OpenLore
Active·★ 140·MIT·Updated 2026-05-29
★ Trending★ Code Assistant★ Workflow Automation
openlore provides persistent architectural memory for AI coding agents by turning codebases into queryable knowledge graphs featuring static analysis, living specs, automated drift detection, and graph-native MCP tools to eliminate context decay and drastically slash orientation token costs.
OpenLore turns any evolving codebase into a navigable knowledge graph backed by OpenSpec living specifications. It maintains persistent architectural context across AI agent sessions, reducing token consumption for orientation from 15,000-50,000 to about 1,000-3,000 tokens. The three-layer system includes static analysis, spec generation, and an MCP agent runtime with 45 tools.
#adr#agentic-workflows#ai-agents#ai-coding#call-graph#codebase-analysis#context-management#developer-tools
01
Features
01Persistent call graph with incremental updates via --watch-auto for live codebase awareness
02Spec drift detection in milliseconds comparing git changes against spec mappings
03Epistemic Lease mechanism to model and signal architectural context decay in long sessions
0445 MCP tools including orient(), graph traversal, semantic search, and drift awareness
05Multi-agent surface auto-install (Claude Code, Cursor, Cline, Continue) via openlore install
02
Compatibility
Node.js
Required
Verified via docs
TypeScript
Analyzed
Verified via docs
Python
Analyzed
Verified via docs
Go
Analyzed
Verified via docs
Rust
Analyzed
Verified via docs
Ruby
Analyzed
Verified via docs
03
Quick start
1
$ npm install -g openlore
2
$ cd /path/to/your-project
3
$ openlore analyze
4
$ openlore install
5
$ openlore mcp
04
Use cases
↳AI coding agents need to quickly understand codebase structure and maintain context across sessions without re-reading files
↳Detecting when code drifts from documented specifications to enforce architectural governance
↳Preventing architectural assumptions from decaying in long agent sessions, especially in monorepos or cross-repo workflows
05
Alternatives
Brave Search MCP★ 86.5k
Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
initrunner★ 38
Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
Related searches
Comments
Log in to leave a comment
No comments yet. Be the first!