# KIAgent **Category:** ๐Ÿ—„๏ธ Databases **Repository:** https://github.com/edjafarov/kiagent-core **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/kiagent ## Description Your mail, chats and documents indexed into a local SQLite corpus, served to AI clients over MCP. ## Claude Desktop Quick Installation Heuristic fallback โ€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "kiagent": { "command": "npx", "args": ["-y","kiagent"] } } ``` ## Documentation & README

KIAgent logo

KIAgent

Your personal AI brain โ€” local, open source, speaks MCP.

Website ยท Download ยท Architecture docs

License: MIT Platforms

KIAgent main window โ€” Sources screen with Gmail and HubSpot syncing

Everyone is building the company a brain โ€” a knowledge layer that ingests everything an organization knows, so AI can answer and act with real context. **KIAgent is that layer for you personally.** A company brain lives in someone else's cloud and belongs to your employer; your personal AI brain runs on your own machine, works with whatever AI you choose, and is yours forever. Concretely, KIAgent is a desktop app that ingests your personal data โ€” mail, documents, chats, notes โ€” on your own machine, stores it in a local database, and serves it to AI assistants over [MCP](https://modelcontextprotocol.io). Everything stays on your computer: ingestion, parsing, OCR and vision all run locally โ€” with on-device inference powered by [llama.cpp](https://github.com/ggml-org/llama.cpp) โ€” so your AI assistant can know your world without your data ever leaving your machine. At its core, KIAgent is a **platform**: a small set of host capabilities (MCP, database, local LLM, filesystem, web access) wired together by an ingestion engine, plus a plugin/extension system that lets sandboxed connectors use those capabilities to bring in new data sources. ```mermaid flowchart TB GMAIL(["Gmail"]) DRIVE(["Drive"]) SLACK(["Slack"]) NOTION(["Notion"]) MORE(["โ€ฆ"]) PLUGINS["Plugins / extensions"] WEB["Web"] LLM["Local LLM"] FS["Filesystem"] DB[("DB")] MCP["MCP"] GMAIL --> PLUGINS DRIVE --> PLUGINS SLACK --> PLUGINS NOTION --> PLUGINS MORE --> PLUGINS PLUGINS <--> WEB PLUGINS <--> LLM PLUGINS <--> FS PLUGINS <--> DB DB --> MCP classDef service fill:#e8f0fe,stroke:#4285f4,color:#1a3c78 classDef core fill:#e6f4ea,stroke:#34a853,color:#1e4620 classDef hub fill:#fce8e6,stroke:#ea4335,color:#7a1c14,stroke-width:2px class GMAIL,DRIVE,SLACK,NOTION,MORE service class WEB,LLM,FS,DB,MCP core class PLUGINS hub ``` Plugins sit at the center: each one connects to a third-party service (Gmail, Drive, Slack, Notion, ...) or the local filesystem, pulls your data in, uses the local LLM to process it, and lands it in the database โ€” which MCP then serves to AI assistants. Access is mediated and permission-gated; plugins never touch these capabilities directly. ## This repo: kiagent-core This repository is the MIT-licensed core that KIAgent is built from, in the same spirit as VS Code and Code-OSS: - **kiagent-core** (this repo) โ€” the open-source core. `npm run package:oss` produces an unbranded `kiagent-core` build you can run and redistribute under the MIT license. - **[KIAgent](https://localkiagent.com/)** โ€” the branded, signed product built from this core and distributed at [localkiagent.com/download](https://localkiagent.com/download). OAuth-backed sources (Gmail, Microsoft) read client credentials from the environment at build time โ€” see `.env.example` / CI secrets. Forks and OSS builds supply their own OAuth client IDs. ## Main components - **Ingestion engine** (`src/main/core/engine`) โ€” pulls batches from sources on a cadence, converts raw items (mail, PDFs, images) into indexed documents, and commits them to the store. Built-in sources live in `src/main/sources` (Gmail, IMAP, Microsoft 365, local folders). - **Database** (`src/main/core/store`, `src/main/db`) โ€” a SQLite corpus (better-sqlite3) holding documents, metadata and search indexes, written by the app and read by the MCP processes. - **MCP server** (`src/main/core/mcp`, `src/main/mcp`) โ€” exposes the corpus to AI assistants over two transports sharing one tool registry: an HTTP server inside the app, and a standalone stdio entry point that clients like Claude Desktop spawn directly. - **Local LLM** (`src/main/providers/local-llm`, `src/main/providers/apple-vision`) โ€” on-device inference via a bundled [llama.cpp](https://github.com/ggml-org/llama.cpp) server (backend auto-detection, curated model tiers) plus native OCR/vision helpers for scanned documents and images. - **Filesystem** โ€” local-folder ingestion, model storage, temp workspaces for conversion workers (`src/main/workers`, `src/main/converter`). - **Web** โ€” outbound HTTP for source APIs, OAuth flows (`src/main/auth`, `src/main/platform/oauth-providers.ts`), and marketplace downloads. - **Plugin / extension system** (`src/main/platform`, `src/main/marketplace`) โ€” connectors run in isolated host processes with a manifest-declared, permission-gated view of the platform (sources, auth, storage, network). A GitHub-backed marketplace handles discovery, install and updates. A second, privileged tier lets a product build ship first-party extensions inside the app package itself โ€” see [`docs/architecture/extension-platform.md`](docs/architecture/extension-platform.md) for the full model, including the bundled/`unsafe.mainProcess` tier and `product.json`. - **Renderer** (`src/renderer`) โ€” the React UI: source setup, marketplace, MCP connection status, settings and logs. ## Developing ```bash npm install npm start # run in development (hot reload) ``` Other useful scripts: ```bash npm test # jest test suites npm run lint # eslint + prettier npm run typecheck # tsc, no emit npm run package # build a distributable npm run package:oss # build an unbranded kiagent-core distributable npm run vendor:inference # fetch llama.cpp server + build vision helper ``` ## Repository layout ``` src/main Electron main process: engine, store, MCP, platform, sources, providers src/renderer React UI (screens: Sources, Marketplace, Connection, Settings) src/shared Contracts and UI primitives shared across processes concept/ Types-only blueprint for the core redesign docs/ Design specs and implementation plans native/ Native helper sources (vision/OCR) scripts/ Build and vendoring scripts ``` ## MCP directories KIAgent is published on the [official MCP registry](https://registry.modelcontextprotocol.io/v0/servers?search=kiagent) as `com.localkiagent/kiagent` (see [`server.json`](server.json)) and listed on Glama: [![kiagent-core MCP server](https://glama.ai/mcp/servers/edjafarov/kiagent-core/badges/card.svg)](https://glama.ai/mcp/servers/edjafarov/kiagent-core) ## Acknowledgements KIAgent's on-device inference is powered by **[llama.cpp](https://github.com/ggml-org/llama.cpp)**, created by Georgi Gerganov and maintained by the ggml-org community (MIT license). The app bundles prebuilt `llama-server` binaries from the official llama.cpp releases (`npm run vendor:inference` fetches them at build time). Running capable models privately on consumer hardware is only practical because of their work โ€” thank you. ## License MIT โ€” see [LICENSE](LICENSE).