WonderSearch lets Claude Code, Codex and Cursor share one brain—no vector DB needed
Scobleizer · x · 2026-11-03
Developer daleverett unveiled WonderDrive/WonderSearch, a YC-backed serverless semantic search that gives every coding agent (Claude Code, Codex, Cursor) a shared drive: what one agent learns, all agents know; if one deletes 48,120 files, you just hit undo. It uses sparse retrieval instead of vector databases or embeddings, claiming to match OpenAI's best embedding model without a single embedding. Pricing is per-query with storage at object-storage rates, and access is offered via MCP, API, CLI and SDK. Launching soon.
More from coding & agent
- Berkeley's GEPA-Curator filters noisy failure signals to boost agent prompt optimization — Berkeley · 2026-11-03
- Default AI agents to serverless, then let production data decide what moves — rseroter · 2026-11-03
- Skill-centric training beats task-centric for small web agents across 4 benchmarks — anmarasovic · 2026-11-03
- Your agentic coding trajectories are a treasure, argues new blog post — Bartaseth · 2026-11-03
- Dev argues agents make experimentation so cheap you should be 10x more scientific — zack_overflow · 2026-11-03
- Anthropic launches Message Threads in public beta, cutting long-conversation latency — ClaudeDevs · 2026-11-03