Self-improving starter skill and operator toolkit for running Codex or Claude Code as the orchestrator over Symphony workers with Linear-managed execution.

repo for reusable plugins and skills

Skill Forge — turn an LLM agent's repeated failures into reviewed, signed-installation skills. Telegram-approved HMAC tokens, replay regression gate, and a full Forge Console covering doctor → demo → forge → install → evolve.

Tirami — distributed LLM inference where compute is currency. 1 TRM = 10^9 FLOPs. 21B supply cap, yield halving, staking, collusion resistance. 100% Rust, OpenAI-compatible, no token, no ICO. "tira mi su" = pull me up.

Planner-Worker-Judge-Curator multi-agent system with self-improvement (Gene/Capsule store) over a local A2A bus

Give your AI agent memory. Convenience wrapper for agent-episodic-memory.

Local-first, model-agnostic workflow optimizer for long-running AI agents: observable JSONL ledgers, deterministic reducers, no-meta gates, and receipt-backed self-improvement without LLM judges or model-weight updates.

Adaptive Verified Iteration Loop (AVIL): A Self-Improving Software Development Lifecycle for Agentic AI Systems — research paper with formal model, algorithms, and simulated evaluation

Self-Improving Agents - Autonomous experiment loop for any measurable artifact

A dual-loop self-evolution system for AI agents: fast fixes for local repeated mistakes, slow promotion for durable capability.