Initial docs: model and stack overview

This commit is contained in:
inference-bot committed 2026-09-04 16:04:00 -06:00
commit c2f9c97fce
1 file changed
+69
+69
View File
@@ -0,0 +1,69 @@
# Inference Cooperative
**Private AI, governed together.**
The Inference Cooperative is a member-governed project providing private AI inference. We are fiscally sponsored by [Metagov](https://metagov.org), a nonprofit, and funded through our [Open Collective](https://opencollective.com/inference-cooperative).
- **Website:** https://inference.coop
- **Chat:** https://chat.inference.coop
- **Open Collective:** https://opencollective.com/inference-cooperative
- **Contact:** info@inference.coop
---
## The model
The Inference Cooperative is a **member-governed** AI inference utility. Members contribute on a sliding scale (currently $10–20/month) and, in return, get access to private AI inference through a shared, cooperatively governed infrastructure.
Because we are legally under a nonprofit (Metagov is our fiscal sponsor), we are **member-governed** rather than member-owned: members direct the project through governance, while the nonprofit holds the legal and financial structure.
### Membership
- **Sliding scale:** $10–20/month
- **Governance:** members participate in decisions about models, privacy, and direction
- **Access:** private AI inference through the cooperative's gateway
---
## The stack
The Inference Cooperative runs a self-hosted stack on [Cloudron](https://cloudron.io), with all inference routed through a single gateway.
```
Members → LibreChat (chat.inference.coop)
↓
LiteLLM gateway (gateway.inference.coop)
↓
Inference backend (Ollama Cloud today; TEE-protected Tinfoil planned)
```
### Components
| Component | Purpose | URL |
|-----------|---------|-----|
| **LibreChat** | Member-facing chat interface | chat.inference.coop |
| **LiteLLM** | AI gateway — keys, metering, model routing | gateway.inference.coop |
| **Gitea** | Git hosting (code + docs) | git.inference.coop |
| **Loomio** | Member governance / decision-making | (forum) |
| **Open Collective** | Membership billing + fiscal sponsorship | opencollective.com/inference-cooperative |
### Models
The gateway currently exposes two models:
- **DeepSeek V4 Flash** — default model, best for agentic tasks
- **GPT-OSS 120B** — lightweight fallback
### Privacy
Privacy is a core value. The current backend (Ollama Cloud) is a policy-based privacy model. The roadmap is to move to **TEE-protected inference** (via Tinfoil), which provides architectural — not just policy — privacy guarantees.
---
## Governance
The Inference Cooperative is fiscally sponsored by [Metagov](https://metagov.org). Members govern the project through [Loomio](https://www.loomio.com) and the Open Collective.
---
*This documentation lives in a public git repository. Contributions welcome.*