spark

agent
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 20 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Spark — local-first coding agent (Python + React), self-hosted, MCP-native, with tool sandbox, repo-map context and OTel observability. 本地自托管的 AI 编程智能体。

README.md

🌐 English | 中文

Spark — Local-first AI Coding Agent

License: MIT
Python 3.11+
Node 18+

Code stays with you. Keys stay with you. A self-hosted AI coding assistant that runs entirely on your machine — zero privacy leaks, full control.

Core Values

🔒 Privacy First — All code, conversation, and memory data stay entirely local. No third-party servers involved.
⚡ Ready in a Click — Launch with one command, access via browser. Zero configuration overhead.
🧠 Persistent Memory — Remembers your project preferences, naming conventions, and workflow habits.
🔬 Four-Level Sandbox — From read-only analysis to full access, tunable by risk profile.
⏮️ Checkpoint & Rollback — Jump to any previous state just like Git.

Quick Start

git clone https://gitcode.com/badhope/spark
cd spark && python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
spark web --workdir /your/project

Open http://localhost:8000 to start conversing.

Preview

Spark Agent Interface

Feature Overview

Category Features
Chat SSE streaming render, Markdown code blocks, image attachment upload
Tools File read/write, grep/glob search, Shell commands, Jupyter, Web Fetch
Planning Multi-step task plans, parallel sub-Agent delegation (up to 4)
Permissions Four-level sandbox, tool approval flow, protected path list
Memory AGENTS.md injection, long-term memory retrieval, auto keyword tagging
Persistence Session management, checkpoint & rollback, hot-reload configuration
Models DeepSeek, OpenAI, Ollama local models, multi-profile switching
Extension MCP protocol compatible, custom Provider, project-level skills (.spark/skills/)

Architecture

Architecture Overview

Detailed architecture → docs/ARCHITECTURE.md

Platform Requirements

  • Python 3.11+
  • Node.js 18+ (frontend development only)
  • Any OpenAI-compatible API (DeepSeek, OpenAI, Ollama, Azure, etc.)

Community


License: MIT · Author: badhope · Built with ❤️ in Shenzhen

Yorumlar (0)

Sonuc bulunamadi