Mit Token-Effizienz verknüpfte gemessene Katalogeinträge.
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
Sterne29Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.
Sterne28Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.
Sterne24Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.
Sterne24Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Claude Code harness that refreshes its own context instead of compacting: at a threshold it writes a verified capsule, runs /clear, and resumes in a fresh session. Memory is plain markdown in git, readable with git log. MIT, runs locally, one install (Node 18+). Codex adapter included.
Sterne23Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
Downloads · letzte 7 Tage107Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
Downloads · letzte 7 Tage101Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Deprecated — Catalyst local runtime, kept for history. Use coalesce-labs/catalyst-dev-skills and coalesce-labs/catalyst-cloud-skills.
Sterne20Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token costs in some scenarios.
Sterne17Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung
Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.
Sterne17Gemessen · 22.10.2026
Momentum07 Tage · Gemessen · 0% relative Änderung