Aryan SinghandClaude Opus 5
cb985dcf9c
One endpoint in front of every free LLM tier, with automatic failover and no provider key ever leaving the box. Providers are data, not code: adding one is a JSON file plus an env var, never a TypeScript change. Ships 12 providers pre-written; `verify-provider --apply` derives the live model list from your own key. - core: registry, bucketed quota meter (rolling + UTC-calendar windows), key-pool store, 6-step model router with diagnostic rejection reasons - gateway: node:http, failover that commits to a stream only after 200 headers, SSE passthrough with usage sniffing, virtual keys with admin/inference roles - context engine: sqlite sessions and a 5-rung refit ladder, so a 128k thread keeps working when it fails over to an 8k model - cache: exact (sha256, safe-by-default) + opt-in semantic (flat Float32Array) - guard: inbound limits, quota forecasting, limit calibration from upstream headers, key health, secret/PII/injection scanning - dashboard: one self-contained HTML file, live SSE request log, token usage - sdk: zero-dep typed client, drop-in for the OpenAI SDK Zero runtime dependencies. 326 tests, 27-check smoke suite against a scripted mock upstream so routing is testable without spending quota. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
18 lines
784 B
JSON
18 lines
784 B
JSON
{
|
|
"$schema": "./_schema.json",
|
|
"id": "ollama",
|
|
"label": "Ollama (local)",
|
|
"docs": "https://github.com/ollama/ollama/blob/main/docs/openai.md",
|
|
"console": "https://ollama.com/library",
|
|
"priority": 90,
|
|
"baseUrl": "${OLLAMA_HOST}/v1",
|
|
"auth": { "type": "none", "envKeys": [] },
|
|
"limits": {},
|
|
"limitsSource": "docs",
|
|
"verifiedOn": "2026-08-16",
|
|
"modelsEndpoint": "/models",
|
|
"modelsPath": "data[].id",
|
|
"notes": "Your own machine, so there is no quota to meter and no key to hold — the point of auth.type: none. Set OLLAMA_HOST=http://127.0.0.1:11434 to enable. Priority 90 keeps it as the last resort, i.e. the thing that still answers when every hosted free tier is exhausted. Leave models empty; discovery lists whatever you have pulled.",
|
|
"models": []
|
|
}
|