# OpenLore

Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: medium
- Recommended workflows: Coding agent workflow, Memory or RAG workflow
- Permission surface: shell/files, memory, external services
- Agent JSON: https://www.openagent.bot/memory-systems/openlore.agent.json

## Summary
OpenLore is an open-source memory layer for AI coding agents. It turns codebases into queryable knowledge graphs with static analysis, living specs, drift detection, and MCP tools so agents can recover architectural context instead of re-discovering it every session.


## Guide
OpenLore provides persistent architectural memory for AI coding agents.

### What it is
It turns a codebase into a queryable knowledge graph and exposes context through MCP tools.

### Why it matters
Coding agents need durable architecture context to avoid re-learning the same repository every session.

### How it works
Start by indexing a repository, inspect the generated knowledge graph and specs, then connect the memory surface to an agent workflow.


### FAQ
- Is OpenLore open source?
  - Yes. The GitHub repository is listed under the MIT license.
- What kind of memory does OpenLore provide?
  - It focuses on architectural and codebase memory for coding agents, including queryable code relationships and MCP tools.
## What It Does
It turns a codebase into a queryable knowledge graph and exposes context through MCP tools.

## How To Evaluate
Start by indexing a repository, inspect the generated knowledge graph and specs, then connect the memory surface to an agent workflow.

## Why It Matters
Coding agents lose time and quality when they lack project memory. OpenLore focuses on durable architectural memory, not just chat history or vector search.


## Best For
- Teams using coding agents on large or long-lived repositories
- Developers who want graph-backed project memory and architecture context
- Agent builders exposing codebase knowledge through MCP tools

## Not For
- Small scripts where repository orientation is trivial
- Teams that only need document RAG rather than codebase structure

## What It Actually Does
- Architecture memory: OpenLore focuses on persistent architectural context for coding agents.
  - Why it matters: Architecture decisions and code relationships are often the context agents need most.
- Queryable codebase graph: The project describes codebases as queryable knowledge graphs with static analysis.
  - Why it matters: Graph structure can expose relationships that flat notes or chat summaries miss.
- MCP tool surface: OpenLore includes graph-native MCP tools for agent access.
  - Why it matters: MCP makes codebase memory easier to connect to multiple agent hosts.

## Typical Use Cases
- Repository orientation: Help agents understand architecture and code relationships before editing.
- Living specs: Use living specs and drift detection to keep project memory aligned with code.
- MCP codebase context: Expose structured repository context to agent environments through MCP.

## How It Compares
- When to choose OpenLore: Compare it with nearby memory systems by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Coding agent workflow: strong. OpenLore has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Memory or RAG workflow: strong. OpenLore has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Connector or protocol layer: partial. OpenLore has at least one signal for connector or protocol layer, but should be checked against a real task before adoption. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Evaluation and observability: partial. OpenLore has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Browser automation: weak. OpenLore is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Local or private AI stack: weak. OpenLore is not primarily positioned for local or private ai stack in the current metadata. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.

## Evidence
- verified: OpenLore is listed as open source. Source: License metadata: MIT
- verified: OpenLore has a recorded GitHub repository: clay-good/OpenLore. Source: Resource facts and GitHub source link.
- inferred: OpenLore supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: OpenLore is tagged with memory, context retrieval, state, mcp capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/clay-good/OpenLore
- Open Homepage: https://www.npmjs.com/package/openlore

## Facts
- Category: memory-systems
- Resource type: memory_system
- Open source: yes
- License: MIT
- Last verified: 2026-06-10
- GitHub repo: clay-good/OpenLore
- GitHub stars: 163

## Capabilities
- memory
- context-retrieval
- state
- mcp

## Structured Use Case Tags
- personal-memory

## Getting Started
- Open the GitHub repository: https://github.com/clay-good/OpenLore
- Open the npm package: https://www.npmjs.com/package/openlore

## Links
- GitHub: https://github.com/clay-good/OpenLore
- Homepage: https://www.npmjs.com/package/openlore

## Structured Outputs
- JSON: https://www.openagent.bot/memory-systems/openlore.json
- Markdown: https://www.openagent.bot/memory-systems/openlore.md
- Agent JSON: https://www.openagent.bot/memory-systems/openlore.agent.json
- Canonical: https://www.openagent.bot/memory-systems/openlore