by schmitech
Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.
# Add to your Claude Code skills
git clone https://github.com/schmitech/orbitLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:14:31.382Z",
"npmAuditRan": true,
"pipAuditRan": true
}See how orbit compares with popular alternatives.
orbit is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by schmitech. Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents. It has 352 GitHub stars.
Yes. orbit passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/schmitech/orbit" and add it to your Claude Code skills directory (see the Installation section above).
orbit is primarily written in Python. It is open-source under schmitech on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh orbit against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The self-hosted AI backend for private data and tool-using agents.
Connect your data and tools to local or hosted models through one OpenAI-compatible API. Configure with YAML. Deploy on your own infrastructure.
Build a chat app over private documents, an agent that calls your tools, or a triage workflow—with the same backend.
| What you get | |
|---|---|
| Your data, connected | Files, SQL, NoSQL, vector stores, APIs, and MCP tools through YAML-configured adapters. |
| Your choice of models | Switch between local and hosted providers behind one OpenAI-compatible API. |
| Your infrastructure | Self-host on-premises or in a private cloud; use local models for air-gapped deployments. |
| Operations built in | Authentication, quotas, audit logs, provider fallbacks, monitoring, and an admin UI. |
Explore the capability matrix for a detailed comparison.
Prerequisites: Python 3.11+ (3.12 preferred), an internet connection for downloads, and Ollama installed and running. If needed, run ollama serve in a separate terminal. On Windows, follow the installation guide.
curl -LO https://github.com/schmitech/orbit/releases/download/v2.18.0/orbit-2.18.0.tar.gz
tar -xzf orbit-2.18.0.tar.gz && cd orbit-2.18.0
./install/setup.sh --profile default
ollama pull gemma4:e2b
# Required for file/multimodal adapters:
ollama pull nomic-embed-text
./bin/orbit.sh start
./bin/orbit.sh status
Open the admin dashboard and sign in with admin / ChangeMe!2026.
For a quick smoke test, the release seed includes default-key mapped to the
simple-chat adapter:
curl -X POST http://localhost:3000/v1/chat \
-H 'Content-Type: application/json' \
-H 'X-API-Key: default-key' \
-H 'X-Session-ID: readme-smoke-test' \
-d '{
"messages": [
{"role": "user", "content": "Say hello in one sentence"}
],
"stream": false
}'
Continue with your first chat to create an API key, or use the Docker quick start for containers.
The default setup uses Ollama with the gemma4-e2b-cpu preset, which resolves to gemma4:e2b.
config/config.yaml.config/inference.yaml, set its credential in .env, and select it globally or per adapter.config/ollama.yaml.config/adapters.yaml and config/adapters/. Start with the adapter guide or intent templates.See Before you start for installation checks, file retrieval setup, and API-key management.
Use orbit-cli from a terminal (Node.js 20+):
npm install -g @schmitech/orbit-cli@latest
orbit-chat --url http://localhost:3000 --key default-key
Or launch OrbitChat in your browser:
npm install -g orbitchat@latest
cat > orbitchat.yaml <<'EOF'
agentMode:
mode: "single"
defaultAdapterId: "simple-chat"
adapters:
- id: "simple-chat"
EOF
ORBIT_ADAPTER_KEYS='{"simple-chat":"default-key"}' orbitchat --config orbitchat.yaml --open
OrbitChat opens at http://localhost:5173. See the example configuration for more options.
| I want to… | Start here |
|---|---|
| Learn ORBIT | Tutorial · First chat · HTTP APIs |
| Connect private data | Files · Vector stores · SQL · Intent templates · Adapter system overview |
| Build agents | MCP tools · Automatic skill routing · A2A · Adapter creation |
| Make real-time decisions | Decision models · Triage Rush demo · Sentiment Pulse |
| Run in production | Authentication · Cost tracking · Rate limiting · Fault tolerance |
| Use a client | OrbitChat · Realtime Voice · Node.js SDK · Python API example |
See the documentation index for every guide and architecture deep dive.
Contributions are welcome: new retrievers and provider integrations, deployment guides, tests, fixes, and documentation. Read CONTRIBUTING.md, pick an open issue, or start a discussion.
Maintained by Remsy Schmilinsky.
ORBIT (Open Retrieval-Based Inference Toolkit) is licensed under the Apache License 2.0.