by syv-labs
ContextPool
MCPPersistent memory layer for AI coding agents — extracts engineering insights from past sessions and loads them automatically via MCP at session start.
ContextPool solves the blank-slate problem with AI coding agents. Every new Cursor, Claude Code, or Windsurf session starts from scratch — you re-debug the same bugs and re-explain decisions you already made. ContextPool scans past sessions, extracts actionable engineering insights using an LLM, and surfaces them automatically at session start via MCP. Local mode is free forever with raw transcripts staying on your machine. Cloud sync enables team-shared memory pools where insights from one developer's session are available to the whole team. Installs in 30 seconds with a single curl command.
Capabilities
Pros & Limitations
Editorial assessmentPros
- ✓Local mode free forever — no account needed
- ✓Installs in 30 seconds, single curl command
- ✓MCP-native — works with Cursor, Claude Code, Windsurf, and Kiro automatically
- ✓Privacy-first — raw transcripts never leave your machine
- ✓Team shared memory pool via cloud sync
Limitations
- ⚠Cloud sync required for team sharing (paid tier)
- ⚠Currently macOS, Linux, and Windows only
- ⚠Insight quality depends on LLM extraction accuracy
Technical Details
Similar agents
Commercial
Industries
Rating
Editorial score
Leave a review
Never displayed publicly.
Agent Stacks
See workflow stacks that feature ContextPool — curated and community-verified multi-agent setups.
Is this your tool?
Claim this listing to update your details and get a Verified badge.
Claim this listing →