Self Improvement Python Packages

darwin-memo

Self-curating memory for LLM agents: MeMo-style external memory kept honest by survival-based selection. No reward models, no judges.

axiom-apex

Deterministic, self-improving AI agent execution harness and runtime for the AXIOM ecosystem. Enforces plan-deterministic execution, parallel swarm orchestration, and signal-level sandboxing.

kairos-agent

kairos picks the right LLM technique for any task by querying a curated wiki of agent patterns - RAG, ReAct, Reflexion, and 17 more. Karpathy LLM Wiki + rule-based selector + 3 working runners. Zero API keys (routes through llm-mcp).

evoloop

Framework-agnostic eval toolkit for AI agents — capture traces, judge outputs, and evolve prompts.

memary

The Open Source Memory Layer For Autonomous Agents

spellwell

Practice spelling using your terminal.

ratchet-factory

Scaffold and generate agents and modules for the Ratchet framework

ratchet-research

Deep research capability for the Ratchet framework

ratchet-core

The accountability layer for AI agents — core framework

ratchet-memory

Persistent agent memory for the Ratchet framework

ratchet-pilot

Self-improvement engine for the Ratchet framework

ratchet-ops

Business process automation for the Ratchet framework