slow-stack/mneme - Open Source PR Review Scorecard

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

C-Rank Grade: D (Risky) - 30/100

External PR Merge Rate: -

Response Time: 13h

First Timer Success: -

Frequently Asked Questions

Is slow-stack/mneme welcoming to first-time open-source contributors?

slow-stack/mneme has a recorded first-timer success rate of 0.0%. Repositories ranked D typically provide actionable feedback during code reviews and actively nurture new community contributors.

How fast can I expect code review feedback on my pull request?

Maintainers in slow-stack/mneme respond to incoming external pull requests in approximately 13.3 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.

What does the 29.9 C-Rank™ score (D Tier) represent?

The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 29.9 places slow-stack/mneme in the D tier.

What is the external contributor pull request merge rate for slow-stack/mneme?

The external contributor pull request merge rate for slow-stack/mneme is 0.0%, based on public PR activity from non-core contributors.

Are there Good First Issues available in slow-stack/mneme?

slow-stack/mneme currently has 5 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".

slow-stack
slow-stack/mnemeD•Risky145
GitHub
Back to Explorer
slow-stack

slow-stack/mneme

145
InactiveD•Risky(30/100)Low Sample (<20 PRs)JavaScript

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

GitHub
Compare••
Jump to:

AI Maintainer Review Guidelines

Review Persona

Strict Architecture Gatekeeper

Warmth Score
7.2/10
Patience Score
8.0/10
Nitpick Rate
25%

Strict review standards in slow-stack/mneme. Ensure PR scope matches issue requirements closely before requesting review.

What Contributors Actually Say

Discussions in slow-stack/mneme focus heavily on practical implementation feedback, code formatting standards, and issue reproduction details.

Hidden Friction Signals

Unlinked PRs without issue context and changes that fail automated test suites face the highest review friction.

Unwritten Rules

  • •1) Keep PR scope strictly aligned with the linked issue.
  • •2) Ensure local linters pass before opening a review.
  • •3) Maintain full test coverage for modified logic.

Top PR Submission Do's

  • •Ensure code complies with the project coding style
  • •Keep PRs scoped to a single concern
  • •Include context and link to the related issue

Top PR Friction Pitfalls (Don'ts)

  • •Do not submit PRs without linking an issue
  • •Do not break existing tests without fixing them
  • •Do not mix unrelated refactors in a single PR
Response Velocity
13 hours
Standard maintainer review cycle

Average Response Latency

Tracks hours until a maintainer leaves a review, comment, or PR response.

Merge Efficiency
0.0%
Selective PR acceptance rate

External Acceptance Rate

Percentage of community pull requests successfully merged into main.

First-Timer Success
0.0%
No first-timer merges recorded in window

First PR Conversion

Rate at which developers submitting their first repository PR succeed.

Active Maintainers
3 core
Small core review team
Diagnostic Health HUD
0.0%
Merge Gauge
0.0%
1st-Timer
Community Vibe20/100

Embed C-Rank Badge

Show contributors that your repository actively reviews and merges external pull requests.

GetMerged C-Rank badge for slow-stack/mneme
[![GetMerged C-Rank](https://getmerged.abhishekco.de/api/badge/slow-stack/mneme)](https://getmerged.abhishekco.de/slow-stack/mneme?utm_source=github&utm_medium=badge)

Active Good First Issues (5)

View on GitHub

背景 记忆巩固(autoSummarize / dream)依赖 LLM 调用,属成本大头。除 #229(游标内存态 → 重启重放)外,还有两个放大成本的来源: 触发频率无上限:总结/巩固按事件触发,长会话内高频执行,缺少频率下限与会话次数上限; 无成本分级:所有待蒸馏内容一律走 LLM,没有「轻规则预判 → 才升级 LLM」的级联;高峰期(LLM 服务繁忙/配额紧张)也没有延迟到非高峰再执行的机制。 目标:减少 LLM 调用次数,且能避开高峰时段。 提案 1. 成本感知级联(论文:2608.22215 Dual-Layer Agentic Memory) 路由用「小模型先筛、大模型兜底」级联(原文 1.7B/8B,<50% 输入升级大模型)。对应到蒸馏/巩固管线: 蒸馏前先做零 LLM 预判:类型已知可跳过(constraint/preference 类已有独立类型)、去重命中(saveWithDedupe 三元组)、低价值条目(quality_score / importance 低于阈值)→

📅 Opened Sep 19, 2026💬 6 comments
Quality: 90/100Contribute

背景 #164 的论文调研(六篇)给 A1/C1/C2 提供了理论锚点,其中遗忘三篇(2604.00131 / 2601.18642 / 2604.02280)共同指向同一件事:记忆系统需要一层「受访问频率与时间调制的热度衰减」,否则要么无限膨胀(长程性能 0.45→0.05 的反面教材),要么一刀切硬删(丢掉本可复活的低频高价值记忆)。 本 issue 立项 D 批次:heat 热度衰减,按刻意保守的路径落地:opt-in → 真实数据 → 对照论文找偏差。 理论依据(三篇) Oblivion(2604.00131,EMNLP 2026):遗忘 = 降低可及性而非删除——经验随时间变得不易获取,但可被强化或情境线索重新激活;且「帮过忙的记忆应被强化」。与本项目 archived/forgotten 两列的既有设计同构,本 issue 是它的量化延伸。 FadeMem(2601.18642):不同记忆应有不同衰减率,由语义相关性、访问频率、时间模式三者调制;存储可缩减 45%。幂

📅 Opened Sep 17, 2026💬 11 comments
Quality: 90/100Contribute

背景 对面板前端做了第一遍 WCAG 导向审计。骨架及格:按钮/输入框基本都有 aria-label、装饰图标统一 aria-hidden、星级评分有 role="img"+数值标签、会话列表用 tree/treeitem 语义、大弹层有 role="region"+aria-label+Esc 关闭、开关控件有 aria-checked/aria-expanded。 系统性缺口(按 WCAG 四原则): 缺口 位置 原则 状态变化无播报 保存成功/失败、队列刷新、resolve 完成——纯视觉 span,无 aria-live 可感知 操作缺上下文 冲突队列「保留 A」读屏只听到「保留 A」,不知是哪一对 可理解 状态卡无语义 「最近巩固/待确认冲突」是纯 div,不可聚焦、无 heading 层级 可操作 弹层焦点管理 记忆库 sheet 开时不移焦、无 focus trap、关闭不还焦 可操作 图表无替代 ego 关系图 SVG 无可访问名称与数据摘要 可感知 对比度未审计 三级灰字 11px 在浅色主题下疑似低于 4.5:1 可感知

📅 Opened Sep 15, 2026💬 1 comment
Quality: 90/100Contribute

临时有个无关的想法测试,但又不想进入记忆如何做?—— 类似浏览器【无痕浏览】类似逻辑 A 在dsh-market 停用插件? B 正常使用后,另起对话memory_delete? 希望可以在对话栏或右上角直接有个无痕选项,参考ChatGPT

📅 Opened Sep 2, 2026💬 4 comments
Quality: 75/100Contribute

图谱增强:把"图"从展示变成检索信号 来自 discussion #22(@heptaspirit 提案 + 多轮合议后收敛)的追踪 issue。 核心理念:mneme 的实体三表 + ego graph 前端已经「画」出图了,但缺的是「激活」——把图从展示升级为运行时检索信号,让 LLM 每次推理被动受益,无需主动去看。这顺着 0.6.x Wiki-Link / Tag 加权召回的方向自然延伸,不另起炉灶。 排期:v0.7(workspace + 兴趣漂移 heat)地基打牢后再上(v0.8)。图谱桥接的三个接入点(TYPE_DECAY、touch、sleep)依赖 heat 成熟后的信号质量,先跑稳 v0.7 更自洽。 按合议拆四块,均为模块级设计而非交互待续: 1️⃣ 锚定层(Activation Anchoring) 多路起点:精确名 → Tag 桥接 → 向量 三路激活 多路命中累加前需按通路先做 min-max(或 rank)归一化再累加(精确名是布尔 1.0、Tag 是计数、向量是 cos 相似度,尺度不同,直接

📅 Opened Aug 22, 2026💬 5 comments
Quality: 90/100Contribute
Looking for more JavaScript beginner tasks?Explore JavaScript GFI

Contributor Community Vibe Feedback

Rate what actually matters after opening a pull request here.

Have you contributed to this repo?

Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.

3 ratings required
Maintainer helpfulness
Review speed
Beginner friendliness

Contributor Compatibility & Review Speed Analysis for slow-stack/mneme

When evaluating whether to contribute to slow-stack/mneme, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.

Currently, maintainers of slow-stack/mneme acknowledge new external contributions in approximately 13 hours. Out of all submitted pull requests from non-core authors in the last 180-day window, 0.0% were successfully merged into the primary branch.

Frequently Asked Questions - Contributing to slow-stack/mneme

01

Is slow-stack/mneme welcoming to first-time open-source contributors?

slow-stack/mneme has a recorded first-timer success rate of 0.0%. Repositories ranked Risky typically provide actionable feedback during code reviews and actively nurture new community contributors.

02

How fast can I expect code review feedback on my pull request?

The initial maintainer response time averages ~13 hours. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.

03

What does the 29.9 C-Rank™ score represent?

The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 29.9 places slow-stack/mneme in the Risky tier.

04

What is the external contributor pull request merge rate for slow-stack/mneme?

The external pull request merge rate is 0.0%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.

05

Are there beginner Good First Issues open in slow-stack/mneme?

Yes, slow-stack/mneme currently has 5 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.

GetMerged C-Rank™ Indexing Standard

All metrics displayed for slow-stack/mneme are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.