Unsloth is the fastest, most VRAM-efficient local LLM fine-tuning tool — 2× training speed and 70% less VRAM. In 2026 it added a Desktop app that bundles inference, training, image/video generation, web search, and agent integration into a complete local AI workstation.
The key question in self-hosted inference isn't how fast the engine is — it's your GPU utilization. A fully saturated A100 costs ~$0.70 per million output tokens; at 10% utilization that becomes $7, more than most cloud APIs. This overview maps seven tools across three layers to help you decide which layer you need.
TensorRT-LLM is NVIDIA's open-source LLM inference library (Apache 2.0). It offline-compiles model weights and compute graphs into optimized TensorRT engines, then serves them with custom CUDA kernels, in-flight batching, and multi-dimensional parallelism. The cost: NVIDIA GPUs only, compilation takes tens of minutes, and switching models or quantization means rebuilding.
Text Generation Inference (TGI) is HuggingFace's own LLM inference server, built in Rust and Python. It pioneered continuous batching and Flash Attention in open-source inference engines. The GitHub repository was archived on March 21, 2026, and HuggingFace recommends migrating to vLLM or SGLang. TGI still matters: it defined the architectural baseline that successor engines inherited, and many HuggingFace Inference Endpoints still run it.
Chroma manages embeddings, documents, and metadata through collections; it embeds into Python locally, uses HNSW on a single node, and separates compute from storage with object storage, SSD caches, and SPANN in distributed deployments.
LiteLLM is not a model provider. It is a Python SDK and self-hosted proxy that normalizes 100+ LLM APIs, then centralizes routing, fallbacks, virtual keys, budgets, and observability at the gateway layer.
Milvus separates real-time ingestion, historical queries, index building, and persistence into independently scalable components. It fits large, continuously updated retrieval services, but smaller projects often pay too much operational complexity for that architecture.
R2R packages document ingestion, hybrid search, knowledge graphs, RAG, Agents, and access controls behind a REST API; it fits teams that already own their product frontend and backend and need a retrieval service.
RAGFlow puts document parsing, human chunk review, retrieval tests, chat, and citations in one platform; it fits layout-heavy PDFs and tables, but carries more deployment weight and platform state than a Python library.
Ray Serve is a distributed serving layer on Ray. Deployments and handles compose Python service graphs, while replicas, CPU/GPU scheduling, autoscaling, and model multiplexing handle orchestration; it complements rather than replaces vLLM or SGLang.
Redpanda reimplements a Kafka-compatible event log with C++/Seastar, thread-per-core execution, and a Raft group per partition. Client compatibility is broad, but operational and edge semantics still require testing.
Scrapy separates crawling into the Engine, Scheduler, Downloader, Spider, Item Pipeline, and middleware; it fits high-volume, rule-driven HTTP crawling where you need control over scheduling, throttling, retries, and storage.
SGLang is an inference engine for generative models. RadixAttention reuses KV cache across shared prefixes, while OpenAI-compatible APIs, structured output, and multi-GPU parallelism support production LLM serving; it is not a complete product backend.
Triton Inference Server serves TensorRT, ONNX, PyTorch, and other models through consistent HTTP and gRPC APIs. Its defining tools are the model repository, dynamic batching, instance groups, and ensembles—not LLM-specific KV-cache scheduling.
Typesense is a search server centered on instant, typo-tolerant keyword search. Collection schemas, field weights, facets and sorting are enough to build site search, with a choice between self-hosting and Typesense Cloud; Chinese fields need locale: zh, and domain terminology may require custom segmentation.
changedetection.io is a web-change signal layer: narrow the monitored content, suppress noise, and notify downstream systems only when a meaningful change occurs. It is neither a search API nor a crawler replacement.
Firecrawl puts single-page scraping, site discovery, whole-site crawling, and JSON extraction behind one API. Cloud removes browser, proxy, and worker operations; self-hosting gives infrastructure control, but not the complete Cloud feature set.
Free access is not one model: recurring allowances, balance top-ups, rate-limited access, one-time credits, and self-hosting have different steady-state costs.
Meilisearch turns application data into fast, typo-tolerant full-text search; the hard parts are index settings, asynchronous tasks, Chinese tokenization, access filters, and tested recovery.
Qdrant is not just a place to store embeddings: define the vector schema, index frequently filtered payload fields, then add dense+sparse queries, tenant boundaries, snapshots, and monitoring to build an operable retrieval service.
SearXNG is a metasearch engine, not a crawler, and it does not own a web-wide index. Based on the official 2026.8.20 documentation, this guide covers Compose installation, settings.yml, engine selection, the JSON API, and empty-result diagnosis.
Three components, one job each: SearXNG finds, Crawl4AI reads, and a thin layer of your own code glues them together. Three defaults will stop you cold — `formats` only emits HTML, `secret_key` ships as the literal string `ultrasecretkey`, and turning on the limiter blocks your own code. Also, the official install path changed in March 2026, so most tutorials online point at a repository that is now archived.
Tavily and Exa are cloud-only APIs and can't be self-hosted. What you can assemble instead is SearXNG (269 upstream engines, 82 on by default) plus Crawl4AI (78.8k stars, Apache-2.0), and the ready-made Tavily-compatible wrappers are all still double-digit-star solo projects you should not depend on. But SearXNG has no index of its own, and running it from a datacenter IP gets you empty results — those two facts decide whether self-hosting is worth it.
Self-hosting an agent that runs 24/7 means opening something on your own network that must be reachable from outside and must never sit on the public internet. This post takes apart what each Tailscale mechanism actually solves: the tailnet for reachability, subnet routers for private resources, tags plus ACLs for the permission boundary, and seconds-fast policy propagation plus Tailnet Lock for revocation. Pricing checked 2026-08: Personal is free, up to 6 users, unlimited user devices, 50 tagged resources included.
AEO/GEO tools aren't a single category — they span three distinct layers: the input layer (is your website ready for AI to read), the traffic layer (how much are AI bots actually crawling), and the output layer (how is your brand mentioned in AI answers). This post maps out all three layers, from open-source self-hosted options to commercial SaaS.
OpenClaw has 200+ docs. This article helps you see the big picture, understand what each section covers, and decide where to start based on your role.
Ollama wraps llama.cpp in a Docker-style CLI + REST API, letting you run LLMs locally with a single command. This post covers core concepts, installation, API, hardware requirements, Modelfile customization, and what this tool is — and isn't — good for.