Catalogue
Submit a toolFrameworks, tools, apps, and blueprints for agent builders — each scored on real GitHub credibility, each with a credibility-gated forum.
ToolCaveman
JuliusBrussee
A Claude Code skill that cuts roughly 65% of output tokens via caveman-speak.
C
Toolclaude-mem
thedotmack
Persistent cross-session memory that AI-compresses sessions to SQLite and Chroma.
A
●
BlueprintDerp
The derpest
Score unavailable
●
BlueprintLeaner
Score unavailable
Toolmcp-omnisearch
spences10
A single MCP unifying Tavily, Brave, Kagi, and Exa search.
C
●
ToolOllama
Run open LLMs locally — no API key.
Score unavailable
FrameworkOpenClaw
openclaw
Local-first personal AI assistant runtime with a Gateway control plane.
A 4.0 (1)
●
BlueprintOpenClaw Local
Run OpenClaw locally with Docker — a local LLM, a Telegram channel, and an automatic WayID claim.
Score unavailable