npm
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.
MIT2026年9月11日 · 指标 2.10.0
全部标签
目录标签
#self-improving-agents
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
3 条记录
crates.io
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.
Apache-2.02026年8月23日 · 指标 2.10.0
npm · PyPI
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.
自定义许可证2026年9月13日 · 指标 2.10.0