Portfolio
2025Tooling

ClaudeBench

Claude Code Best Friend

Anticipated Anthropic's Harness Pattern

A Redis-first, event-driven workbench with swarm intelligence for decomposing complex tasks into specialist-assigned subtasks. Features JSONRPC 2.0 + WebSocket communication, MCP integration, and React dashboard with Kanban. Architecture anticipated Anthropic's published long-running-agent harness pattern.

Client
Open source (MIT)
Role
Creator & sole maintainer
Duration
Ongoing since 2025
Team
Solo
Highlights
  • Redis-first coordination with direct primitives
  • Swarm intelligence for task decomposition
  • Event-driven with JSONRPC 2.0 + WebSocket
  • MCP integration from day one
  • React dashboard with Kanban
  • 579+ commits at time of writing
Screenshots
01

Why I built it

When you're running long coding sessions with Claude as the executor, you run out of context window before you run out of work, and the next session starts blind.

I solved that my way: a Redis-first, event-driven workbench with swarm intelligence for decomposing complex tasks into specialist-assigned subtasks — observable through a real-time dashboard.

02

Timeline

On 26-Nov-2025 Anthropic published 'Effective harnesses for long-running agents'. ClaudeBench was released approximately 8 weeks prior.

The architectural pattern ClaudeBench implements aligns with the concepts later published in that document.

AgentClaudeMCPRedisTask ManagementSwarm Intelligence