AgentHydra
Active·★ 44·MIT·Updated 2026-10-18
AgentHydra is a local daemon that centralizes AI coding session history from tools like Claude, Codex, and OpenCode into a single browser tab. It acts as a unified dashboard, enabling users to view, filter, queue, and manage multiple AI instances and their interactions across different accounts and projects.
#AI Session Management#Multi-Agent Orchestration#Local LLM Dashboard#Code Assistant Integration#Workflow Automation#Instance Management#Developer Tools
01
Features
01Unified view of AI coding sessions from Claude, Codex, and OpenCode.
02Queue and schedule Claude runs with customizable prompts, models, and accounts.
03Manage isolated Claude Desktop and Codex instances (open, quit, create, delete, focus).
04ChatGPT handoff feature for preparing tasks and repository context, omitting secrets.
05Persistent runs that reattach after restarts and intelligent rate limit handling for Claude sessions.
02
Compatibility
Claude Desktop
AI Client
Verified via docs
claude CLI
Tool Integration
Verified via docs
Codex Desktop/CLI
AI Client
Verified via docs
OpenCode
Tool Integration
Verified via docs
Bun
Runtime
Verified via docs
Windows
Operating System
Verified via docs
03
Quick start
1
$ git clone https://github.com/LunarWerxs/AgentHydra.git
2
$ cd AgentHydra
3
$ bun install
4
$ bun run build
5
$ bun run start
04
Use cases
↳Consolidating and tracking AI coding activity across multiple tools and accounts.
↳Orchestrating and scheduling a series of AI tasks, such as overnight code generation or analysis.
↳Managing and quickly switching between different isolated AI development environments or accounts.
↳Preparing contextual prompts for ChatGPT by automatically bundling repository files while filtering out sensitive data.
↳Monitoring the status, usage, and progress of multiple concurrent AI agents or client instances.
05
Alternatives
agentweave★ 42
Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware routing and recovery.
Agentflow★ 27
Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
entwurf★ 29
Garden-citizen dispatch for pi, Claude Code, Copilot CLI, OMP, Antigravity, and Codex; visible tmux sibling seats for Pi/Claude/Copilot/OMP/Codex, preserving each harness's auth, tools, and transcript; plus Claude/Cortex ACP.
cli-agent-orchestrator★ 1.5k
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
suede-creator-skills★ 125
67 open-source Agent Skills for Claude Code and Codex: Full Send orchestration, A-F code review, AI evals, CI ship-gates, design, copy, SEO/AEO/GEO, app shipping, creator rights, and consumer recovery.
Comments
Log in to leave a comment
No comments yet. Be the first!