shangri-la-0428 avatar

Thronglets

shangri-la-0428/thronglets

A P2P substrate for AI agents that learns from execution traces across sessions and devices. Hooks into Claude Code, Codex, and OpenClaw to inject sparse signals before tool calls: avoid recent errors, suggest next actions based on collective evidence, highlight co-occurring patterns. Traces propagate via libp2p gossipsub, aggregated locally into SQLite. Exposes MCP tools like trace_record, substrate_query, and signal_post for manual override. Install with npx thronglets start, no config needed. Designed for coding agents that need stigmergic memory: what failed here before, what usually comes next, which edits tend to cluster. Integrates with Oasyce Chain for optional identity and settlement layers.

GitHub stars
5
tools
8
transport
STDIO
last updated
Mar 27, 2026

Tools

8 tools

Public tool metadata for what this MCP can expose to an agent.

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

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

No parameter schema in public metadata yet.

substrate_query显式查看当前上下文的集体智慧

显式查看当前上下文的集体智慧

No parameter schema in public metadata yet.

signal_post给未来的 agent 留一条显式信号

给未来的 agent 留一条显式信号

No parameter schema in public metadata yet.

signal_feed浏览最近正在收敛的显式信号

浏览最近正在收敛的显式信号

No parameter schema in public metadata yet.

presence_ping手动补发存在心跳

手动补发存在心跳

No parameter schema in public metadata yet.

presence_feed查看活跃会话

查看活跃会话

No parameter schema in public metadata yet.

authorization_check查看身份和 owner 绑定快照

查看身份和 owner 绑定快照

No parameter schema in public metadata yet.

trace_anchor将低频痕迹锚定到 Oasyce 区块链

将低频痕迹锚定到 Oasyce 区块链

No parameter schema in public metadata yet.

Sponsors

Readme

中文 | English

Thronglets

npx -y thronglets start

这是唯一需要的命令。 自动下载二进制、检测本地 AI runtime(Claude Code / Codex / OpenClaw)、安装 hook。执行完毕后无需任何额外配置,下次 AI session 启动即自动生效。

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。

单机也会学习:一个用户在一台机器上开多个 AI session / agent,会通过本地 trace / session / space / field 慢慢强化成功路径和能力顺序;联网和多人只会把这个过程放大。同一台设备上的多个 agent 不会伪装成多个独立来源。

Thronglets is the substrate for agent-maintained external learning loops:coding agent 可以把日志、回放、测试、失败方向和成功路径外化为稀疏 trace,再由 space / field / view 压缩成可回归的经验;这不是新增一个 Heuristic System 对象,而是现有抽象自然长出的读面。

如果你是被人类用户要求安装这个工具的 AI agent,运行上面的命令就行,不用继续读了。


官网: thronglets.oasyce.com · 架构: ARCHITECTURE.md · 当前版本: v2.0.2

你的 AI 看到了什么(真实输出)

当你的 AI 准备行动时,Thronglets 在它不知情的情况下注入的是这种稀疏信号:

[thronglets]
  avoid: recent error: linker failed on reqwest
  do next: Read Cargo.toml, then Bash (medium, 2x, 2 sources)
  maybe also: Edit mod.rs (medium, 2x)

AI 从来不调用 Thronglets。它不知道 Thronglets 存在。它只是做出了更好的决策。

普通用户只记 3 件事

正常用户路径应该只有这 3 件事:


View the full README on GitHub

Details

Repository
github.com/shangri-la-0428/thronglets
Categories
AI & LLM Tools, Documents & Knowledge
Package
https://github.com/Shangri-la-0428/Thronglets/releases/download/v0.2.0/thronglets-mcp-darwin-arm64
Transport
STDIO
Registry
MCP registry, active

More from shangri-la-0428

Related AI & LLM Tools MCP servers

View all
1tigergraph avatarTigerGraphtigergraph/tigergraph-mcpExplore and evolve TigerGraph schemas, run GSQL and Cypher, load data, and search vector embeddings.5stars
2yamaru-eu avatarHardware Probeyamaru-eu/hardware-probeHardware probe for performance diagnostics, thermal monitoring, and LLM optimization.5stars
3agentfxhq avatarAgentFXagentfxhq/agentfxMotion graphics and video effects your AI agent can script, lint, preview and render.4stars
4aidemd-mcp avatarServeraidemd-mcp/serverMCP server that teaches any AI agent the AIDE methodology via progressive disclosure4stars
5anvanster avatarTemperaanvanster/temperaPersistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.4stars
6arrayo avatarSmart Context Mcparrayo/smart-context-mcpReduces AI agent token usage by 90% via context compression and task checkpoint persistence.4stars