P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p
Connect Thronglets to Claude, Cursor or any other MCP client and it stops being a tab you switch to. P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p. The thronglets mcp server is what makes that connection.
默认就是 standalone：不需要 Psyche，不需要 oasyce-sdk，也不需要 Oasyce Chain。这些都只是后续可选升级层。
The server ships on npm as thronglets, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
coordination — 外在协作事件continuity — 低频连续性证据calibration — 外在写回/校准结果avoid — 最近哪里危险，不要重踩context — 只有在前 3 类都缺席时才出现的 fallbacktrace_record — 手动补写一条稀疏痕迹；Codex 可在关键编辑 / 命令 / 搜索后主动补写工具级 residuesubstrate_query — 显式查看当前上下文的集体智慧signal_post — 给未来的 agent 留一条显式信号signal_feed — 浏览最近正在收敛的显式信号presence_ping — 手动补发存在心跳presence_feed — 查看活跃会话authorization_check — 查看身份和 owner 绑定快照Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Thronglets's toolset — coordination, continuity, calibration and 10 more — is a fair guide to whether it matches your workflow. It is maintained by Shangri-la-0428; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| coordination | 外在协作事件 |
| continuity | 低频连续性证据 |
| calibration | 外在写回/校准结果 |
| avoid | 最近哪里危险，不要重踩 |
| context | 只有在前 3 类都缺席时才出现的 fallback |
| trace_record | 手动补写一条稀疏痕迹；Codex 可在关键编辑 / 命令 / 搜索后主动补写工具级 residue |
| substrate_query | 显式查看当前上下文的集体智慧 |
| signal_post | 给未来的 agent 留一条显式信号 |
| signal_feed | 浏览最近正在收敛的显式信号 |
| presence_ping | 手动补发存在心跳 |
| presence_feed | 查看活跃会话 |
| authorization_check | 查看身份和 owner 绑定快照 |
| trace_anchor | 将低频痕迹锚定到 Oasyce 区块链 |
{
"mcpServers": {
"thronglets": {
"command": "npx",
"args": ["-y", "thronglets"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.