neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
MIND 是一种确定性系统语言,其输出在 x86_64(AVX2)和 ARM64(NEON)CPU 基板上对其覆盖工作负载实现位相同,并通过 "" 生成防篡改证据链进行哈希。
AI 翻译
MIND is a deterministic systems language whose output is bit-identical across x86_64 (AVX2) and ARM64 (NEON) CPU substrates for its covered workloads, with a tamper-evident evidence chain hashed over
开发工具Python · ShellGitHub @star-ga在线运营者未确认
试用过了吗? 点一下就好,无需登录。
MIND 为 Claude Code、OpenClaw 以及任何兼容 MCP 的代理提供持久化 AI 记忆。采用 BM25F 与向量混合,具备治理感知、本地优先、零基础设施。
AI 翻译
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Replayable memory for AI agents. Governed recall with canonical, hash-anchored audit evidence.
Built on the MIND substrate • Governed-write • Deterministic recall • 107 MCP tools
MIND Language Profile: default (full tensor stdlib + Q16.16 + heap) — see Phase 10.6
Current release: v5.0.4 (candidate; publication pending) — corrects lifecycle ranking, graph admission and release gates, and adds source-only training preparation —
see CHANGELOG
(single source of truth; per-version detail tables below may lag the changelog)查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Replayable memory for AI agents. Governed recall with canonical, hash-anchored audit evidence.
Built on the MIND substrate • Governed-write • Deterministic recall • 107 MCP tools
MIND Language Profile: default (full tensor stdlib + Q16.16 + heap) — see Phase 10.6
Current release: v5.0.4 (candidate; publication pending) — corrects lifecycle ranking, graph admission and release gates, and adds source-only training preparation —
see CHANGELOG
(single source of truth; per-version detail tables below may lag the changelog)查看完整 README ↗