By usecortex
Secure HydraDB automation for Claude Code with workspace sync, prompt recall, and conversation capture.
Retrieve relevant HydraDB context when answering would benefit from prior conversations, workspace docs, project decisions, team conventions, or user preferences not fully present in the current chat. Use proactively for substantive project questions or when continuity may matter.
Background guidance for sessions where HydraDB context is injected. Use when <hydradb-context> blocks appear or when the user asks how the HydraDB plugin behaves.
Show the most recent auto-recall payload captured by the HydraDB plugin. Use when debugging whether UserPromptSubmit recall ran, what HydraDB returned, or what was injected into context.
Deprecated hidden alias for manual HydraDB search.
Deprecated hidden alias for syncing workspace context into HydraDB.
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.
Secure HydraDB automation for Claude Code with markdown-first workspace sync, prompt-time recall, and configurable memory capture modes.
The plugin gives Claude Code persistent, cross-session memory powered by HydraDB. It hooks into the Claude Code lifecycle to automatically recall relevant context at prompt time, sync workspace documentation into HydraDB, and capture conversation content as durable memories.
*.md, *.mdx, CLAUDE.md) into HydraDBgit clone https://github.com/usecortex/hydradb-claude-code.git
cd hydradb-claude-code
make bootstrap
The bootstrap script will:
npm installconfig.json from config.example.json (if it doesn't already exist)Then set your credentials:
export HYDRADB_API_KEY="your-api-key"
export HYDRADB_TENANT_ID="your-tenant-id"
Install the plugin in Claude Code:
/plugin marketplace add /path/to/hydradb-claude-code
/plugin install hydradb@hydradb
Or, once the repo is public:
/plugin marketplace add usecortex/hydradb-claude-code
/plugin install hydradb@hydradb
Reload Claude Code and run /hydradb:status to verify.
The plugin resolves configuration from multiple layers (later layers override earlier ones):
HYDRADB_PLUGIN_CONFIG environment variable${CLAUDE_PLUGIN_DATA}/config.json./.hydradb-plugin-data/config.json.hydradb-plugin.json.hydradb-plugin.local.json{
"apiBaseUrl": "https://api.hydradb.com",
"apiKey": "${HYDRADB_API_KEY}",
"tenantId": "${HYDRADB_TENANT_ID}",
"subTenantId": "",
"autoRecall": true,
"autoIngest": true,
"captureMode": "session-upsert",
"searchMode": "memory",
"ingestionMode": "memory"
}
| Field | Default | Description |
|---|---|---|
apiBaseUrl | https://api.hydradb.com | HydraDB API endpoint |
apiKey | — | HydraDB API key (use ${HYDRADB_API_KEY} to reference env var) |
tenantId | — | HydraDB tenant ID (use ${HYDRADB_TENANT_ID} to reference env var) |
subTenantId | — | Sub-tenant scope; set to "" for HydraDB's default sub-tenant |
userName | — | Display name attached to captured memories |
autoRecall | true | Automatically recall HydraDB context on each user prompt |
autoIngest | true | Automatically sync workspace docs on session start |
captureMode | session-upsert | turn, session-upsert, both, or off |
searchMode | memory | memory, knowledge, or both |
ingestionMode | memory | memory, knowledge, or auto |
recallMode | thinking | Recall strategy passed to HydraDB |
graphContext | true | Include graph entity paths and relations in recall |
maxContextChars | 7000 | Max characters injected into Claude's context per prompt |
maxMemoryResults | 6 | Max memory chunks returned per recall |
maxKnowledgeResults | 4 | Max knowledge chunks returned per recall |
requestTimeoutMs | 15000 | Timeout for HydraDB read requests |
writeTimeoutMs | 15000 | Timeout for HydraDB write requests |
maxFileSizeBytes | 52428800 | Max file size for workspace sync (50 MB) |
maxFilesPerSync | 25 | Max files synced per workspace sync run |
includeGlobs | ["CLAUDE.md", ".claude/**/*.md", "**/*.md", "**/*.mdx"] | File patterns to include in workspace sync |
excludeGlobs | (see config.example.json) | File patterns to exclude from workspace sync |
ignoreMarker | hydra-ignore | Marker string to skip capture/sync for specific files or prompts |
memoryCustomInstructions | (see config.example.json) | Instructions for memory extraction from conversations |
workspaceMemoryCustomInstructions | (see config.example.json) | Instructions for memory extraction from workspace docs |
debug | false | Enable JSONL debug logging |
npx claudepluginhub usecortex/hydradb-claude-code --plugin hydradbMulti-tiered memory and knowledge base with semantic search, auto-compaction, and built-in evaluation. Works across Claude Code, Copilot CLI, OpenCode, Cline, and Cursor.
Persistent cloud memory for Claude Code. Auto-loads memories on session start, auto-saves on stop, with on-demand store/recall skills.
Persistent memory for Claude Code. Capture work across sessions and recall relevant context.
The memory layer for agent teams. Deterministic retrieval, hard per-project isolation, zero LLM in the critical path.
The bridge between Claude's working memory and Basic Memory's durable knowledge graph — session briefings, pre-compaction checkpoints, and capture reflexes
Curated persistent memory for Claude Code. Write gate prevents bloat — only behavior-changing facts get saved. Tiered architecture: daily logs, structured registers, and auto-loaded working memory.