MCP server that provides real-time rate-limit and context budget awareness to Claude Code, enabling it to plan tasks that fit within its constraints and defer work when needed.
Reversibly compress a large tool output to a recoverable 8-hex handle over stdio, expand it back to the exact original bytes on demand, and report a local token/dollar savings ledger. Zero runtime dependencies; content never leaves the machine.
A terminal live-tail and a browser dashboard — one process, one event stream, served from localhost. Unified timeline across Claude Code, Codex, Gemini CLI, Cursor, Hermes, and OpenClaw. Token + cost accounting, compaction + anomaly detection, hybrid search, SVG call graphs, monaco-style diff attribution, agent-aware replay ("what would the agent say if I edited the prompt?"), policy editor, MCP s
Compacts noisy test, build, and cloud-log output before an AI agent reads it — dedupes repeats, collapses stack frames, folds Playwright retries, and renders CloudWatch/GCP JSON logs down to the signal. Typically 80–95% fewer tokens on failures.
Tool: compact_output. Run: npx -y logslim logslim-mcp
Guck is a tiny, MCP-first telemetry store for agentic debugging. It provides token-efficient log analytics by capturing JSONL telemetry events and exposing a minimal MCP toolset for fast, filtered queries.
Reduces log files to remove noise and duplicate information, cutting tokens by 70-90% for AI agents, preserving only errors, warnings, and unique events.