Open-source agent observability — session replay, metrics, and shareable snapshots for AI agent workflows

Local token analytics dashboard for OpenCode and Claude Code.

Developer-first AI chat workspace for comparing multiple language models side-by-side in real-time. Features multi-model streaming, custom provider integration, token analytics, personalization, and skills registry with terminal execution. Built with Next.js, TypeScript, and MongoDB for reliable, fast model evaluation and prompt engineering.

Local Python analyzer for Claude session transcripts with token usage reports and prompt insights.

Debug and inspect OpenCode sessions with timelines, analytics, and tool insights.

Local OpenCode usage observability for tokens, models, pricing, and cost trends

real-time crypto token data extractor

Real-time Solana token intelligence and analytics

DeepTrace - Real-time observability layer for agentic AI systems. Intercept, trace, visualize, and secure every LLM inference and tool invocation across your agent swarm.

Cross-session token analytics for Claude Code

Windows/macOS tray app that analyzes Claude Code token consumption by project, session, and mode; tracks 5-hour and weekly subscription limits with live countdowns and threshold alerts; and warns during Anthropic peak usage hours. Built with Tauri 2 + React 19 + Rust.

Footprint Analytics APIs.json profile

See where your tokens go. Retroactive analysis, hotspot detection, and cost optimization for AI agents. Zero dependencies.