Bodhi Realtime Agent — Communication skill for Claude Code
Real-time voice agents with parallel async background sub-agents — conversations continue naturally while tasks run • Join the builders → https://discord.gg/mqxKaN3UKC.
How to install Bodhi Realtime Agent
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sonichi/bodhi_realtime_agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Bodhi Realtime Agent does
Real-time voice agents with parallel async background sub-agents — conversations continue naturally while tasks run • Join the builders → https://discord.gg/mqxKaN3UKC.
Alternatives in Communication
- Open SaaS — A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma) 14.1k ★
- Claude Code Remote — Control Claude Code remotely via email 1.2k ★
- Taiyi Continue 881 ★
README
Bodhi: High-Performance, Multi-Agent realtime Voice Stack
[](https://www.npmjs.com/package/bodhi-realtime-agent) [](https://opensource.org/licenses/MIT)
**Conversational voice agents with non-blocking background execution.** (No other framework does this out of the box.)
Most voice agent frameworks block conversation while tools execute. User says "generate me a video" and the agent goes silent for two minutes. Bodhi splits the work: **main agents** handle the live conversation (Gemini Live API by default, OpenAI Realtime also supported), while **background subagents** (Vercel AI SDK) run long tasks in parallel. When a task finishes, the agent naturally announces it.
User: "Make me a video of a sunset AND search for weather in Tokyo"
Main Agent (Gemini/OpenAI Live — realtime voice):
"I'm generating your video and looking up the weather..."
│
├─ Subagent 1: Video generation (2 min, Veo API)
├─ Subagent 2: Web search (3 sec, Gemini)
│
"What else can I help with?" ← keeps talking
│
[3s] "The weather in Tokyo is..." ← search result arrives
[2m] "Your video is ready!" ← video arrives
Claude Code Demo — Voice-Driven Coding Assistant
Speak coding requests naturally — Claude Code reads, edits, creates files, runs commands, and searches your codebase in the background while you keep talking. See [examples/claude_code](examples/claude_code/) for setup.
OpenClaw Integration — Voice-Driven AI Agent
Runtime-first agent harness for official coding CLIs, chat transports, background tasks, and controlled write- The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated flo The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated flo Real-time X/Twitter search powered by Grok-4 and Grok-4.20 - find tweets, read threads, track trends, analyze Opens a link to join the Pinecone Discord, allowing users to learn from each other, contact the Pinecone team, A Claude Code skill for posting to X (Twitter) directly from your Claude Code session. Just ask Claude natural Fullstack vibe coding assistant. Talk naturally — I plan, code, test, and deploy for you. Perfect for non-tech Use proactively for all OpenAI Realtime API integration - WebRTC setup, audio streaming, session management, a Execute PLAN.md tasks one at a time with human oversight. Triggers on "execute", "execute plan", "execute theRelated Skills
ControlMesh
Communication community
Theboringoffice
Communication community
Theboringfloor
Communication community
Clawdbot Skill Search X
Communication community
Join Discord
Communication community
X Post Skill
Communication community
Related Agents
Vibe Coder
DevOps & Infrastructure community
Realtime API Engineer
Development community
Execute Plan
Project Management community