khoj-ai--khoj
Khoj — open-source self-hostable AI second brain: chat với docs + web, semantic search, custom agents, image gen, TTS. Multi-LLM (Claude/GPT/Gemini/Ollama). Browser/Obsidian/Phone.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 13
- Forks
- 2
01 前言 Front Matter
- name
- khoj-ai--khoj
- description
- Khoj — open-source self-hostable AI second brain: chat với docs + web, semantic search, custom agents, image gen, TTS. Multi-LLM (Claude/GPT/Gemini/Ollama). Browser/Obsidian/Phone.
- allowed-tools
- Bash, Read, Write
- user-invocable
- true
03 SKILL.md 正文
Khoj: personal AI assistant self-hostable — "AI second brain" biết về docs của anh, tìm kiếm semantic, tạo agents với knowledge riêng.
Deploy (Self-hosted)
# Docker (recommended)
docker pull ghcr.io/khoj-ai/khoj:latest
docker run -p 42110:42110 \
-v ~/.khoj:/root/.khoj \
ghcr.io/khoj-ai/khoj:latest
# PyPI
pip install khoj
khoj --anonymous-mode # no login required for local use
Key Features
Multi-source RAG:
PDF, Markdown, Org-mode, Word, Notion files
Web search (realtime)
Image understanding
Semantic Search:
Natural language query qua toàn bộ documents
Cross-file relationships
Custom Agents:
Tạo agent với: custom knowledge + persona + model + tools
Ví dụ: "Research Agent" biết về security papers
Content Generation:
Image generation
Text-to-speech + audio playback
LLM Support
Claude, GPT-4, Gemini, DeepSeek — cloud
Llama3, Qwen, Gemma, Mistral — local via Ollama/llama.cpp
Access Points
Browser — web UI tại localhost:42110
Obsidian — plugin sync vault với Khoj
Emacs — org-mode integration
Desktop App — macOS/Windows/Linux
Mobile — iOS/Android app
WhatsApp — chat interface
API
import httpx
# Chat với context
response = httpx.post("http://localhost:42110/api/chat", json={
"q": "What did I write about authentication last week?",
"stream": True
})
# Search documents
results = httpx.get("http://localhost:42110/api/search", params={
"q": "database migration strategy",
"n": 5
})
Khi nào dùng
- Personal knowledge base tìm kiếm được bằng natural language
- Chat với tài liệu dự án (PDF specs, notes, docs)
- Self-hosted alternative cho Notion AI / Perplexity
Source
https://github.com/khoj-ai/khoj · AGPL-3.0 · app.khoj.dev (cloud option)
04 同仓库更多 Skills
openai--sentry--sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
ito-basket-compare
Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.
implementing-network-traffic-baselining
Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling
detecting-evasion-techniques-in-endpoint-logs
Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.
implementing-microsegmentation-with-guardicore
Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.
ramdisk-tmpfs-patterns
暂无简介