Ollama
Run large language models locally with a single command. OpenAI-compatible API for Llama, Mistral, Gemma, and more.
Ollama
Ollama makes running open-weight LLMs locally as simple as ollama run llama3. It ships a cross-platform daemon with a fully OpenAI-compatible REST API, so any agent or tool that speaks to OpenAI can point to localhost:11434 and run on-device models with zero cloud dependency.
Key Features
- One-command setup —
curl -fsSL https://ollama.com/install.sh | shon Linux/macOS - Model library — 100+ curated models: Llama 3, Mistral, Gemma 3, Phi-4, Qwen, DeepSeek, and multimodal models
- OpenAI-compatible API — drop-in replacement for
openaiSDK clients by changing one base URL - GPU acceleration — NVIDIA CUDA, AMD ROCm, Apple Metal — automatic detection
- Modelfile — parameterize, layer adapters, and customize system prompts in a Dockerfile-like format
- Streaming — token-by-token streaming responses
Quick Start
# Install and run a model
ollama run llama3.2
# Use via OpenAI-compatible API
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "llama3.2", "messages": [{"role": "user", "content": "Hello!"}]}'
Install via ai-supply
npx ai-supply add ollama-local-model-runtime
Curated mirror of the open-source Ollama project (MIT). Install upstream from the repository.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/ollama-local-model-runtime/check). Click a policy:
Consume Ollama programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/ollama-local-model-runtime
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/ollama-local-model-runtime/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add ollama-local-model-runtime
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/ollama-local-model-runtime/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "ollama-local-model-runtime" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.