15 Jun 19:31

03c5fd4

Memcore Cloud 2026.6.16 Latest

Latest

Memcore Cloud 2026.6.16

Memcore Cloud 2026.6.16 focuses on making the local AI memory library easier to
connect, inspect, and trust. It fixes the local AI "finished the chat, lost the
context" problem by keeping original records, preferences, project boundaries,
proven work paths, and borrowing receipts on the user's own machine.

Highlights

Local AI memory library: original records remain the archive, library ids
make memories findable, and usage receipts show what an agent borrowed before
it answered.
Source-backed recall: recall can return compact source refs, rank reasons,
and bounded original excerpts when explicitly requested.
Pre-work context checks: before coding, installing, syncing, or
troubleshooting, an agent can check whether the work looks already built,
miswired, missing diagnostics, or truly missing.
Zhiyi and Xingce stay distinct: Zhiyi keeps preferences, corrections,
habits, and boundaries; Xingce keeps repair paths, validation steps, and work
methods.
Experience reaches local agents: skill-, instruction-, and MCP-capable
local agents can read the same Xingce guidance before work instead of keeping
separate private experience stores.
Traceable experience evolution: successful fixes, mistakes, and user
corrections can become candidates. Source-backed candidates with original
evidence and acceptance checks can be adopted, upgraded, rejected, or rolled
back with receipts.
Record Doctor: a safe read-only check shows whether source records, raw
mirrors, the canonical index, and memory/experience links are guarded before
real recall is tested.
Quieter first response: capability check remains read-only and no-recall;
real memory is only retrieved when an agent calls recall.
Installer entry points: macOS, Linux, and Windows installers use the
2026.6.16 release tag and keep local data such as memory/, raw/, zhiyi/,
and config/ separate from app files.

中文

Memcore Cloud 2026.6.16 的重点，是让“忆凡尘这座本机 AI 记忆图书馆”更容易接入、检查和信任。它解决本机 AI “聊完就散、换窗就忘、做过还重做”的硬伤：原始记录仍然是最高事实；召回要能回源；有用的工作经验必须经过证据和验收，才能变成下一次可复用的行策。

主要更新

本机 AI 记忆图书馆：原始记录是馆藏原件，馆藏号负责定位，借阅记录说明 agent 回答前用了哪些记忆。
可回源召回：召回可以返回精简来源线索、命中理由，并在明确需要时给出有界原文摘录。
开工前上下文检查：写代码、安装、同步、排障前，agent 可以先判断这件事更像已经做过、接线错了、缺诊断，还是确实缺功能。
知意和行策分开：知意保存偏好、纠正、习惯和边界；行策保存修复路径、验证步骤和工作方法。
经验可以接给本机 agent：支持 skill、自定义指令或 MCP 的本机 agent，都可以在动手前读取同一套行策经验，而不是各自攒一套私有经验。
经验可追踪进化：做成、踩坑、纠错都可以先成为候选；带得回来源、原文和验收条件的候选，才能被采纳、升级、拒绝或回滚，并留下回执。
记录医生：真实召回前，可以先用只读自检确认源记录、raw 镜像、canonical index 和记忆/经验链路是否守住。
更安全的第一次测试：capability check 仍然只读、无真实召回；只有 agent 明确调用 recall，才读取真实记忆。
安装入口对齐：macOS、Linux、Windows 安装器使用 2026.6.16 release tag，并把 memory/、raw/、zhiyi/、config/ 等本地数据和软件文件分开。

Boundaries

Summaries help navigation, but they do not replace original records.
Experience is not a skill marketplace and Xingce is not a callable function
library.
Experience evolves, but it stays source-backed, reviewable, and reversible.
Local data stays on the user's machine by default.

Assets 6

15 Jun 03:53

strmforge

v2026.6.15

9646c7f

Memcore Cloud 2026.6.15

Memcore Cloud 2026.6.15 is a release for the Tiandao-governed memory and
experience system. It keeps the 2026.6.14 cleanup base, then makes
the next codebase easier to audit by turning experience adoption into a
receipt-backed, source-traceable dry-run flow.

Status: published GitHub Release.

English

Highlights

Tiandao-governed module split: the former giant console, platform guard,
Claude Desktop, raw gateway, Hermes liveness, and record-guardian surfaces
have been split by ownership boundary rather than arbitrary line count.
Record origin remains first: canonical indexing, raw evidence excerpts,
and raw backfill now live in dedicated record modules, but raw source records
remain the highest authority.
Console stays an entrypoint: p6_console.py remains the human console and
compatibility wrapper, while UI, action gates, status diagnostics, OpenClaw
inlet, Zhiyi runtime, and experience governance live in smaller modules.
Platform Guard is clearer: catalog, model identity, package inventory,
and surface scanning are separated from authorized platform-config apply.
Claude Desktop capture boundary is clearer: Claude Desktop raw ingest
logic is isolated from the connector entrypoint, and local relay references
remain development/compatibility metadata rather than public requirements.
Runtime version alignment: the release reports 2026.6.15 in the version
file, gateway health, active-memory routing, preflight metadata, local console
text, platform storage contract, and packaged Zhiyi skill.
Install readiness waits for large local libraries: macOS, Linux, and
Windows installers now wait for slow-starting local services instead of
failing after a single early smoke probe.
Experience validation receipts: Xingce can now emit a dry-run validation
receipt schema that records pass/fail status, evidence links, and adoption
blockers without mutating the experience library.
Receipt-backed apply gate: adoption checks prefer validation receipts when
present, while preserving compatibility with the older validation-report
fallback path.
Apply package preview: a ready apply package can be built as a local
dry-run artifact. package_status=ready means ready for a future authorized
apply, not already adopted.
Experience flow overview: the console can now show a compact record chain
across experience evolution, review action, validation report, validation
receipt, review queue, apply gate, apply receipt schema, and apply package.
Release validation: 2026.6.15 was tested in this
run on macOS and two Windows hosts. Full local tests passed, the working-tree
release gate passed before commit, the committed-HEAD release gate passed
before publication, Windows native smoke passed, and the record-chain audit
found no lost source or lost raw. Claude Desktop bridge presence was verified
on detected Windows Claude config homes; one package-scoped Windows config
is still malformed JSON and remains a local follow-up.
Record doctor and record chain: a new read-only doctor/demo check shows
whether source records, raw mirrors, the canonical index, and memory/experience
links are guarded. The timeline/replay surface is framed as a record chain,
not a memory wall.
Recall output is quieter by default: Zhiyi recall now returns compact
source refs, counts, receipts, and rank reasons by default. Bounded raw
excerpts remain available only when explicitly requested with a raw response
budget.
Runtime bootstrap starts the foundation cleanup: new and migrated command
entry points can share one repository/import bootstrap instead of adding more
ad-hoc path setup snippets.
Double-click install entries: release zips now include a macOS
Memcore Cloud Installer.command and a Windows Memcore Cloud Installer.cmd;
the Windows entry opens a folder picker before running the same installer.
Public wording tightened: public copy now leads with local continuity,
source-backed records, recall, and reusable work paths, while the detailed
integration capability coverage stays maintainer test material rather than
user-facing product text.
Release checks remain guarded: public wording scans, private local
agent-rule file exclusion, release artifact checks, internal direction audit,
and full tests passed before publication.

Boundaries

Release assets are built from committed HEAD after the release gate passes.
Local maintainer-only files and private local agent-rule files remain ignored
and are not part of public release artifacts.
Capability check remains read-only and no-recall.
LAN reachability for OpenClaw and Hermes remains supported when explicitly
configured.
Multi-machine validation for 2026.6.15 was filled from the 2026-06-15
current run only; older 2026.6.14 results were not reused as proof.

中文

主要更新

天道管辖下拆分模块：原先过大的 console、Platform Guard、Claude Desktop、raw gateway、Hermes liveness 和记录守护相关文件，按真实管辖边界拆分，而不是按行数硬切。
记录起源仍然第一：canonical index、raw evidence excerpt、raw backfill 进入独立记录模块，但 raw source record 仍然是最高事实。
控制台仍是入口：p6_console.py 保留为人类控制台入口和兼容 wrapper；UI、动作安全门、状态诊断、OpenClaw inlet、知意 runtime、体验治理拆到更小模块。
Platform Guard 更清楚：catalog、model identity、package inventory、surface scan 与授权 platform config apply 分开。
Claude Desktop 采集边界更清楚：Claude Desktop raw ingest 从 connector 入口中拆出；本地中转痕迹只保留为开发/兼容元数据，不写成公开依赖。
运行版本对齐：发布版在 VERSION、gateway health、active memory routing、preflight metadata、本地控制台文本、platform storage contract 和随包 Zhiyi skill 中统一报告 2026.6.15。
安装 smoke 适配大库慢启动：macOS、Linux、Windows 安装器现在会等待本地服务就绪，不再把一次过早探测失败当成最终失败。
经验验证回执：行策可以生成 dry-run 验证回执格式，记录通过/失败状态、证据链接和采纳阻断点，但不改写经验库。
采纳门禁引用回执：采纳检查会优先使用验证回执；旧的验证报告路径仍然保持兼容。
采纳包预览：可以生成本地 dry-run 采纳包。package_status=ready 只表示未来授权采纳已准备好，不表示已经采纳。
经验链路总览：控制台可以展示经验演进、review action、验证报告、验证回执、review queue、采纳门禁、采纳回执格式、采纳包的紧凑记录链路。
发布验证：2026.6.15 已在本轮对本机 macOS 和两台 Windows 主机实测；本地全量测试通过、提交前 working-tree release gate 通过、发布前 committed-HEAD release gate 通过、Windows 原生 smoke 通过，记录链路巡检未发现遗失源或遗失 raw。已在检测到的 Windows Claude 配置位置确认 Claude Desktop bridge 存在；其中一个 package-scoped Windows 配置仍是异常 JSON，作为本机后续项保留。
记录医生与记录链路：新增只读 doctor/demo 自检，展示源记录、raw 镜像、所有会话底座、记忆与经验链路是否守住；timeline/replay 按记录链路展示，不做记忆墙。
召回默认降噪：知意召回默认返回精简的来源线索、计数、回执和命中理由；有界原文摘录仍可用，但必须显式请求 raw response budget。
运行地基统一起步：新增统一 repository/import bootstrap，新入口和后续迁移可以复用同一套路径初始化，不再继续增加零散 path setup。
双击安装入口：release zip 现在包含 macOS Memcore Cloud Installer.command 和 Windows Memcore Cloud Installer.cmd；Windows 入口会先弹出目录选择，再调用同一套安装脚本。
公开文案收紧：公开文案改为强调本机工作续接、可回源记录、召回和可复用工作路径；细分接入覆盖留作维护者测试材料，不作为用户可见产品文本。
发布检查继续守门：公开文案扫描、私有本机 agent 规则文件排除、发布包检查、内部方向审计和全量测试已在发布前通过。

边界

发布资源从提交后的 HEAD 构建，并在 release gate 通过后上传到 GitHub Release。
维护者本地文件和私有本机 agent 规则文件仍然被忽略，不进入公开发布包。
capability check 仍然只读、无真实召回。
明确配置时仍然保留 OpenClaw / Hermes 的局域网访问能力。
2026.6.15 的多机验证已来自 2026-06-15 当前运行；没有沿用旧版 2026.6.14 的结论。

Assets 6

12 Jun 16:48

strmforge

v2026.6.12

843d586

Memcore Cloud 2026.6.12

Memcore Cloud 2026.6.12 is a public-wording and release-gate patch release. It
keeps the 2026.6.11 reliability base, then removes local relay tool names from
the open-source surface, preserves compatibility with older local relay traces,
and turns the wording cleanup into a repeatable release check.

English

Highlights

Public relay denaming: public docs, catalogs, watchlists, diagnostics, and
tests no longer expose a specific local relay product as a supported public
dependency or platform entry.
Compatibility without publicity: older local relay paths, environment
variables, database names, and raw formats can still be recognized through
legacy-compatible code paths, but user-facing payloads use neutral
local_relay wording.
Lost-source wording: record diagnostics keep the preferred lost source /
lost raw semantics instead of legacy stray-record wording.
Release-gate regression scan: tools/release_gate.py now scans the
public and repository text surfaces for the removed relay names and legacy
stray-record diagnostics so the cleanup does not regress in future releases.
Runtime version alignment: installers, gateway health, active-memory
routing, preflight metadata, the local console, and packaged Zhiyi skill
metadata report 2026.6.12 consistently.
Windows install validation hardening: native Windows smoke now recognizes
running watcher processes even when PowerShell normalizes install paths
differently, tolerates prefixed JSON from Codex status checks while still
validating raw_sync, and avoids an OpenClaw config traceback when the
dialog-entry token is empty.
Real-machine validation: the 2026.6.12 package was validated on local
macOS plus two Windows hosts, with Windows native smoke confirming
codex_capture_status raw_sync=raw_current.

Boundaries

2026.6.12 does not add a new user workflow; it hardens naming, attribution,
Windows install validation, and release checks around already-built record and
recall behavior.
Local relay compatibility is retained for existing personal setups, but the
public project does not present any relay product as required infrastructure.
Capability check remains read-only and no-recall.
LAN reachability for OpenClaw and Hermes remains supported when explicitly
configured.

中文

主要更新

公开仓库去名化：公开文档、平台目录、watchlist、诊断和测试不再把某个本地中转工具写成公开依赖或平台入口。
兼容但不宣传：旧的本地中转路径、环境变量、数据库名和 raw format 仍能被兼容识别，但用户可见 payload 使用中性的
local_relay 表达。
遗失措辞统一：记录诊断继续使用遗失源 / 遗失 raw 语义，不再回到旧的游离记录说法。
release gate 防回归：tools/release_gate.py 会扫描公开面和仓库文本，阻止被移除的中转工具名和旧的游离记录诊断重新进入发布包。
运行版本对齐：安装器、gateway health、active memory routing、preflight metadata、本地控制台和随包 Zhiyi skill 都统一报告
2026.6.12。
Windows 安装验收加固：原生 Windows smoke 能识别 PowerShell 路径归一化差异下仍在运行的 watcher；Codex 状态检查即使夹杂前缀输出，也会提取 JSON 后继续校验
raw_sync；OpenClaw config helper 在 dialog-entry token 为空时不再抛 traceback。
真机验证：2026.6.12 包已在本机 macOS 和两台 Windows 主机上验证，Windows native smoke 均确认
codex_capture_status raw_sync=raw_current。

边界

2026.6.12 不新增普通用户工作流；它加固已有记录和召回能力周围的命名、归属、Windows 安装验收和发布检查。
旧本地中转兼容保留给已有个人环境，但公开项目不把任何中转产品写成必要基础设施。
capability check 仍然只读、无真实召回。
明确配置时仍然保留 OpenClaw / Hermes 的局域网访问能力。

Assets 6

11 Jun 14:05

strmforge

v2026.6.11

2f03402

Memcore Cloud 2026.6.11

Memcore Cloud 2026.6.11 is a reliability release for the local record base and
the active Zhiyi/Xingce path. It keeps the record-first boundary from 2026.6.9,
then makes recovery, preflight recall, and runtime health checks less passive.

English

Highlights

Checkpoint recovery: corrupt P0 and P2 checkpoint files are preserved as
.corrupt-backup-* files and the next save uses atomic replacement, so a bad
local state file does not stall record capture.
Canonical session identity: Codex and Claude Code records now normalize
canonical window identity to the native session id while keeping older
workspace/window hints as source refs and project clues.
Zhiyi/Xingce preflight: the read-only preflight planner can decide when
source-backed Zhiyi or Xingce anchors should surface before an agent answers,
and when it should retreat silently.
Fast current-window recall: the raw gateway can answer short continuation
preflight requests from the canonical record index without cold-loading broad
recall or returning raw excerpts.
Claude Code hook: installers can add a quiet UserPromptSubmit hook for
Claude Code. It only emits additional context when preflight returns a
source-backed surface decision.
Runtime guard tightening: raw gateway health reports its source identity
and hash; Windows guardian checks that identity and reports foreign port
owners. Dialog-entry tokens are scoped to dialog-entry service commands
instead of being injected into unrelated local services.

Boundaries

Preflight is a behind-the-scenes agent aid, not a new user-facing feature.
Capability check remains read-only and no-recall.
Raw excerpts are not exposed by preflight bridge compaction or the Claude Code
hook.
LAN reachability for OpenClaw and Hermes remains supported when explicitly
configured.

中文

主要更新

checkpoint 坏账本恢复：P0 / P2 checkpoint 损坏时会先备份为
.corrupt-backup-*，后续保存改为原子替换，避免一个坏状态文件卡住记录采集。
canonical session 身份修正：Codex 和 Claude Code 记录把 canonical window
统一到原生 session id，同时把旧 workspace/window 线索保留为 source refs 和项目线索。
知意 / 行策 preflight：新增只读裁判层，能判断什么时候应该在回答前主动浮现有来源的知意
或行策锚点，什么时候应该静默退回。
当前窗口快速召回：raw gateway 可以从 canonical record index 回答短续问 preflight，
不冷启动宽范围召回，也不返回 raw 原文。
Claude Code hook：安装器可以写入安静的 UserPromptSubmit hook；只有 preflight
返回有来源的 surface 决策时才给 Claude Code 增加上下文。
运行守护收紧：raw gateway health 带 source 身份和哈希；Windows guardian 校验该身份并报告
端口归属。dialog-entry token 只进入 dialog-entry 服务命令，不再扩散到无关本地服务。

边界

preflight 是 agent 背后的辅助机制，不是新的用户功能入口。
capability check 仍然只读、无真实召回。
preflight bridge 和 Claude Code hook 不暴露 raw excerpt。
明确配置时仍然保留 OpenClaw / Hermes 的局域网访问能力。

Assets 4

08 Jun 21:42

strmforge

v2026.6.9

9299eb7

Memcore Cloud 2026.6.9

Memcore Cloud 2026.6.9 is a record-first release candidate: it tightens the
local record base, keeps source boundaries clearer, and adds release gates for
the larger pre-release change set.

English

Highlights

Record Origin Guard: raw source records are treated as the origin of the
local memory timeline. The guardian checks source/raw freshness, corruption,
recoverability, and lost source / lost raw states.
All-session canonical index: Codex, Claude Code CLI, Claude Desktop,
OpenClaw, Hermes, and other verified local records can be indexed across
sessions without turning summaries into authority.
Claude Desktop three-surface model: Chat is handled as the claude.ai
web-chat surface with local cache evidence only; Cowork and Code/agent records
use verified local JSONL body candidates when available.
Safer LAN entry points: local action routes are token-gated while keeping
LAN access available for setups that intentionally use OpenClaw or Hermes from
another machine on the same network.
Second Brain and Time River contracts: material processing, external docs
evidence, context delivery compaction, and Time River sediment now have
bounded dry-run contracts. They strengthen source-backed recall without
replacing raw records.
Release gate coverage: the pre-release gate compiles Python, checks
installer syntax, scans public wording, runs internal direction and core record
reliability audits, and executes the test suite.

Boundaries

Chat cache evidence is not claimed as a complete local Claude.ai transcript.
Capability check remains read-only and no-recall.
Public docs avoid development-only relay/tool names as dependencies.
User-facing status should show record health, recovery, and lost source / lost
raw states rather than internal construction progress.

中文

主要更新

记录底座与时间起源：原始 source / raw 记录被放回记忆系统的起点。记录守护会检查
source/raw 新鲜度、损坏、可恢复状态，以及遗失源 / 遗失 raw。
所有会话 canonical index：Codex、Claude Code CLI、Claude Desktop、
OpenClaw、Hermes 和其他已验证本机记录可以进入跨会话索引，但摘要仍然只是导航，不替代原始记录。
Claude Desktop 三模式分型：Chat 按 claude.ai 网页聊天表面处理，本地只算缓存证据；
Cowork 和 Code/agent 在可验证时使用本地 JSONL 正文候选。
LAN 入口安全分档：动作路由加 token gate，同时保留有意使用局域网连接 OpenClaw /
Hermes 的能力。
第二大脑与时间长河契约：资料处理流水线、外部文档证据、上下文投递压缩、时间长河沉积
都进入有边界的 dry-run 合同，用来增强可回源召回，不替代 raw。
发布前检查增强：release gate 会编译 Python、检查安装脚本语法、扫描公开文案、运行
内部方向审计、核心记录可靠性审计和测试套件。

边界

Chat 缓存证据不声明为完整本地 Claude.ai transcript。
capability check 仍然只读、无真实召回、不返回原文。
公开文档不把开发环境里的中转工具名写成用户依赖。
普通用户界面应该展示记录健康、恢复和遗失源 / 遗失 raw，而不是内部施工完成度。

Assets 4

03 Jun 20:45

strmforge

v2026.6.4

0b2f3a1

Memcore Cloud 2026.6.4

Memcore Cloud 2026.6.4 ships the latest local-memory work:
native Windows installs, official Codex MCP connection, active memory routing,
and clearer local-tool discovery.

The product promise is simple: install once, let Memcore Cloud find local AI
tools, connect supported Skill/MCP surfaces, and keep recall tied to source
records without making every new window start from zero.

English

Highlights

Native Windows is now the normal path: Windows users should install
Memcore Cloud directly with PowerShell. WSL remains for development or
advanced testing.
Official Codex on Windows is verified: Memcore Cloud can find the bundled
official codex.exe even when it is not on PATH, then register
yifanchen-zhiyi through official codex mcp add.
Codex MCP uses a current-window bridge: the installed Codex MCP entry uses
a local stdio bridge so recall can carry window/session identity instead of
guessing from another Codex session.
Active recall is window-first, not window-only: ordinary clients try the
current window/session first, then same project/workspace, same
workstream/task, and stable preferences/tool facts. raw-pool/global remains
explicit; Hermes broad context stays limited to explicit skill-generation or
review workflows.
Continuous sync is visible: the local service now reports whether
watchers are running as a continuous loop instead of a one-time install scan.
Claude Desktop local capture joins that loop by default, writing only Memcore
Cloud raw records, while pending collectors stay clearly marked.
Conversation collectors are stricter: a local tool is not promoted to
complete conversation memory unless the verified local format preserves both
user turns and assistant replies.
New-tool recognition has two layers: deterministic local rules run first;
when a model provider is configured, model-assisted identification can classify
unfamiliar local AI tools from metadata only.
Knowledge base pages were updated: the Windows official Codex validation
is now documented in the wiki for future troubleshooting.

Boundaries

A Skill/MCP connection proves the tool can call Memcore Cloud; it does not
mean real memory was recalled.
Capability check remains read-only and no-recall.
Claude Desktop local capture can enter Memcore Cloud raw by default. Ordinary
recall is active and source-backed: current window/session first, then same
project/workspace, same workstream/task, and stable preferences/tool facts.
Not every discovered local AI tool has a verified collector yet. Unknown or
partial formats stay as candidates until source-backed collection is proven.

中文

主要更新

Windows 默认走原生安装：普通 Windows 用户不该装到 WSL。WSL 只保留给
开发、高级测试或特殊排障。
官方 Windows Codex 已验证：即使 codex.exe 不在 PATH，忆凡尘也能从
Codex native-host 元数据找到官方 bundled CLI，然后用官方 codex mcp add
注册 yifanchen-zhiyi。
Codex MCP 走当前窗口 bridge：安装后的 Codex MCP 入口使用本地 stdio
bridge，召回时带上窗口/session 线索，不再靠猜另一个 Codex 会话。
active 召回是窗口优先，不是窗口锁死：普通客户端先读当前窗口/session，
然后同项目/同工作区、同工作流/同任务、稳定偏好/工具事实。raw-pool/global
仍然只在明确要求更宽视图时使用；Hermes 的宽上下文只保留给明确的 skill
生成或审查流程。
持续同步状态可见：本地服务会报告 watcher 是持续循环，不是安装时扫一次。
Claude Desktop 本机采集默认加入这个循环，只写忆凡尘 raw；仍待验证的采集器会
继续标成候选。
对话采集更严格：只有已验证的本地格式同时保留用户发言和 AI 回复，才会被
当作完整对话记忆来源。
新工具识别变成两层：先用本机规则识别；如果配置了模型，再让模型只根据
元数据识别陌生本机 AI 工具。没有模型时继续走本地规则兜底。
知识库补齐：Windows 官方 Codex 原生验证已经写入 wiki，方便后续排障。

边界

Skill / MCP 接上，只证明这个工具能调用忆凡尘，不代表已经召回真实记忆。
capability check 仍然只读、无真实召回、不返回原文。
Claude Desktop 本机记录默认可以进入忆凡尘 raw。普通召回走 source-backed
active 分层：当前窗口/session 优先，然后同项目/同工作区、同工作流/同任务、
稳定偏好/工具事实。
不是每个发现到的本机 AI 工具都有完整采集器。未知格式或只保存部分对话的工具，
仍然只能标为候选，不能宣传成完整记忆来源。

Assets 2

02 Jun 17:55

strmforge

v2026.6.3

03e1902

Memcore Cloud 2026.6.3

Memcore Cloud 2026.6.3 focuses on making the installed skill behave like a real memory habit, not a one-time setup note.

The main change is simple: when an agent sees an ongoing-project question like "what next", "what else", "then what", "之前", "定论", or "还有吗", it should know to call zhiyi_recall before answering.

English

Highlights

The skill is now a standing memory rule: Memcore Cloud Zhiyi prompt v4 tells Codex, Claude Desktop, and other local agents to keep the rule active after installation.
Natural follow-ups trigger memory first: prior decisions, corrections, project boundaries, install/test/release status, and short next-step questions now get clearer recall-before-answer wording.
Install prompts are clearer: README, Wiki, and the local console copy prompt now tell users to paste one prompt into a local agent so it can install the skill, connect MCP, and run a safe check.
Safe checks stay safe: capability check still verifies the Skill/MCP path without recalling real memory or returning raw excerpts.
Local install alignment is verified: macOS and native Windows install roots can be upgraded in place while preserving user data, then installing prompt v4 into Codex and Claude Desktop skill locations.

Boundaries

Claude Desktop UI testing still depends on Claude quota being available.
Skill installation is a connection signal, not permission to read chat bodies.
Deeper platform access still needs explicit authorization.

中文

主要更新

Skill 变成长期记忆规则：Memcore Cloud Zhiyi prompt v4 会告诉 Codex、Claude Desktop 和其他本机 agent，安装后要持续遵守，而不是只看一次安装说明。
自然追问会先想起记忆：旧决定、纠错、项目边界、安装/测试/发布状态，以及“下一步 / 接下来呢 / 还有吗 / 然后呢”这类短追问，会更明确触发先调 zhiyi_recall。
安装提示更像产品入口：README、Wiki 和本地 console 的复制提示都改成“把这段发给本机 agent，它会安装 skill、接 MCP、做安全检查”。
安全检查仍然安全：capability check 仍然只验证 Skill/MCP/只读状态，不召回真实记忆、不返回原文。
本机安装目录已校准：macOS 和 Windows 原生安装目录都可以原地升级并保留用户数据，同时把 prompt v4 安装到 Codex 和 Claude Desktop 的 skill 位置。

边界

Claude Desktop UI 真实窗口测试仍受 Claude 额度影响。
安装 Skill 只是接入信号，不等于授权读取聊天正文。
更深的平台访问仍需要明确授权。

Assets 2

02 Jun 13:00

strmforge

v2026.6.2

724252b

Memcore Cloud 2026.6.2

Memcore Cloud 2026.6.2 makes the memory path feel real from inside the tools people already use.

The headline is simple: Claude can call the local memory gateway, real recall returns readable Chinese, and source-backed memory from more local tools shows up with clearer ownership.

English

Highlights

Claude recall now works cleanly: Claude can call yifanchen-zhiyi through the local MCP bridge, run safe capability checks, and perform real recall without the old timeout / JSON-RPC error path.
Chinese excerpts are readable again: recalled raw_excerpt text stays readable in Claude instead of turning into garbled characters.
Windows setup is less fragile: Claude config is written without UTF-8 BOM, the bridge speaks the JSON-line format Claude expects, and both regular and Store-style Claude config paths can be registered.
OpenClaw and Hermes records show up together: recall can surface source-backed records from multiple local tools while keeping source refs and attribution visible.
Computer-first storage is visible in practice: new records can be found under paths shaped by computer first, then by the AI tool that produced them.
The install prompt got stronger: the skill now tells an agent when to call memory first, especially for previous decisions, corrections, project boundaries, install/test/release status, and "what next" questions.
Wiki source pages are ready: product-facing wiki pages now cover getting started, safe checks, AI tool boundaries, memory layout, and release history routing.

What This Means

Memcore Cloud is no longer only saying "shared local memory" in the README. In this release, the loop is easier to test:

install the skill / MCP connection;
run capability check without recalling real memory;
run real recall;
inspect source refs and raw excerpts;
keep platform boundaries visible.

Boundaries

Claude Desktop chat-body parsing remains a separate authorization step.
Skill installation is still a connection signal, not permission to read every chat body.
Capability check remains no-recall and read-only.

中文

主要更新

Claude 召回链路更稳了：Claude 可以通过本机 MCP bridge 调 yifanchen-zhiyi，能力检查和真实 recall 都能跑通。
中文原文摘录不再乱码：Claude 里召回到的 raw_excerpt 已经能正常显示中文。
Windows 配置更稳：Claude 配置文件不再带 BOM，bridge 输出也改回 Claude 需要的 JSON-line 形式；普通路径和 Store 路径都能注册。
OpenClaw / Hermes 记录能一起召回：多来源本机记忆可以一起出现，同时保留来源和归属。
按电脑优先的目录开始落地可见：新增记录能按“计算机名 -> 软件名 -> 软件保存格式”这条结构进入本机记忆。
Skill 提示更会提醒 agent 调记忆：遇到之前的决定、纠错、项目边界、安装/测试/发布状态、下一步这类问题，先调用 zhiyi_recall。
Wiki 源文件准备好了：包含入门、安全检查、AI 工具边界、记忆目录和版本历史入口。

大白话

这一版重点不是堆新名词，而是让“AI 编程助手终于不失忆了”这件事更能被实际验证。

先安全检查，不碰真实记忆；确认通了，再做真实 recall；召回结果能读、能回源、能看出来自哪台机器和哪个工具。

边界

Claude Desktop 聊天正文解析仍是单独授权步骤。
安装 Skill 只是接入信号，不等于授权读取所有聊天正文。
capability check 仍然只读、无召回。

Assets 2

01 Jun 16:52

strmforge

v2026.6.1

f6dea9a

Memcore Cloud 2026.6.1

Memcore Cloud 2026.6.1 is the first release that presents the project with its English product name by default. 忆凡尘 / Yifanchen remains the Chinese name and codename.

This release is about making local AI memory easier to explain and easier to try. Paste one prompt into a local agent, let it install the skill and MCP connection, then run a safe check before any real memory is recalled.

English

Highlights

Memcore Cloud is now the English-first name: Yifanchen stays as the Chinese name and codename, while the repository becomes easier to search and explain in English.
Your agent can install it for you: paste the install prompt into Codex, Claude Code CLI, OpenClaw, Hermes, or another local agent. It can add the skill, connect MCP where supported, and finish with a safe capability check.
It helps AI tools stop starting from zero: Claude Desktop, Claude Code CLI, Codex, OpenClaw, Hermes, Cursor-style tools, and newer local agents can connect to the same local memory base.
It keeps sources checkable: remembered items can point back to source refs and raw excerpts instead of becoming a loose summary nobody can verify.
It shows what is already on this machine: the local page can show which AI tools are present, which ones can run a safe capability check, and which ones still need a permission step.
Claude stays separated by surface: Claude Desktop, Claude Code CLI, official-login records, and relay records keep their attribution boundaries.
New records are easier to browse later: records are grouped by computer first, then by the AI tool that produced them.
The first check is safe: capability check confirms the path is alive without recalling real memory or returning raw excerpts.

Boundaries

The local page is read-only by default.
Installing a skill is an intent signal, not permission to read chat bodies.
Capability check does not recall real memory and does not return raw excerpts.
Deeper local scans can be heavier on Windows; the default page stays fast, and broader checks should be treated as explicit/background work.

中文

主要更新

英文首屏统一为 Memcore Cloud：忆凡尘 / Yifanchen 保留为中文名和 codename，英文用户更容易搜到和理解。
可以把安装交给本机 agent：把提示发给 Codex、Claude Code CLI、OpenClaw、Hermes 或其他本机 agent，它会帮你安装 Skill、接 MCP，并只做安全能力检查。
让 AI 工具不用每次从零开始：Claude Desktop、Claude Code CLI、Codex、OpenClaw、Hermes、Cursor 类工具和新的本机 agent 可以接到同一个本机记忆底座。
记忆能回到来源：召回结果可以带来源线索和原文摘录，不只是几句无法核对的摘要。
能看见本机有哪些 AI 工具：本地页面会告诉你看到了哪些工具、哪些可以先做安全能力检查、哪些还差一次授权接入。
Claude 各入口分开看待：Claude Desktop、Claude Code CLI、官方登录记录和中转记录保留归属边界。
新记录以后更好翻：新增记录先按电脑分组，再按产生记录的 AI 工具分组。
第一步检查是安全的：capability check 只确认链路可用，不召回真实记忆，也不返回原文。

边界

本机发现默认只读。
安装 Skill 只是接入意图信号，不等于授权读取聊天正文。
capability check 不召回真实记忆，不返回原文摘录。
Windows 上更深的本机扫描可能较重；默认面板保持快速，深扫应作为显式或后台任务处理。

Assets 2

31 May 05:05

strmforge

v2026.5.31

1189c9b

Yifanchen 2026.5.31

忆凡尘 2026.5.31 继续把“本机记忆图书馆”往真实 agent 消费里推进。这一版重点不是宣称 Hermes 已经自动生成 skill，而是让安装、能力检查、自然语言纠错、Hermes 消费状态和 skill/experience 对照都变得可见、可验、可回源。

中文

主要更新

自然语言纠错入口：用户在原来的 AI 工具里说“这条记错了”“你理解偏了”“不是我的意思”时，忆凡尘会把它识别为勘误候选，而不是继续误写成长期偏好。
Agent 安装闭环：README 增加可直接发给 Codex / OpenClaw / Hermes / Claude Code 等 agent 的安装提示。安装器会尽量自动安装 Codex skill，并在 Codex CLI 可用时注册 yifanchen-zhiyi MCP。
能力检查模式收口：安装和冒烟测试继续使用 mode=capability_check，只验证 Skill / MCP / 只读状态，不触发真实召回，不返回 raw excerpts。
Hermes 学习心跳：新增只读 native learning liveness 检查，观察最近是否有 Hermes background_review、skill_manage 和 skill 文件变化，帮助判断自然学习链路是否冷掉。
Hermes 消费回执：按 Hermes 官方 MemoryProvider 生命周期补齐 queue_prefetch 和 sync_turn，记录 Hermes 是否召回、命中多少、source refs 多少，同时保持 hook 非阻塞。
Hermes 技能与经验对比升级：新增只读 skill-experience-diff dry-run，把 Hermes skill 文件与忆凡尘经验对照，产出待审 adoption / upgrade 候选。
状态账本与上下文最小单元：新增只读 State Ledger / Temporal Index 与 context_budget_unit_candidate dry-run，用来复核最新可信判断和可组合上下文，不替代 raw。
模型事实只读方向：忆凡尘读取 OpenClaw / Hermes / Codex 已有模型配置供自己判断和测试，不写回平台，不把自己做成模型中心。

明确边界

忆凡尘不直接替 Hermes 写 skill。
self-review signal receipt 只表示忆凡尘产生了唤醒信号，不等于 Hermes 已执行 background_review。
Windows 大样本实测显示当前能看到 Hermes 原生环境，但 skill_artifacts=0 时不能宣称这几天 Hermes 已自然生成新 skill。
所有 dry-run / contract / candidate 入口默认不写 raw、知意、行策、工具书、勘误或平台配置。

English

Yifanchen 2026.5.31 improves the local memory-library path for real agent use. This release does not claim that Hermes has automatically generated skills. It makes install checks, natural-language corrections, Hermes consumption state, native-learning liveness, and skill-vs-experience comparison visible and reviewable.

Highlights

Natural-language correction entry: user corrections such as "this memory is wrong" can become review-only errata candidates instead of durable preference memories.
Agent install loop: README now includes a prompt users can send directly to a local AI agent. Installers try to install the Codex skill and register the yifanchen-zhiyi MCP server when Codex CLI is available.
Capability check mode: smoke tests use mode=capability_check to verify service/tool/read-only availability without real recall or raw excerpts.
Hermes learning heartbeat: read-only native liveness reports recent background_review, skill_manage, and skill-file changes.
Hermes consumption receipts: follows the Hermes MemoryProvider lifecycle with queue_prefetch and non-blocking sync_turn receipts.
Hermes skill vs experience diff: read-only dry-run compares Hermes skill files with Yifanchen experience and creates review-only adoption / upgrade candidates.
State Ledger and Context Budget Units: contract-first dry-runs for latest trusted judgments and source-backed context units.
Read-only model facts: Yifanchen reads existing OpenClaw / Hermes / Codex model facts for its own checks and does not write them back.

Boundaries

Yifanchen does not directly write Hermes skills.
A self-review signal receipt is not proof that Hermes ran background_review.
If skill_artifacts=0, the correct claim is that Hermes native status is observable, not that new Hermes skills were generated.
Candidate and dry-run endpoints are non-writing unless a separate authorized apply path exists.

Assets 2

Releases: strmforge/memcore-cloud