, hide event types, and navigate correlatio