OpenTendril Logo
Open Source - MIT Licensed

The secure AI coding
orchestrator

Point it at any project. Talk to it. It reads, edits, and commits inside a locked-down sandbox. Run locally with open models. No accounts. No costs. Your machine, your rules.

Tendril neural network visualization
How It Works
A headless kernel that orchestrates LLM-powered code editing through a sandboxed, auditable pipeline.
CLI (Go)
WebSocket
ws ->
Gateway (Go)
:9090/ws
HTTP ->
Brain (Python)
:8080/v1/chat
LangChain Tools:
  • read_file
  • write_file
  • apply_code_patch
  • search_project
  • list_project_files
  • run_bash_command
  • git_commit
  • git_status
Secure Execution

Your project is mounted read-write inside a secure container. No code leaves your machine except to the LLM API, or stays fully local with open models.

Multi-LLM Routing

Tiered reasoning across Claude, Grok, GPT-4, Gemini, or run fully air-gapped with local models via vLLM on your own GPU.

OpenAI-Compatible API

Exposes a standard /v1/chat/completions endpoint. Plug in Aider, Crush, OpenCode, or any OpenAI-compatible tool.

Approval Gate

Human-in-the-loop security for all file edits. Nothing gets written without your explicit approval.

Built Different
Secure by default. Open by design. Tendril is the orchestrator that does not compromise.

Secure by Default

Zero-trust execution model. Sandboxed containers, approval gates, and auditable edit pipelines. The opposite of run anything and hope for the best.

Fully Local Operation

Run with open models on your own GPU via vLLM. No accounts, no API costs, no data leaving your machine. True air-gapped AI coding.

Headless Kernel

Not a UI. An intelligent backend protocol. Connect your favorite terminal UI and let Tendril handle the thinking, editing, and committing.

Self-Building

In Root Agent mode, Tendril operates on its own source code. The system that builds and repairs itself through a staged edit pipeline.

Multi-LLM Intelligence

Tiered reasoning across providers. Use the best model for each task, or fall back gracefully. Claude, Grok, GPT-4, Gemini, or fully local.

MIT Licensed

No restrictive licensing. Build freely, fork freely, deploy freely. The moat is velocity and the managed experience, not the code.

Works With Your Tools
Point your favorite coding TUI at Tendril's OpenAI-compatible endpoint. It handles the rest.

Aider

The gold standard for Git-native code editing.

export OPENAI_API_BASE="http://localhost:8080/v1"
export OPENAI_API_KEY="tendril"
aider --model openai/tendril

Crush

Glamorous, blazing-fast Terminal UI experience.

export OPENAI_API_BASE="http://localhost:8080/v1"
export OPENAI_API_KEY="tendril"
crush --model openai/tendril

OpenCode

Neovim-centric, highly customizable agenting.

# Point OpenCode's custom provider
# configuration to:
http://localhost:8080/v1
Three Commands to Launch
Clone, configure, run. You will be editing code with AI in under a minute.
# Clone and configure
git clone https://github.com/opentendril/core.git
cd core && cp .env.example .env

# Add your LLM API key (or configure local model)
# Then launch:
docker compose up --build

# Verify it is live:
curl -s http://localhost:8080/health | python3 -m json.tool
# - {"status": "healthy", ...}

Full setup guide with Hello World verification

The Evolution
From a self-building Root Agent to a globally distributed registry of agentic skills.
Complete

Evolution 1: The Root Agent

Self-healing, self-building. Multi-LLM routing, approval gate, the /edit endpoint loop, and the Chronicler. Tendril pointed at its own source code.

Current: v0.1.0

Evolution 2: Deployed Agents

Pointing Tendril at external codebases. External project mode, dynamic workspace awareness, tool adaptability. Enterprise pipelines and local-first compute coming next.

Future

Evolution 3: The Automated Hive

Sharing skills learned by deployed agents back to the Root. Skill abstraction, automated PRs to a global registry, federated learning across Tendril instances.

Watch Tendril Build Itself
Live stream of the Root Agent in action: editing, committing, and evolving its own codebase in real time.
Live

Livestream Coming Soon

The self-building kernel, live and unfiltered. Star the repo to get notified.

Star on GitHub

Get Involved

Or send a direct message.