Skillget

ode

agent
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 20 GitHub stars
Code Uyari
  • process.env — Environment variable access in packages/agents/codex/client.ts
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool acts as a bridge, connecting local and remote AI coding agents (like OpenCode, Claude Code, and Codex) to chat platforms such as Slack, Discord, and Lark. It maps chat threads directly to parallel coding sessions, allowing users to trigger and monitor code generation from their messaging apps.

Security Assessment
Overall Risk: Medium. The tool operates by executing local shell commands via connected coding agents, which inherently carries execution risks, though it does not request dangerous standalone permissions itself. It makes external network requests to communicate with chat app APIs. The scan flagged environment variable access (`process.env`), which is expected for reading API tokens, but requires caution as it handles sensitive credentials. There are no hardcoded secrets detected. However, downloading and running the provided install script (`curl | bash`) bypasses manual review and could be a vector for supply chain attacks if the repository is ever compromised.

Quality Assessment
The project is highly active, with its most recent push happening today. It has a small but growing community backing with 20 GitHub stars. However, the repository notably lacks a standard open-source license. This is a significant drawback for developers, as it means the software is technically all-rights-reserved and you do not have formal legal permission to use, modify, or distribute the code.

Verdict
Use with caution: it is an active and functional tool, but the lack of a formal license and the inherent risks of passing sensitive chat tokens to a remote bridging agent require careful consideration before implementation.
SUMMARY

Work anywhere with your favorite coding agents connected, coding sessions map 1-1 to chat threads, live updates and much more!

README.md

Ode

Official Doc

Ode is a agent tool that bridges your coding agents (OpenCode, Claude Code, Codex and much more) to your favorite chat apps (Slack, Discord, and Lark). Perfect for personal or team developers working on the go.

Ode demo

Highlight features

  • 🏖️ Coding from anywhere, just chat and get response in slack or discord.
  • 🖇️ Map coding sessions 1 - 1 to chat threads, and use worktree to get isolated, parallel coding is so easy.
  • 👬 Anyone in the channel can join coding without any extra setup, pay one account for all team members.
  • 📝 Message live message updates, you don't wait for response without any information, you can monitor from real-time text updates.
  • 🐙 Per user git config, who start the thread becomes corresponding git commit author. (Run @bot /setting)

Compare with OpenClaw

  • OpenClaw is greate, but Ode utilize thread based messaging to organize things better, making it easy to port sessions in coding agents directly to chat apps. Just work on one thing in one thread.
  • Ode provide live message updates, you can monitor from real-time text updates for more confident.
  • Channel based settings lets you configure multiple work directories easily in one machine and one slack workspace.
  • Work in parallel, multiple threads can work together and isolated by worktree, multiple channels can also work together, just send messages.
  • Team focused, just allow people to join channel to give them permissions to work together.
  • Ode supports multiple chat tools including Slack, Discord, and Lark.

Setup

Prerequisites

  • Configured OpenCode / Claude Code / Codex / Kimi Code... at least 1 coding cli.
  • Choose one chatting app.
    • Slack - follow this doc to get your APP TOKEN (xapp...) and BOT TOKEN (xbot..).
    • Discord - follow this doc to get your BOT TOKEN.
    • 飞书 - Just CN version for now, as Lark global is not supportting long connection with socket yet. Prepare the larkAppId and larkAppSecret.

Installation and Running

One-line install (macOS/Linux):

curl -fsSL https://raw.githubusercontent.com/odefun/ode/main/scripts/install.sh | bash

ode 
# ODE_WEB_HOST=0.0.0.0 ode if you want to expose setting page

Settings UI can be accessible via http://127.0.0.1:9293 or use /setting command in slack like @bot /setting.

Agent List

Agent Logo Link
OpenCode OpenCode logo opencode.ai
Codex Codex logo github.com/openai/codex
Claude Code Claude Code logo docs.anthropic.com/claude-code
Kimi Code Kimi Code logo moonshotai.github.io/kimi-cli
Qwen Code Qwen Code logo github.com/QwenLM/qwen-code
Goose CLI Goose CLI logo block.github.io/goose
Gemini CLI Gemini CLI logo github.com/google-gemini/gemini-cli
Kilo Code Kilo Code logo kilo.ai/docs/code-with-ai/platforms/cli
Kiro CLI Kiro CLI logo kiro.dev/docs/cli/reference

Chat App List

Chat App Logo Link
Slack Slack logo slack.com
Discord Discord logo discord.com
飞书（CN） Lark logo www.larksuite.com

Usage

  1. Invite the bot to a channel.
  2. Run @bot /setting, select channel setting, choose your coding cli (opencode also can choose model) and working directory.
  3. @ your bot with the prompt you want.
  4. The bot will process your message with the coding agent.

Worktrees

  • Each slack thread uses a dedicated git worktree at <repoRoot>/.worktree/<threadId>
  • If you don't want to use worktree, can run @bot /setting and select general setting, choose default.

License

MIT

Yorumlar (0)

Sonuc bulunamadi