Neo4j vs Neon

Benchmark of Five Managed Graph Databases

A reproducible benchmark comparing CognoDB Cloud, Neo4j AuraDB, Memgraph, FalkorDB and ArangoDB revealed major pitfalls in naive measurement: geographic placement of managed instances skewed raw latency numbers, server-reported execution time (via Bolt drivers) is required for fair engine-to-engine comparison, and CognoDB v0.9.11 exhibited a background-indexing behaviour that caused indexed lookups to return no results while an index was building, silently dropping relationship writes. Concurrency characteristics differed: cloud-hosted databases scaled with client concurrency due to network latency hiding server idle time, while local instances became CPU-bound and slowed. The author published the full harness and raw data on GitHub.

• Five graph databases were benchmarked: CognoDB Cloud, Neo4j AuraDB, Memgraph, FalkorDB and ArangoDB.
• Geographic placement of managed cloud instances (e.g., CognoDB in Google Cloud us-east4 and Neo4j AuraDB in Google's Singapore range) skewed raw wall-clock latency measurements.
• Using server-reported execution time via Bolt drivers (network excluded) was necessary to fairly compare engines in different regions.

Benchmarking Five Graph Databases on 256MB RAM

The author benchmarked five graph databases (CognoDB, Neo4j AuraDB Free, Memgraph, FalkorDB, and ArangoDB) under a tight resource cap (0.5 vCPU / 256MB RAM) using a social-graph SNAP dataset (~18.7k nodes, ~198k edges). Results showed a range of operational and performance issues: Memgraph repeatedly segfaulted at startup across versions and configurations; FalkorDB lost all data after an environment restart due to an incorrect bind mount path and ignored persistence flags; Neo4j AuraDB exhibited a near-constant ~220ms per-query latency floor suggesting a fixed request cost; CognoDB was fastest on most queries but had one query pattern where it performed worst. Full methodology and raw results are available in the linked GitHub repository.

• CognoDB Cloud's free tier provides a graph database instance with 0.5 vCPU and 256MB of RAM.
• The benchmark compared CognoDB, Neo4j AuraDB Free, Memgraph, FalkorDB, and ArangoDB using the same ~18.7k-node / ~198k-edge SNAP dataset and identical query patterns under a 0.5 vCPU / 256MB RAM cap.
• Memgraph crashed immediately on startup with a reproducible segfault across multiple versions and with various runtime/configuration changes.

Claimable Neon: Provisioned by agents, claimed by humans

Claimable Neon implements the anonymous registration method in auth.md, the open agent registration protocol authored by WorkOS, to give agents a way to provision a temporary Neon project without creating an account or collecting payment details.

Build an MCP server with Air Pipe and Postgres

A step-by-step technical guide showing how to build an MCP (model-calling protocol) server using Air Pipe and a Postgres database. The tutorial provides a schema (mcp_tenants, mcp_tokens, mcp_tasks), a single-file Air Pipe config exposing MCP tools (list_tasks, create_task), deployment instructions (managed or self-hosted), token minting (HS256 / SOLO_SECRET), verification via curl, and instructions to point MCP clients (e.g., Claude Desktop, Claude Code, Cursor) at the endpoint. It also covers multi-tenant token exchange, runtime revocation using a jti denylist, gating tool discovery with list_authorizer, observability (Prometheus/OpenTelemetry traces), known limitations, and links to ready-made packs (MCP Postgres Starter, MCP Quickstart).

• Air Pipe provides a pack and config pattern to expose MCP tools over Postgres.
• The tutorial defines three Postgres tables: mcp_tenants, mcp_tokens (revocation denylist), and mcp_tasks.
• MCP clients referenced include Claude Desktop, Claude Code, and Cursor.

Open-source tool enables LLMs to watch videos locally

An open-source project, claude-real-video, enables language models and MCP clients (e.g., Claude Desktop, Cursor) to ingest videos locally by extracting scene-aware, deduplicated keyframes and a timestamped transcript. The tool (MIT license, ~1.9k stars on GitHub) runs fully on the user's machine, offers two MCP-callable tools (watch_video and get_frames), caches analyses under ~/.cache/crv-mcp, and requires Whisper for transcription. Since version 0.8.0 it exposes an MCP server so compatible clients can request videos directly. The author verified end-to-end operation on Claude Code and notes compatibility considerations with the MCP SDK/FastMCP releases.

• claude-real-video is an open-source GitHub repo (MIT) with ~1.9k stars that extracts scene-aware, deduplicated keyframes and a timestamped transcript from videos.
• Since version 0.8.0, claude-real-video ships as an MCP server so MCP clients can request a video directly.
• The package can be installed with pip as 'claude-real-video[mcp]'.