JianFeeeee 28b78e1703 docs: 按 humanizer-zh 规则再改 README 开头
上一版开头四句被指出仍有 AI 味。拆开看问题在:

  · 四句长度接近、每句都是金句,没有一句是普通陈述
  · "说人话:"是元话语,AI 特有的"宣布要通俗化"动作
  · "白天聊过的事,晚上还记得" + "三周前说过的偏好,不会因为上下文窗口
    滚动就丢了" —— 严格对仗,一个口语一个技术解释混在一起
  · "插件崩了它不倒,模型换了它不改" —— 两组四字对仗

用 humanizer-zh 的规则过了一遍,命中三条:

1. **§A.1 不是 X,而是 Y** —— "跟直接调 API 的区别在于它把长期当成了
   基本需求,而不是事后加个向量库",后半句是假想敌。删掉后逻辑没损失。
2. **§A.2 单句收尾** —— "这个仓库从 2026 年 7 月开始开发,现在 1.4.0,
   一千多个提交" 独立成段作收尾。并入上一段。
3. **§A.5 与假想敌辩论** —— 小标题 "它跟别的 Agent 框架哪里不一样"。
   改成 "几个设计决定"。

另外自重写:

- 开头从四句金句改成一句陈述 + 一句具体 + 一段解释。不是排比。
- "## 能力" 从五项 "**类别**:三词·三词·三词" 改成有详有略的散文
  (五项同模板是最密集的 AI 指纹之一)
- "## 几个设计决定" 从五条 "**X,不是 Y。**" 改成一段段长短不一的叙述,
  其中 3 条原本是同一个句式
- 删掉与开头重复的记忆下沉描述

英文版同步,不是直译:`What makes it different` → `Design decisions`,
开头去掉同样的假想敌与收尾句。

## 修掉一处我自己写出来的事实错误

上一版我写了 "微信和 QQ 的文件、语音消息能收发"。核查后:仓库里没有微信
插件,只有 clawhubadapter 注释里提到微信作为通用通道的例子。已删掉微信。

## 验证

- 两版死链检查为空
- 代码块配对(14/14)
- 9 个二级标题中英对齐
2026-10-31 11:15:33 +08:00

⚠️ AI-Assisted Programming Notice: Parts of this project's code, documentation, and commit history were generated or modified with AI assistance. Key changes have been human-reviewed, but please evaluate and verify before use.

HologramAgent

中文: README.md

HologramAgent is an agent kernel that runs on your own hardware. Connect it to QQ, a web UI, your shell, your files, a browser, and it works in all of them.

Memory sinks: the last few turns stay in context, older ones become documents, oldest get distilled into triples in a graph database. That is why it can run for months without stuffing the entire history into every prompt.

./build/homed -data /tmp/ha      # start the kernel
./build/waiter                    # talk to it

You need a Linux box. API keys go in through the web UI and live in local SQLite. Development started July 2026; currently 1.4.0.


Design decisions

Plugins run in separate processes. One panics and the kernel stays up; it restarts on its own. Drop in a new plugin.bin and it's live. The earlier version used C shared libraries, where dlclose silently no-ops under DF_1_NODELETE, cgo timeouts leave threads alive, and one plugin panic dragged homed down with it. That is why it was rewritten as subprocesses plus shared memory.

The kernel itself makes no HTTP calls and reads no files. Everything that touches the outside world lives in plugins: the web UI, QQ, command execution, web search, the browser. Not for tidiness. It means you can swap the entire interaction layer without touching the kernel.

Inside one QQ plugin, a group owner and a random member can hold different permissions. Instructions arriving from another agent don't get written into your memory, though they can trigger recall. The kernel's security module makes those calls; plugins only declare.

Memory is partitioned by scene, not by session. Move from work talk to personal talk and it splits context by channel, conversation partner, tools used, and time of day. When a scene recurs, last time's conclusions come back, including the ones it got wrong.

What it can do

Places it talks: web UI, shell, QQ groups and DMs, other agents over A2A, and an ACP server inside your IDE. It can look at images, video, voice, and web pages, and it can drive a real Chrome.

For getting things done it reads and writes files, runs commands, writes code, and handles calendars, notes, RSS, and music. QQ files and voice messages go both ways.

Behind that sit three memory layers plus a graph database plus a knowledge base, recalled by scene. When new work arrives mid-task it enters a scheduler; if the user pushes back it can jump the queue, and interrupted work saves its state and resumes. Long jobs can be handed to sub-agents so they don't block the line you're talking on.

28 built-in plugins, 89 model-callable tools. External plugins live one-per-repo at github.com/HologramAgent.

How it works

homed  (kernel: LLM orchestration + memory + retrieval)
   ↑ PluginSDK
plugins  (web UI / QQ / CLI / files / network / all IO)

Three channels between kernel and plugins: JSON-RPC over stdio for control, shared memory for bulk data, an event ring for notifications. Large objects aren't serialized, so there's nothing to copy twice.

Incoming messages hit a scheduler first, not the model. This exists for the case where work is already in flight and a new instruction arrives: queued work and interruptions are separate classes, interruptions carry four urgency levels, a higher level preempts a lower one and the preempted work saves its state to resume later. Same level waits.

Below that sits a seven-stage pipeline where the model can call tools in a loop. Multiple tool calls in one turn are serial by default unless a tool declares itself concurrency-safe. One undeclared tool in a batch drops the whole batch back to serial.

Quick Start

make build build-cli
./build/homed -data /tmp/ha
# Interactive mode
./build/waiter

# Or a single message
echo "Hi, remember I like coffee" | ./build/waiter

Daemon mode

waiter can also run resident, holding a persistent connection to homed and waiting for a TUI instance to attach. Useful when the agent needs to reach you proactively or keep a device bridge alive.

# Resident (connects to ~/.homeagent/cli.sock by default)
./build/waiter --daemon

# Custom socket
./build/waiter --socket /path/to/cli.sock --daemon

# Any TUI or one-shot instance then attaches to the running daemon instead of homed directly
./build/waiter

The daemon listens on ~/.homeagent/waiter.sock, replays the last 256 lines of conversation to new clients, survives disconnects, reconnects to homed on its own, and keeps the device bridge alive when device_gateway / device_token are configured.

Set API keys in the web UI at http://localhost:8080; they persist in SQLite.

Code Structure

cmd/homed/          Daemon entry, assembles all subsystems
cmd/waiter/         CLI client (Unix socket)
internal/
├── agent/core/     Agent core: input scheduler (2 classes + 4 levels), event loop, LLM tool loop, 7-stage pipeline, residents
├── agent/api/      LLM Provider (Lua adapter layer: provider.go drives the vm)
├── memory/         Three-layer memory: Graph(SQLite) / Document(JSON+TF-IDF) / Text(JSONL) + StaticEmbedder(pretrained word embedding/TF-IDF fallback) + CleanTemplateText(de-template)
├── knowledge/      Knowledge base (filesystem + TF-IDF)
├── plugin/         Plugin registry + subprocess loader (stdio RPC + shared memory segment + event ring)
├── plugins/        built-in plugins (webui / cli / files / cmd / mcp / kbtree / seq / skillmgr …)
├── sdk/            PluginSDK (Tool/Stage/Event three channels)
├── config/         SQLite config center
├── events/         Event bus
└── internal/lua/adapters/   10 LLM protocol adapter scripts
External plugin development: see the [hologramagentsdk](https://github.com/JianFeeeee/hologramagentsdk)
repo with the `hmapdev` toolchain. Each plugin has its own repo under
[github.com/HologramAgent](https://github.com/HologramAgent).

Documentation

Online docs:

In-repo docs (versioned with the code):

Downloads

Releases ship three variants:

Variant Contents For
full homed + waiter + desktop GUI + systemd unit Single-machine, everything
server homed + waiter + systemd unit Servers (no desktop environment)
client waiter + desktop GUI Connecting to a remote HologramAgent
  • Linux: .deb (amd64/arm64), .rpm (x86_64), .tar.gz
  • Windows: HologramAgent_v1.2.0_{Full,Server,Client}_win64.exe (NSIS installer, includes the AGPL license page). Since v1.2.0 homed no longer supports native Windows (it relies on fd inheritance and in-segment offset dereferencing), so the installer bootstraps WSL2 and installs the Linux packages inside the distribution the same way a Linux host would.
  • Portable: homeagent-bin-<os>_<arch>.tar.gz (homed/waiter/initconfig)
  • Verification: SHA256SUMS

The macOS homed requires a native macOS build (CGO + sqlite3), so release packages ship only waiter/initconfig.

Build

make build build-cli    # Build daemon + CLI
make test               # go test ./...
make install            # Install to system

Dependencies: Go 1.25+, CGo (go-sqlite3), Linux.

homed requires Linux (it relies on fd inheritance and intra-segment offset dereferencing of the shared memory region; see cmd/homed/platform_windows.go). On Windows only waiter.exe is built and homed runs under WSL2 (see Downloads). macOS can build waiter/initconfig; homed must be built on native macOS.

License

This project is released under the GNU Affero General Public License, version 3 (AGPL-3.0-only) — see LICENSE.

This is the strongest copyleft in the GPL family: besides shipping the complete corresponding source when you distribute the software, you must also offer the source to users who interact with it over a network (§13, Remote Network Interaction). Anyone running a modified HologramAgent as a network service therefore has to make the modified source available to that service's users.

Plugins are statically linked against this project through the public hologramagentsdk (the SDK source ends up inside the plugin binary), but that repository is released under MIT. That is a permissive license, so code received under it does not inherit this project's AGPL. External plugins are therefore not derivative works of this project: authors pick their own license (closed-source, commercial or private included), with no same-license obligation and no §13 network clause. The safety and vitality of the third-party plugin ecosystem rest on this.

The boundary is clean: AGPL covers the kernel and the bundled plugins (homed, internal/, the 13 built-in plugins under internal/plugins/); MIT covers the public SDK (sdk/, whose go.mod has zero external dependencies and imports only the Go standard library, never any kernel code). Process isolation is beside the point here. What decides the license is the linked SDK code itself, and that code is MIT.

Third-party components shipped with the packages

Component License Location
Chinese-CLIP ViT-B/16 (ONNX artifacts) Apache-2.0 /usr/lib/hologram/models/chinese-clip-vit-b16-onnx/
ONNX Runtime (libonnxruntime.so) MIT /usr/lib/hologram/onnxruntime/
jieba dictionary (embedded in the binary) MIT internal/memory/jiebadict/
Go dependencies (go-sqlite3, gojieba, bubbletea, …) MIT / BSD-3 / Apache-2.0 permissive, AGPL-3.0-compatible

These components keep their own licenses and are not relicensed by this project. Full texts are shipped in /usr/share/doc/hologramagent/licenses/, and the package metadata declares this package as AGPL-3.0-only.

Description
No description provided
Readme AGPL-3.0 188 MiB
Languages
Go 79.5%
JavaScript 10%
Python 3.1%
HTML 1.8%
CSS 1.5%
Other 4%