Ennodia
Let one coding agent hand tasks to other installed agents and get answers back
- Pricing
- Open source
- Platforms
- self-hosted, CLI
- Runs
- Locally
- Version
- 0.5.5
- Listing updated
- 3 days ago
About Ennodia
Ennodia is an open-source MCP server for ai models and llm tooling. It runs locally on your machine and is started by your AI client.
Ennodia has no window of its own. You stay in Claude Code, Codex or another agent, and when a task suits a different model, your agent hands that part over and the answer comes back into the same conversation.
Under the hood your agent calls ennodia_run with the task, the target agent or model and a time limit. Ennodia starts that agent's own command-line tool in a fresh session on your computer, using your own accounts and plans, and keeps a local receipt of who did the work, how long it took and what came back. Run history is a record only; the site says learning which model to pick next is still planned.
It loads eight core tools by default, or all of them with a flag, and needs Bun 1.3.14 or newer. The README lists Claude Code, Codex CLI, OpenCode, Antigravity, Kilo Code, Kiro, Cline and Hermes Agent as agents it can use. Because several agents run, it can use more tokens, and you can limit runs and estimated input tokens.
Install
Run in a terminal
claude mcp add ennodia -- npx -y ennodiaAdd to claude_desktop_config.json
{
"mcpServers": {
"ennodia": {
"command": "npx",
"args": [
"-y",
"ennodia"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"ennodia": {
"command": "npx",
"args": [
"-y",
"ennodia"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"ennodia": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ennodia"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"ennodia": {
"command": "npx",
"args": [
"-y",
"ennodia"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"ennodia": {
"command": "npx",
"args": [
"-y",
"ennodia"
]
}
}
}Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- ennodia_run
- Hands a task to a chosen agent or model with a time limit and returns the result
What it does
- Agent-to-agent handoff
- Your agent delegates part of a task to another installed agent.
- Local receipts
- Each handoff leaves a record of who worked, how long it took and what returned.
- Your own accounts
- It reuses the agents and plans you already have, with no Ennodia account.
- Run limits
- Cap agent runs and estimated input tokens.
- Core or full tool set
- Eight core tools by default; add --tools all for the full set.
Good for
- Get two independent reviews of one patch in fresh sessions
- Have another model transcribe an audio file your agent cannot hear
- Run several research passes and have one agent judge the evidence
- Compare answers when two agents disagree
Pricing
Open source
Free and open source; uses the agent plans you already have
Prices change. Check ennodia.cherninlab.com before you buy.
Ennodia FAQ
Does it send my data to an Ennodia service?
No. It runs on your computer with no Ennodia-hosted service, though the agents you pick still send prompts to their own model providers.
What does it cost?
It is free and open source with no account.
Will it use more tokens?
It can, since more agents run. You can limit agent runs and estimated input tokens.
What does it require?
Bun 1.3.14 or newer, an MCP client and a supported agent with working provider access.
Is Ennodia free?
Yes. Ennodia is open source, so you can use and self-host it for free.
How do I add Ennodia to Claude Code?
Run this command in your terminal: claude mcp add ennodia -- npx -y ennodia
What are the best alternatives to Ennodia?
The closest alternatives to Ennodia are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Ennodia

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools