Tags give the ability to mark specific points in history as being important
-
-
-
v0.6.0
52a1186b · ·v0.6.0: remove model group aliases, fix vision group - remove model_group_alias (was silently broken — maps to one model, not a list) - remove group-level fallbacks (fast/smart/vision) that depended on aliases - add local-ollama-moondream to vision group in config - fix README: update usage examples to use actual model names - fix README: Speaches description includes TTS
-
v0.5.0
1f3809a5 · ·v0.5.0: remove infinity reranker, README fixes - remove infinity service (too RAM-hungry for CPU-only stacks) - remove local-infinity-rerank model - README: drop 'one compose file' claim, fix auth wording
-
v0.4.0
2cb78e31 · ·v0.4.0: local reranking, 83 models - add Infinity reranking service (michaelf34/infinity:0.0.77-cpu) - mxbai-rerank-xsmall-v1 cross-encoder for RAG pipelines (~70MB, ONNX) - local-infinity-rerank model routed via LiteLLM - resource limits in recommend-limits.sh - 83 models across 12 providers
-
v0.3.0
4329333e · ·v0.3.0: 82 models, local TTS, nginx rate limiting, security hardening Models: - add ollama: qwen3:4b, smollm2:1.7b, qwen2.5-coder:3b, bge-m3, qwen3-embedding:0.6b - add speaches: whisper, parakeet transcription, Kokoro TTS - 82 models across 12 providers Infrastructure: - speaches-pull container pre-downloads whisper, parakeet-onnx, kokoro-int8 - ollama-pull DNS fix: network_mode service:ollama - litellm workers configurable via LITELLM_WORKERS env var - speaches healthcheck fixed (/health not /healthz) - remove litellm memory limits Security: - nginx rate limiting on all endpoints (api 120r/m, storage 60r/m, claudebox/browser 30r/m) - Cloudflare real IP restoration (CF-Connecting-IP) so rate limits work behind tunnel - HAProxy __queue/health and __queue/status restricted to private networks - default auth tokens to lulz-4-security (stealthy-auto-browse, hybrids3)
-
-
-