#llm-observability

Budget enforcement + observability plugin for Hermes Agent. Stops runaway costs before they happen.

Local dashboard for every Claude Code session on your machine — live activity, cost per repo, loop alerts. No telemetry.

Local desktop dashboard for Claude Code. Reads your JSONL transcripts and surfaces per-prompt cost, tool heatmaps, subagent attribution, cache analytics, and a rule-based tips engine. Rust + Tauri, fully offline, MIT.

My Claude Code (MCC) is a local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents — 57 providers, fallback routing, credential health, a native web-search tool proxy, and exhaustive analytics with cost provenance in one local dashboard.

git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block.

Real-time detection and repair of LLM agent failures — a one-class behavioural monitor at ~200 µs/step, with 2,823 committed traces.

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model access, platform-run tools, request history, and usage.

Deterministic health monitoring for LLM conversations. Detects context pressure, drift, repetition and tool anomalies without adding anything to model context.

Production-inspired AI observability lab: a traced and evaluated fictional banking RAG assistant with OpenTelemetry, Phoenix, prompt experiments, guardrails, and optional Dynatrace fan-out.

Marketing landing page for loopgain.ai — an open-source cost controller for AI agent loops.

Local-first debugger for tool-using AI agents — freeze a failed run, patch one step, replay, diff, and prove the fix. Metadata-only capture, never your prompts.

Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.

MCP server for AgentMinds — cross-site collective intelligence for production AI agents. Drop in to Claude Code, Cursor, Zed: push agent reports, pull personalised recommendations from the network.

Python SDK for AgentMinds — cross-site collective intelligence for production AI agents. Auto-capture errors + push/pull patterns from the network pool.

Node.js SDK for AgentMinds — cross-site collective intelligence for production AI agents. Auto-capture errors + push/pull patterns from the network pool.

Time-travel debugging for AI agents: record, fork and replay runs, trajectory evaluation, MCP server

OpenTelemetry observability and privacy-aware failure replay for production AI agents.

LLM chatbot + auto-instrumented inference logging pipeline — Rust/Axum SDK wrapper fires structured telemetry (latency, tokens, model, status) over a tokio channel into Postgres, with a live SvelteKit dashboard. One-command Docker setup.

LLM chatbot + auto-instrumented inference logging pipeline — Rust/Axum SDK wrapper fires structured telemetry (latency, tokens, model, status) over a tokio channel into Postgres, with a live SvelteKit dashboard. One-command Docker setup.