HeyJaredSelf Hosted Ai tools
SelfHostedAITool helps startup founders, indie hackers, agencies, and small business owners replace expensive SaaS subscriptions with free open-source alternatives.
- Indexed videos, last 90 days
- 18
- Latest publication
- Sep 25, 2026
- Audience
- ~52 subscribers
- Earliest in this view
- Jul 19, 2026
Latest videos
7 Ways NVIDIA's $12.9B Deal CRUSHES Your Local AI Stack (opens the original)
Read excerpt
7 Ways NVIDIA's $12.9B Deal CRUSHES Your Local AI Stack | NVIDIA Hugging Face acquisition | self hosted llm | local AI stack | open source ai tools ━━━━━━━━━━━━━━━━━━━━ 🔗 Research Hugging Face https://huggingface.co NVIDIA https://www.nvidia.com llama.cpp (ggml) https://github.com/ggml-org/llama.cpp Hugging Face Mirror https://hf-mirror.com ModelScope https://modelscope.cn OpenRouter https://openrouter.ai Stripe https://stripe.com ━━━━━━━━━━━━━━━━━━━━ Video Summary NVIDIA just agreed to pay $12.
OpenCode vs Claude Code: The Terminal Agent War Nobody's Talking About (opens the original)
Read excerpt
OpenCode vs Claude Code terminal agent war | OpenCode vs Claude Code | terminal agent | AI coding agent | coding agent comparison ━━━━━━━━━━━━━━━━━━━━ 🛠️ Research OpenCode (GitHub) https://github.com/sst/opencode Claude Code (Anthropic docs) https://docs.claude.com/en/docs/claude-code Anthropic Claude pricing/plans https://www.anthropic.com/pricing Terminal-Bench https://www.tbench.ai/ SWE-bench https://www.swebench.com/ llama.cpp https://github.com/ggml-org/llama.cpp LM Studio https://lmstudio.
I Spent $5,000 On Local AI Hardware — Here's What Won (opens the original)
Read excerpt
I Spent $5,000 On Local AI Hardware — Here's What Won | RTX 5090 vs Mac Studio | local AI hardware | self hosted llm | AI homelab ━━━━━━━━━━━━━━━━━━━━ 🛠️ Research NVIDIA RTX 5090 https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5090/ Apple Mac Studio https://www.apple.com/mac-studio/ vLLM (serving engine) https://github.com/vllm-project/vllm llama.cpp https://github.com/ggml-org/llama.cpp DeepSeek R1 https://github.com/deepseek-ai/DeepSeek-R1 Llama 3.3 (Meta) https://www.llama.c
You Don't Need GPUs: Qwen4's Preview Is WILDLY Fast (opens the original)
Read excerpt
You Don't Need GPUs: Qwen4's Preview Is WILDLY Fast | Qwen4 | local llm setup | self hosted llm | open source ai tools ━━━━━━━━━━━━━━━━━━━━ 🔎 Research Qwen3.8-Flash-Next (Qwen4-exp) — the 125B/6B-active preview model this whole video breaks down. https://huggingface.co/Qwen/Qwen3.8-Flash-Next Unsloth GGUF quants — the 1-bit build that gets this model running on 75GB of RAM with zero GPU VRAM. https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF llama.cpp — the inference engine that added suppo
What DeepSeek Won't Tell You About Harness's "DONE" (opens the original)
Read excerpt
What DeepSeek Won't Tell You About Harness's "DONE" | deepseek harness | open source ai agent | self hosted llm ━━━━━━━━━━━━━━━━━━━━ 🔍 Research DeepSeek Harness (dsh) https://github.com/deepseek-ai/deepseek-harness Cordis (meta-framework powering the plugin architecture) https://github.com/deepseek-ai/deepseek-harness Claude Code https://claude.com/product/claude-code Codex CLI https://github.com/openai/codex OpenCode https://github.com/sst/opencode Goose https://github.com/block/goose Ollama ht
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
~52 subscribers
Measured Sep 19, 2026
Source's subscribers, not the number who saw an individual piece.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.