By geojaz
Context retrieval using Graphiti knowledge graph, Context7 docs, and Serena symbol analysis
Configure Graphiti MCP backend and plugin prerequisites
Gather comprehensive context from all sources
Systematically populate the knowledge base using Serena's LSP-powered symbol analysis for accurate, comprehensive codebase understanding.
Deep exploration of the knowledge graph
List recent memories from the knowledge base
Deep exploration of Graphiti knowledge graph. Use when investigating connections, tracing decisions, or understanding architectural evolution.
Architectural analysis workflow using Serena symbols and Graphiti knowledge graph. Use when analyzing project structure, documenting architecture, or creating architectural memories from code.
When to query and save to Graphiti knowledge graph. PROACTIVELY query before starting work. Save important decisions and patterns.
Guidance for using Serena's LSP-powered symbol analysis. Use when exploring codebases, finding symbol definitions, tracing references, or when grep/text search would be imprecise.
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Unified context retrieval for Claude Code — orchestrates Graphiti knowledge graph, Context7 documentation, and Serena symbol analysis into a single context-gathering workflow.
claude plugins install graphiti-context-hub --marketplace geojaz
Or install from local path:
claude plugins install /path/to/graphiti-context-hub
Run the setup command to configure:
/context-hub-setup
This will:
http://localhost:8000)main)~/.config/claude/graphiti-context-hub.confRequired: Graphiti MCP Server
Install and run the Graphiti MCP server (see Graphiti documentation):
graphiti-server start --port 8000
Recommended: Serena (for /encode-repo-serena)
claude plugins install serena
Recommended: Context7 (for framework docs)
claude plugins install context7 --marketplace pleaseai/claude-code-plugins
Single config file: ~/.config/claude/graphiti-context-hub.conf
GRAPHITI_GROUP_ID=main
GRAPHITI_ENDPOINT=http://localhost:8000
SERENA_ENABLED=true
Created automatically by /context-hub-setup.
Group ID: Uses a single unified knowledge graph. All memories include repo context via automatic Repo: {name} tagging for flexible cross-repo querying.
| Command | Description |
|---|---|
/context_gather <task> | Gather context from Graphiti, code, and docs |
/encode-repo-serena | Bootstrap repository into Graphiti using Serena |
| Command | Description |
|---|---|
/memory-search <query> | Search knowledge graph semantically |
/memory-list [count] | List recent episodes |
/memory-save | Save current context as episode |
/memory-explore <query> | Deep knowledge graph traversal |
| Command | Description |
|---|---|
/context-hub-setup | Configure and verify setup |
| Skill | Description |
|---|---|
using-graphiti-memory | When/how to query and save to Graphiti |
exploring-knowledge-graph | Deep graph traversal and relationship discovery |
using-serena-symbols | Symbol-level code analysis guidance |
serena-code-architecture | Architectural analysis with Graphiti integration |
This plugin automatically registers advisory hooks that encourage context-aware development:
| Hook | Trigger | Purpose |
|---|---|---|
| SessionStart | Every session | Check config, provide Graphiti context |
| PreToolUse (Edit/Write) | Before code changes | Remind to query Graphiti for prior decisions |
| PreToolUse (EnterPlanMode) | Before planning | Remind to gather context first |
| PreCompact | Before compaction | Remind to save unsaved context to Graphiti |
| SubagentStart | Before subagent | Remind to persist context before handoff |
| SubagentStop | After subagent | Remind to capture subagent findings |
All hooks are zero-token-cost (command type) — they add context reminders without consuming LLM tokens.
Hooks are conditional on configuration:
SERENA_ENABLED=true in configOrchestrates multiple sources:
All memories automatically include repository context:
Repo: my-project
Decision: Implemented user-level group_id
Rationale: Enables cross-repo pattern discovery
This enables both repo-specific and cross-repo queries.
npx claudepluginhub geojaz/graphiti-context-hub --plugin graphiti-context-hubMake your AI agent code with your project's architecture, rules, and decisions.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation