Grov

Video Review

About

Grov is an open-source memory layer for AI coding agents that captures reasoning traces from developer sessions and shares them across your entire engineering team. When one developer's Claude Code figures out your authentication flow, payment integration, or deployment pipeline, Grov ensures every other developer's AI agent already knows it in their next session. The tool works as a local proxy that sits between your terminal and the LLM API, intercepting calls to capture context on task completion and injecting relevant memories into new sessions via hybrid semantic and keyword search. All data is stored locally in a SQLite database at ~/.grov/memory.db, with optional cloud sync through app.grov.dev for team collaboration. Grov's measurable impact is significant: token usage drops from 50,000+ tokens for manual codebase exploration down to 5,000-7,000 tokens per session when relevant memories exist, translating to up to 4x faster response times. Tasks that previously took over 10 minutes of redundant AI exploration complete in 1-2 minutes with team context available. Key technical features include anti-drift detection that scores AI agent alignment on a 1-10 scale and intervenes at escalating levels (nudge, correct, intervene, halt), extended prompt cache management that keeps Anthropic's cache warm beyond the standard 5-minute expiration for roughly $0.002 per keep-alive, and auto-compaction that summarizes conversations at 85% context capacity while preserving goals, decisions, and next steps. Grov supports Claude Code via proxy, plus native MCP integration for Cursor, Zed, and Antigravity. It is currently in public beta (v0.6.x) under the Apache 2.0 license, with the free tier supporting individuals and teams up to 3 developers. The tool is strongest for small to mid-size teams that rely heavily on AI coding agents and want to eliminate the 'context tax' of agents repeatedly re-analyzing unchanged code across sessions. However, teams with strict enterprise compliance requirements should evaluate the roadmap before committing, as enterprise features are still in development.

Key Features

• Automatic reasoning capture from AI coding sessions stored in local SQLite
• Team memory sync with shared dashboard at app.grov.dev
• Anti-drift detection scoring agent alignment 1-10 with escalating corrections
• Hybrid semantic + keyword search for relevant memory injection
• Extended prompt cache management keeping Anthropic cache warm beyond 5-min expiry
• Auto-compaction at 85% context capacity preserving goals and key decisions
• Intelligent memory evolution that updates existing memories instead of duplicating
• Multi-IDE support: Claude Code (proxy), Cursor, Zed, Antigravity (native MCP)

Use Cases

• 1Engineering teams eliminating redundant AI exploration of the same codebase patterns
• 2Onboarding new developers whose AI agents instantly have team architectural knowledge
• 3Reducing Claude Code token costs by up to 90% through shared memory injection
• 4Preventing AI drift from established project conventions across multiple developers
• 5Preserving institutional knowledge from AI sessions that would otherwise be lost
• 6Accelerating complex debugging tasks with prior resolution context from teammates