Skip to content
@AgentGameLab

虾球球XiaQiuQiu

Building AI-Agent-native games and the infrastructure behind them. Games where agents don't assist — they are the game.

Popular repositories Loading

  1. mneme mneme Public

    Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.

    JavaScript 7 1

  2. typeless-but-free typeless-but-free Public

    Local, private, hold-to-talk voice dictation with AI cleanup. Like Typeless — but free & open source.

    Python 6 2

  3. learn-coach learn-coach Public

    教学陪练 Claude Code skill — 把「给答案」升级为「教到会」(费曼回讲 / 苏格拉底提问 / 脚手架分层 / 生产性失败)。A Claude Code skill that teaches to mastery, not just answers.

  4. harness-evolve harness-evolve Public

    Self-evolving Agent Skill (SKILL.md) for any harness with config + logs — one pipeline: track frontier research, self-audit config, act within L1/L2/L3 risk tiers. Native in Claude Code; also usabl…

  5. tuneup tuneup Public

    Agent Skill (SKILL.md) that turns a fuzzy request into a high-information-density prompt — triage + 4-quadrant forging + domain-expert lens + theory anchors. Native in Claude Code; also usable in C…

  6. evolve evolve Public

    Turn your AI agent into a capability amplifier — it watches your real work, finds where you're actually stuck, traces it to the discipline that studied it for decades, and feeds what it learns into…

    JavaScript

Repositories

Showing 9 of 9 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…