S
syncable-dev/memtrace-public
Structural memory graph, with no model call
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"syncable-dev-memtrace-public": {
"command": "npx",
"args": ["-y", "@deepseek-ai/dsh"]
}
}
}解析自我们于 2026-11-04 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"syncable-dev-memtrace-public": {
"command": "npx",
"args": ["-y", "@deepseek-ai/dsh"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio syncable-dev-memtrace-public -- npx -y @deepseek-ai/dsh
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx -y @deepseek-ai/dsh
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx -y @deepseek-ai/dsh。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
Your agents deserve structural memory .
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Official Memtrace by Syncable. Start at memtrace.io/docs. The official package is memtrace on npm, and the public repository is syncable-dev/memtrace-public. Other projects with the same name are unrelated. Compare memtrace --version with the Stable and Nightly release history.
For installation support, open an issue in the official public repository with your operating system, Memtrace version and exact error. Remove credentials and private source from shared logs. The Syncable team maintains this package and its support channels.
📖 Docs ·
⭐ Star us ·
memtrace.io ·
npm ·
Discord
Memtrace turns your codebase into a live knowledge graph that AI coding agents can query in milliseconds — every function, class, call edge, and version, across every session, without re-reading files or breaking things they can't see.
Get your fleet on shared structural memory in under 90 seconds.
Structural · zero LLM calls · Bi-temporal · time-travel queries · Replay-aware · zero blind refactors
## DeepSeek Harness
Memtrace runs as a DeepSeek Harness plugin. Install Harness first (npm install -g @deepseek-ai/dsh — that is the dsh command), then add Memtrace:
sh
npx -y @deepseek-ai/dsh plugin --profile web add github:syncable-dev/dsh-plugin-memtrace
Then ask the agent to index the workspace and pull blast radius, evolution, or an architecture briefing. Details: syncable-dev/dsh-plugin-memtrace.
## What it does
Three things, every release.
🧭 Run a fleet of coding agents on the same repo without merge hell.
Each agent reads the same call graph, sees the same blast radius, inherits the same temporal history. No collisions. No stale context.
🔁 Replay any refactor with full causal awareness.
Agents see exactly what depends on what, and what changed when. No more "I refactored a function and 14 tests broke that nobody saw."
⚡ Index a 50k-file repo in under 90 seconds.
Rust + Tree-sitter, $0 in API costs, 20+ languages plus framework-aware scanners (Vapor, Lapis, Kong, GitHub Actions, Terraform, RLS policies, …), fully local. Your code never leaves your machine.
🆕 LeanCTX Native — compressed reads, smart trees, and a value ledger.
Four new compression modes on getsourcewindow, single-call directory maps, real-time token-savings dashboard, and an opt-in adaptive learner that beats the static table by ~14%. Full breakdown: docs/leanctx-native.md. Available in v0.3.57+.
https://github.com/user-attachments/assets/e7d6a1e9-c912-4e65-a421-bd0256dffa5a
## Numbers
| Operation | Memtrace | Best alternative | Δ |
| Index 1,500 files | 1.5s · $0 | Mem0: 31 min · $10–50 | ~1,200× faster |
| Exact symbol query (acc@1, lat) | 96.6% · 0.07 ms | GitNexus: 97.0% · 8.95 ms | 128× lower latency |
| Graph callers recall (Django) | 81.6% | GitNexus: 5.3% | 15.4× |
| Incremental re-index p95 | 42.5 ms | CodeGrapher: 613.7 ms | 14.4× |
| Hybrid acc@1 (Django, 3K cases) | 73.9% | GitNexus: 38.6% | 1.91× |
| PR code-review F1 (50 PRs) | 0.7268 | Cubic v2: 0.6077 | +19.60% |
| RSS / process | 26 MB | ChromaDB: 1,060 MB | 41× tighter |
| Languages | 16+ (Tree-sitter) | varies | — |
For installation support, open an issue in the official public repository with your operating system, Memtrace version and exact error. Remove credentials and private source from shared logs. The Syncable team maintains this package and its support channels.
📖 Docs ·
⭐ Star us ·
memtrace.io ·
npm ·
Discord
Memtrace turns your codebase into a live knowledge graph that AI coding agents can query in milliseconds — every function, class, call edge, and version, across every session, without re-reading files or breaking things they can't see.
Get your fleet on shared structural memory in under 90 seconds.
Structural · zero LLM calls · Bi-temporal · time-travel queries · Replay-aware · zero blind refactors
## DeepSeek Harness
Memtrace runs as a DeepSeek Harness plugin. Install Harness first (npm install -g @deepseek-ai/dsh — that is the dsh command), then add Memtrace:
sh
npx -y @deepseek-ai/dsh plugin --profile web add github:syncable-dev/dsh-plugin-memtrace
Then ask the agent to index the workspace and pull blast radius, evolution, or an architecture briefing. Details: syncable-dev/dsh-plugin-memtrace.
## What it does
Three things, every release.
🧭 Run a fleet of coding agents on the same repo without merge hell.
Each agent reads the same call graph, sees the same blast radius, inherits the same temporal history. No collisions. No stale context.
🔁 Replay any refactor with full causal awareness.
Agents see exactly what depends on what, and what changed when. No more "I refactored a function and 14 tests broke that nobody saw."
⚡ Index a 50k-file repo in under 90 seconds.
Rust + Tree-sitter, $0 in API costs, 20+ languages plus framework-aware scanners (Vapor, Lapis, Kong, GitHub Actions, Terraform, RLS policies, …), fully local. Your code never leaves your machine.
🆕 LeanCTX Native — compressed reads, smart trees, and a value ledger.
Four new compression modes on getsourcewindow, single-call directory maps, real-time token-savings dashboard, and an opt-in adaptive learner that beats the static table by ~14%. Full breakdown: docs/leanctx-native.md. Available in v0.3.57+.
https://github.com/user-attachments/assets/e7d6a1e9-c912-4e65-a421-bd0256dffa5a
## Numbers
| Operation | Memtrace | Best alternative | Δ |
| Index 1,500 files | 1.5s · $0 | Mem0: 31 min · $10–50 | ~1,200× faster |
| Exact symbol query (acc@1, lat) | 96.6% · 0.07 ms | GitNexus: 97.0% · 8.95 ms | 128× lower latency |
| Graph callers recall (Django) | 81.6% | GitNexus: 5.3% | 15.4× |
| Incremental re-index p95 | 42.5 ms | CodeGrapher: 613.7 ms | 14.4× |
| Hybrid acc@1 (Django, 3K cases) | 73.9% | GitNexus: 38.6% | 1.91× |
| PR code-review F1 (50 PRs) | 0.7268 | Cubic v2: 0.6077 | +19.60% |
| RSS / process | 26 MB | ChromaDB: 1,060 MB | 41× tighter |
| Languages | 16+ (Tree-sitter) | varies | — |
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/syncable-dev-memtrace-public/)
- 来源
- awesome · https://github.com/syncable-dev/memtrace-public
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。