gigabrain

MCP数据服务

提供方 legendaryvibecoder · 包名 gigabrain

数据服务 stdio · 本地进程 未标注 社区 / 第三方 Claude DesktopCursorClineClaude Code
查看接入方式

Local-first memory layer for OpenClaw, Codex App, and Codex CLI: capture, recall, dedupe, and native sync.

一句话选型结论

按资料字段整理

gigabrain 属于数据服务类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude Desktop、Cursor、Cline 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类数据服务 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 189 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

数据服务
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

gigabrainai-agentai-tools

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
npx -y gigabrain

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
数据库查询

用自然语言查库、取数,不用手写 SQL。

数据同步与清洗

把多来源数据拉到一处做整理。

报表取数

按口径快速拉出统计结果。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Cursor、Cline,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在数据服务场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
gigabrain当前 未标注 stdio · 本地进程 本地部署 有 2026-04-10
Memory 9d25f64e 9 未标注 未标注 无 2026-05-17
Getzep MCP 9 stdio · 本地进程 本地部署 有 2026-05-17
anything-llm 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Prisma MCP Server 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Astr Bot 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

数据服务
字段来自项目仓库与公开索引,中文说明由本站标注
提供方legendaryvibecoder上游标注的维护方 legendaryvibecoder
分类数据服务本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时gigabrain · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-04-10上游最后核验时间

详细介绍

18.6 KB
来自项目仓库与上游目录的原文,未做删改

Gigabrain

One shared memory for your AI assistants, under your control.

Configuration ·
Changelog ·
Contributing ·
Security ·
Discussions


Why this exists

Each AI assistant keeps a separate memory of your work, so one assistant can miss a decision that you made with another. You then explain the same facts again. Old information can also guide new work.

When a Codex session moves an app from Stripe to Paddle, Claude Code can still hold the old Stripe record. A later billing change can then use Stripe code.

What Gigabrain does

Gigabrain keeps one local record for supported AI assistants.

  • Read supported memory files. Gigabrain adds the facts that it finds to the shared record. It keeps each source file unchanged.
  • Keep the source and dates. You can check where a fact came from and when it entered the store.
  • Show conflicts. Gigabrain applies documented rules when two records disagree about the same fact. It gives more weight to strong support and recent evidence, then keeps the decision history.
  • Store data on your computer. The default memory store stays on your computer. You choose each optional connection.

Gigabrain works beside each assistant's built-in memory as a shared record that you can inspect or correct. Use an export when you want to move it.

Quickstart

These commands install the package, connect a project, check the setup, and write an audit report. All supported imports stay read-only.```bash
npm install @legendaryvibecoder/gigabrain
npx gigabrainctl init --project-root /path/to/repo
npx gigabrainctl doctor --config ~/.gigabrain/config.json --target both
npx gigabrainctl handoff --config ~/.gigabrain/config.json \
--output-dir ./gigabrain-memory-audit


`init` writes the configuration to `~/.gigabrain/config.json`. The other commands and assistant setups use this file. Read the audit report before you enable a feature from the configuration guide.

Open the guide for your assistant: Codex · Claude Code · OpenClaw.

## Limits and safeguards

- Memories in ChatGPT, Claude.ai, Gemini, and Copilot stay in those accounts. Gigabrain can import a supported file after you export it.
- A laptop and a desktop use separate stores. Use a reviewed bundle or a configured connection when you want to move data between them. See the sharing guide.
- Gigabrain ranks evidence with documented rules and lets you inspect or change the result.
- The local store can contain sensitive data. Protect the computer and review every export before you move it. Read the privacy guide.

The configuration guide describes every setting and optional feature.

---

## Technical reference

## Core behavior

- **Shared recall with clear scope:** Codex, Claude Code, Hermes, and OpenClaw can share project facts and stable user preferences when they use the same Gigabrain configuration.
- **Source record:** Each claim keeps its source host, path, evidence, time data, status, and trust tier.
- **Conflict rules:** Gigabrain checks source trust first. It then checks independent support. Recency resolves the final tie. An append-only record keeps each decision.
- **Time model:** A fact can have a content time and a validity window. Normal recall skips expired or superseded rows.
- **Checkpoint control plane:** A checkpoint is an immutable episode, not automatically a durable fact. Durable candidates stay as reviewable claims until an authorized decision promotes them.
- **Audit tools:** Optional tools can recover transcripts, filter secret risks, manage review queues, write Handoff Records, and build a memory wiki.
- **Local operation:** The default setup runs locally, where SQLite stores the data and lexical search finds it. Policy checks control each result. A cloud memory service is optional.

## Processing flow

1. **Ingest:** Add supported local memory files, explicit checkpoints, and manual exports to a local event store.
2. **Build the current view:** Write the latest state to SQLite and keep its source and validity data.
3. **Resolve conflicts:** Apply reviewable rules to duplicate or conflicting claims. A queue holds uncertain changes that can remove data.
4. **Serve recall:** Use lexical search through MCP, the CLI, or authenticated HTTP. Loopback Ollama embeddings are optional.```
   Codex   Claude   Cursor   OpenClaw   Hermes   manual exports
     └────────┴────────┴─────────┴─────────┴──────────────┘
                              │   (supported imports are read-only)
                              ▼
                    ┌────────────────────┐
                    │      Gigabrain     │   capture · resolve · recall
                    │ arbitration ledger │   MCP · CLI · HTTP
                    └─────────┬──────────┘
                              │  recall with sources after conflict checks
                              ▼
                  any configured agent uses gigabrain_recall

Release highlights

What it means for you
Checkpoint control plane Checkpoints become immutable episodes. Durable candidates remain reviewable proposals, and decisions can produce policy-versioned receipts.
Remote MCP beta A self-hosted Streamable HTTP connector can serve approved tools to Claude and ChatGPT. It verifies OAuth JWTs, enforces exact memory scopes, redacts local paths, and enables no writes by default.
Answer-focused recall Recall selects evidence that can answer questions about duration, completion, or certification. Unrelated preferences rank lower.
Conflict checks during import Gigabrain checks conflicts during import and during maintenance. Risky changes wait for review.
Local host imports Gigabrain can inspect and import supported local data from Codex, Claude Code, Hermes, Cursor, and Windsurf. Each imported fact keeps its source.
Portable handoff Export and import bundles use integrity hashes. Data moves only when you run the export and import commands.
Privacy check for releases The release check scans Git files and the npm package contents. It blocks unknown binary files and redacts each finding.
Secured local console Runtime tests cover authentication, scope rules, path limits, security headers, and dependency checks.

The cloud inbox, transcript recovery, Git wiki, Obsidian reference set, remote bridge, and URL importer start disabled. Read the configuration guide and privacy model before you add a data source or network provider.

Supported clients

Host surface Install What Gigabrain handles
OpenClaw openclaw plugins install Provides an optional memory slot, registry, recall, conflict checks, and maintenance
Codex desktop, CLI, or IDE npm install and setup Provides explicit, on-demand project and user recall through MCP tools.
Claude Code npm install and setup Uses the same standalone store when its configuration matches. Automatic prelude and teardown hooks remain opt-in.
Claude Desktop claude:desktop:bundle Uses the same MCP-backed memory store and tools as Claude Code
Claude web or ChatGPT web Self-hosted remote MCP Connects to an OAuth-protected, read-only-by-default /mcp endpoint. See the remote setup guide.
Hermes Agent gigabrain-hermes-setup Adds MCP tools and imports local Hermes memory files in read-only mode
Cursor or Windsurf gigabrainctl sync-hosts Imports local project rules and memory in read-only mode
Cloud assistants Explicit file import Parses supported ChatGPT, Gemini, or Copilot files after you export them

Privacy model

  • Gigabrain keeps the standalone SQLite store under ~/.gigabrain/. A hosted Gigabrain service is optional.
  • The default LLM provider setting is none. Optional semantic embeddings go only to a loopback Ollama endpoint.
  • Gigabrain extracts raw transcripts through a local provider or a local hook that you add. A cloud audit excludes rows that can contain credentials. Before data leaves the computer, Gigabrain masks supported PII patterns and removes the original scope.
  • Native host stores use read-only import. To add a supported memory file from a cloud account, export it first.
  • Enable each network feature before use. The remote bridge is opt-in. For URL import, the Python console requires an exact host allowlist and an explicit setting.
  • Remote MCP is an explicit self-hosted service. It reads the configured Gigabrain store while running; it does not upload or replicate that store by itself, and writes stay disabled unless separately enabled and authorized.
  • The release gate scans all publishable files, the npm package contents, Git data, and GitHub data. Its output hides matched values.

The SQLite store and generated Markdown can contain sensitive memory. Protect the host account, use disk encryption, restrict file permissions, and review each export before you move it. Read the full boundary in the privacy model.

Safe defaults

  • Recall is observational: it never imports files, rebuilds projections, or runs maintenance.
  • Automatic session-prelude injection is off. Agents recall only when a task needs prior decisions or an explicit preference.
  • An exact project scope does not search the personal store or profile rows.
  • target: "both" is for questions that intentionally span project and personal context.
  • Checkpoints require completed substantive work and are bounded to one record per stable session_id.
  • Host sync, maintenance, session hooks, and other write paths stay explicit.

How it works under the hood```

Conversation (OpenClaw / Codex / Claude Code / Claude Desktop)
│
▼
┌──────────────────────────────────┐
│ Gigabrain │
│ (memory layer + MCP server) │
├──────────────────────────────────┤
│ Capture ─► Policy ─► Registry │
│ Recall ◄─ Orchestrator │
│ Host Sync ◄─ Codex/Claude/etc. │ ← read-only adapters
│ Transcript Harvester ◄─ logs │ ← optional recovery
│ Arbiter (trust>support>recency)│ ← at ingest + nightly
│ World Model (entities/beliefs) │
│ Git Wiki ◄─► reviewed edits │ ← optional, high trust
└──────────────┬───────────────────┘
│
SQLite + FTS5 + optional local embeddings


- **Capture:** Explicit `remember` calls, host imports, and optional transcript recovery become append-only events. Checkpoints additionally create immutable episodes; durable candidates become reviewable claims rather than silent memories.
- **Recall:** FTS5 and BM25 search text directly. When local embeddings are available, Gigabrain combines lexical and dense rankings. Cross-store results use reciprocal-rank fusion, then exact scope, relevance, status, source, and conflict rules.
- **Conflict review:** The world model records competing beliefs for each claim slot and ranks them by trust tier. It next checks independent support. Recency resolves any remaining tie. Clock-skew and source-independence checks protect the result.
- **Audit reports:** Static Markdown, HTML, and JSON reports show readiness, source coverage, conflicts, stale rows, and omitted secret risks.

The published evidence comes from a small development regression set. The benchmark evidence page describes its limits.

## Why use it when native memory exists?

Several assistants provide useful native memory. Codex has local memories, Claude Code has auto memory, Cursor has project memories, and OpenClaw has hybrid memory search. Each product documents a different scope. Some stores stay on one machine or inside one product.

Gigabrain keeps source data across products and separates project facts from user preferences. Fixed rules resolve conflicts. Validity dates control when each fact applies. You can move the record with an export and audit the protocol independently. The detailed comparison maps these features to native memory.

## MCP tools

`gigabrain_recall` · `gigabrain_remember` · `gigabrain_checkpoint` · `gigabrain_checkpoint_list` · `gigabrain_checkpoint_get` · `gigabrain_claim_propose` · `gigabrain_claim_review` · `gigabrain_claim_decide` · `gigabrain_receipt_write` · `gigabrain_receipt_get` · `gigabrain_provenance` · `gigabrain_recent` · `gigabrain_sources` · `gigabrain_sync_status` · `gigabrain_export_brief` · `gigabrain_entity` · `gigabrain_relationships` · `gigabrain_contradictions` · `gigabrain_arbitrate` · `gigabrain_adjudications` · `gigabrain_beliefs_as_of` · `gigabrain_review_queue` · `gigabrain_doctor`

Local and remote surfaces are intentionally asymmetric: broad writes stay local,
while remote MCP exposes a reviewed read allowlist and narrow opt-in writes. See
the checkpoint control plane, remote connector
guide, and coverage matrix.

## CLI```bash
npx gigabrainctl init                       # Find and connect installed agents
npx gigabrainctl handoff --output-dir ./out # Write a memory audit and safe Handoff Records
npx gigabrainctl nightly                    # Run the nightly import, conflict check, and audit
npx gigabrainctl doctor                     # Check system health
npx gigabrainctl inventory                  # Show memory statistics
npx gigabrainctl review contradictions      # Review conflicts across agents
npx gigabrainctl sync-hosts --host codex,claude_code  # Import a host again
npx gigabrainctl vault sync|status          # Use the read-only Obsidian reference set
npx gigabrainctl transcript sync|status     # Recover raw local transcripts
npx gigabrainctl wiki project|reconcile|status  # Manage the Git versioned memory wiki
npx gigabrainctl watch --install-hook --kind=session  # Optional opt-in teardown checkpoint hook
npx gigabrainctl export-bundle --out ./memory-bundle.json
npx gigabrainctl import-bundle --in ./memory-bundle.json
npx gigabrainctl migrate legacy-drop --dry-run  # Preview legacy cleanup

All commands accept --config and are also available as npm run scripts.

HTTP endpoints

Method Path Auth Description
GET /gb No Service landing response
GET /gb/health No Health check
POST /gb/bench/recall Token Recall result plus benchmark diagnostics
POST /gb/control/apply Token Mutating: apply an explicit memory action
GET /gb/entities Token List world-model entities
GET /gb/entities/:id Token Entity detail (/gb/entities/detail?id=... is also accepted)
GET /gb/beliefs Token List beliefs
GET /gb/episodes Token List episodes
GET /gb/open-loops Token List open loops
GET /gb/contradictions Token List contradiction-review items
GET /gb/adjudications Token List arbitration verdicts
GET /gb/beliefs-as-of Token Bi-temporal belief snapshot
GET /gb/review-queue Token Read-only review queue
GET /gb/relationships Token Relationship graph for an entity
GET /gb/evolution Token Entity evolution by claim slot
GET /gb/memory/:id/timeline Token Event timeline for a memory
POST /gb/recall Token Memory recall for a query
POST /gb/recall/explain Token Recall diagnostics and routing explanation
POST /gb/suggestions Token Mutating: validate and ingest structured suggestions

/gb and /gb/health return service status only. Every data route accepts X-GB-Token, X-OpenClaw-Token, or a Bearer token. A route denies access when its configuration has no token. The dangerous development setting GB_ALLOW_NO_AUTH=1 can bypass Node route checks only when no token is configured. It prints a warning. Use this setting only in a disposable loopback environment. OpenClaw gateway authentication can add an outer layer.

Key subsystems

Subsystem Docs
Checkpoint / claim / receipt control plane docs/checkpoint-control-plane.md
Remote MCP for Claude and ChatGPT docs/setup-remote-mcp.md
Memory Audit + Handoff Records docs/handoff-record.md
Surface coverage matrix (MCP / CLI / HTTP) docs/coverage-matrix.md
Configuration reference docs/configuration.md
Privacy and trust boundaries docs/public/privacy-model.md
Public security review docs/public/security-review.md
Native-memory comparison docs/public/why-gigabrain.md
Benchmark evidence docs/public/benchmark-evidence.md
Recall pipeline docs/recall.md
Nightly maintenance docs/maintenance.md
Obsidian vault reference docs/obsidian.md

Prerequisites

  • Node.js 22.18.0 or later. Gigabrain uses node:sqlite and built-in TypeScript type stripping.
  • Ollama is optional. It provides local fact extraction and semantic search.
  • OpenClaw 2026.2.15 or later is required for the plugin path.
  • Python 3.10 or later is required for the optional web console.

Testing```bash

node tests/run-all.js # Run the repository tests
node scripts/package-smoke.js # Test the packaged runtime
npm run pack:dry-run # Check the published package contents
node scripts/check-no-pii.mjs
node scripts/check-public-mirror.mjs --require-single-commit # Check the public mirror
npm run audit:github-metadata -- --repo owner/repository # Check a new remote
```

Security

  • Node HTTP endpoints that carry data require a token by default. The code compares tokens with timing-safe logic. A Node token grants access to its configured store, where scope filters recall and queries. The optional FastAPI console isolates scoped tokens and conceals whether an ID exists. Limit GB_ALLOW_NO_AUTH=1 to the development use described above.
  • The optional web console listens on loopback as documented. It sets security headers and limits uploads. Extracted PDF text also has a size limit. URL import starts disabled.
  • Release checks run npm audit and pip-audit against dependencies. The security review gives the date, result, and remaining risks.
  • An explicit allowlist creates the public mirror with a new single-commit history. The private engineering repository stays private.

Report vulnerabilities through the private process in SECURITY.md.

Contributing

Read CONTRIBUTING.md before you send a change. Report a concrete bug in Issues, or use Discussions for design and usage questions. Remove private data from every post, including secrets, local paths, identifiers, and runtime files.

License

MIT License. See LICENSE.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
gigabrain 怎么安装?

在客户端按下面的安装命令接入:npx -y gigabrain。对应的包名是 gigabrain。装完在客户端配置里引用同一个包或端点。

gigabrain 怎么在 Claude Desktop、Cursor、Cline 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

gigabrain 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

gigabrain 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

gigabrain 支持哪些客户端?

资料标注支持 Claude Desktop、Cursor、Cline、Claude Code;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

gigabrain 能提供哪些能力?

资料显示能力标签包括 gigabrain、ai-agent、ai-tools、claude、codex。具体工具清单以官方文档为准。

gigabrain 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

gigabrain 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-04-10。