by TonyStef
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.
# Add to your Claude Code skills
git clone https://github.com/TonyStef/GrovGuides for using cli tools skills like Grov.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
Your team's AI agents are learning in silos.
The waste: Redundant exploration, duplicate token spend, knowledge that disappears when sessions end.
Grov captures what your team's AI learns and shares it automatically.
Dev A: "How does auth work in this codebase?"
↓
Claude investigates, figures it out
↓
Grov captures the reasoning + decisions
↓
Syncs to team dashboard
↓
Dev B: "Should we add password salting?"
↓
Claude already knows: "Based on verified team knowledge,
no - this codebase uses OAuth-only, no passwords stored"
↓
No exploration needed. Instant expert answer.
Measured impact: Tasks drop from 10+ minutes to 1-2 minutes when team context is available.
npm install -g grov # Install
grov init # Configure (one-time)
grov proxy # Start (keep running)
Then use Claude Code normally in another terminal. That's it.
grov setup # Interactive setup (Cursor, Zed, Codex)
grov init cursor # Direct setup for Cursor CLI
grov init antigravity # Direct setup for Antigravity
IDE integrations (Cursor, Zed, Antigravity) use native MCP - no proxy needed.
Important: Your
ANTHROPIC_API_KEYmust be set permanently in your shell profile, not just withexportin a terminal. See Troubleshooting for setup instructions.
For team sync:
grov login # Authenticate via GitHub
grov sync --enable --team ID # Enable sync for your team
Free for individuals and teams up to 3 developers.
Real reasoning, not just file lists:

Architectural decisions, patterns, and rationale - automatically extracted and synced to your team.
Every captured memory includes:
When a teammate asks a related question, Claude already knows:

No exploration. No re-investigation. Instant expert answers from team memory.
Claude receives verified context and skips the exploration phase entirely - no "let me investigate" or "I'll need to look at the codebase."
The core value: what one dev's AI learns, everyone's AI knows.
Grov monitors what Claude does (not what you ask) and corrects when it goes off-track.
# Test drift detection
grov drift-test "refactor the auth system" --goal "fix login bug"
Anthropic's prompt cache expires after 5 minutes of inactivity. Grov keeps it warm.
grov proxy --extended-cache
Opt-in only. By using --extended-cache, you consent to Grov making API requests on your behalf.
When your context window fills up, Grov automatically compacts while preserving what matters.
No manual /compact needed. No lost reasoning.
# Setup
grov init # Configure for Claude Code (proxy mode)
grov init cursor # Configure for Cursor CLI
grov init antigravity # Configure for Antigravity
grov setup # Interactive setup (Cursor, Zed, Codex)
# Proxy (CLI tools only)
grov proxy # Start the proxy
grov proxy-status # Show active sessions
# Memory & Sync
grov status # Show captured tasks
grov login # Login to cloud dashboard
grov sync # Sync memories to team dashboard
# Utilities
grov doctor # Diagnose setup issues
grov disable # Disable grov
grov uninstall # Remove all grov data and config
grov drift-test # Test drift detection
┌─────────────────────────────────────────────────────────────┐
│ Claude Code │
│ │ │
│ ▼ │
│ Grov Proxy (localhost:8080) │
│ │ │
│ ├──► Inject team memory from past sessions │
│ ├──► Forward to Anthropic API │
│ ├──► Monitor for drift, inject corrections │
│ ├──► Track context usage, auto-compact if needed │
│ └──► Capture reasoning when task completes │
│ │ │
│ ▼ │
│ Team Dashboard (app.grov.dev) │
│ │ │
│ ▼ │
│ Available to entire team │
└─────────────────────────────────────────────────────────────┘
Local by default: Memories stay on your machine in ~/.grov/memory.db (SQLite) unless you enable team sync.
Browse, search, and manage your team's AI knowledge at app.grov.dev.
# Required for memory sync and drift detection
export ANTHROPIC_API_KEY=sk-ant-...
# Optional
export GROV_DRIFT_MODEL=claude-sonnet-4-20250514 # Override model
export PROXY_HOST=127.0.0.1 # Proxy host
export PROXY_PORT=8080 # Proxy port
Without an API key, Grov uses basic extraction and memories will not sync.
Run grov doctor to diagnose:
grov doctor
This checks your proxy, API key, login, sync status, and local database.
Using export ANTHROPIC_API_KEY=... directly in terminal only works in THAT terminal session. When you open a new terminal, the key is gone.
Fix: Add the key to your shell profile so it persists:
# For zsh (macOS default):
echo 'export ANTHROPIC_API_KEY=sk-ant-...' >> ~/.zshrc
source ~/.zshrc
# For bash:
echo 'export ANTHROPIC_API_KEY=sk-ant-...' >> ~/.bashrc
source ~/.bashrc
Then run grov doctor to verify:
✓ ANTHROPIC_API_KEY: Set
Get your API key at: https://console.anthropic.com/settings/keys
| Tool | Type | Proxy Required | |------|------|----------------| | Claude Code | CLI | Yes | | Cursor | IDE | No (native MCP) | | Cursor CLI | CLI | No | | Zed | IDE | No (native MCP) | | Antigravity | IDE | No (native MCP) | | Codex | CLI | Yes |
Coming soon: VS Code, Gemini CLI