agent-optimization

OpenTelemetry-native SDK for AI agent observability, tracing, evaluation, debugging, governance, and runtime policy enforcement. Framework-agnostic and built for OpenAI Agents, LangGraph, CrewAI, and LLM applications in production.

Claude Code for DSPy: Comprehensive CLI to Optimize Your DSPy Code. our AI-Powered DSPy Development Assistant

RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Tune your AI Agent to best meet its KPI with a cyclic process of analyze, improve and simulate

SuperOptiX: Full Stack Agentic AI Framework

Turbocharge your AI Agents with TurboQuant

Agentic Environment Optimization for Autonomous AI Agents

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD methodology (RED-GREEN-REFACTOR). Features rescue-tokens skill: 90% verbosity reduction, eliminates rate limits through 9 optimization patterns.

Auto consolidate all your Agent Runtimes. Share memory across your agents.Auto highly structured task analyzer.

Official MutagenT skills for AI coding agents — Claude Code plugin marketplace for prompt optimization, evaluation, and observability.

Real-world demos for Opik Agent Optimizer: improve prompts and agents with Opik, the open-source LLM observability and evaluation platform, built by Comet.

Leangetic CLI - turn your AI agent into a proven cheaper hybrid. Source-available client; the optimization service is hosted at leangetic.com.

Self-evolving agent optimization system — iteratively improves AI agents via hypothesis-driven code changes. Supports Claude Code and Kiro CLI.

NoeticOS: the JIT compiler for agents. Adaptive runtime intelligence for production agents, per-task-class tuning of model, temperature, topP, maxTurns, retryBudget, and contextShare with confidence-bound bandits, deterministic canary rollouts, automatic rollback, and a complete decision audit log. Zero dependencies, TypeScript, edge-ready.

Optional, independently switchable agent optimization pack for Ledgered Agent Memory Fabric.

Process-Aware Agent Evaluation and Reliability Optimization — Open Core and Public Evidence Release

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Automatic optimization for multi-agent systems — prompts, config, communication, topology. OpenClaw-native.