Catalogue tag

#self-improving-agents

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

3 records

Tagged “self-improving-agents”Ranked by health index

npm

84Excellenthealth index

IgorGanapolsky/ThumbGate

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

JavaScript · HTML★ 26↓ 2,369/moSep 11, 2026

MITSep 11, 2026 · metrics 2.10.0

crates.io

73Goodhealth index

AreevAI/areev

Self-improving agents, governed. Areev is the substrate for adaptive agents — agents that get better from their own history, under human authority, in steps you can inspect, undo, and re-measure.

Rust★ 7↓ 762/moAug 23, 2026

Apache-2.0Aug 23, 2026 · metrics 2.10.0

npm · PyPI

67Goodhealth index

Opus-Aether-AI/legion-core

The model-agnostic execution layer for AI agents: scoped routing and delegation, isolated worktrees, evidence, observability, and learning loops. The stack, not another wrapper. Seven executors — Claude Code, Codex, Cursor, opencode, DeepSeek Harness, Hermes, Pi — under one metered contract.

Python · Shell★ 0↓ 3,129/moSep 13, 2026

Custom licenseSep 13, 2026 · metrics 2.10.0