The Vaib Report · 2026-09-11
Daily Digest – 2026-09-11
Daily curated repos and tools for solo founders, AI/B2B SaaS builders, and small business tools. 1016 repos evaluated, 30 made the cut. Plus 38 picks from HuggingFace, Replicate, Papers with Code, npm, PyPI, GitLab, Ollama, and launch platforms.
Founder & Solopreneur Tools
sickn33/agentic-awesome-skills
Local catalog of 2,100+ agentic skills with agent-owned discovery, validation, and planning via CLI and MCP. (Python, 46.3k★)
★ 46,281
agno-agi/agno
Framework to build, run, and manage agent platforms with SDK, runtime, and web UI for full stack control. (Python, 42.1k★)
★ 42,139
MadsLorentzen/ai-job-search
Fork-and-own job search framework on Claude Code, evaluates postings, tailors CVs, writes cover letters, preps interviews. (Python, 41.8k★)
★ 41,817
mindsdb/mindshub
Unified workspace pairing open-source models with agent skills and MCP, pick your own models and keep your data. (Makefile, 39.7k★)
★ 39,723
Tool Sprawl & Alternatives
every-app/open-seo
Open source SEO suite with keyword research, rank tracking, backlinks, audits, and agent skills for Claude Code. (TypeScript, 18.4k★)
★ 18,379
supertokens/supertokens-core
Self-hosted auth provider with email, passwordless, OAuth, JWT RBAC, and SDKs for Node, Python, Go, React. (Java, 15.3k★)
★ 15,296
yusufkaraaslan/Skill_Seekers
Turn docs, repos, and PDFs into Claude skills with automatic conflict detection and built-in MCP server. (Python, 15k★)
★ 14,953
sml2h3/ddddocr
General-purpose captcha and OCR recognition with text detection, slide-solving, and API server. (Python, 14.7k★)
★ 14,736
UGC, Social & Creative Marketing
Vincentwei1021/video-shotcraft
Claude Code skill for cinematic product videos via Remotion: 152 shot templates, 209 motion previews, production-ready. (TypeScript, 8.1k★)
★ 8,076
apify/apify-mcp-server
MCP server that lets AI agents extract data from any website using thousands of ready-made Apify actors and tools. (TypeScript, 6.8k★)
★ 6,773
vllm-project/vllm-omni
Fast omni-modal inference (text, image, audio, video) with production serving, batching, and ComfyUI integration. (Python, 6.8k★)
★ 6,767
showlab/Awesome-Video-Diffusion
Curated list of video diffusion models for generation, editing, and restoration. (Multi, 5.8k★)
★ 5,776
salesforce/BLIP
Deprecated: archived repo; use LAVIS instead for vision-language pretraining (image captioning, VQA, retrieval). (Jupyter Notebook, 5.7k★)
★ 5,712
Oddities
NationalSecurityAgency/ghidra
Reverse engineering framework for binary analysis, decompilation, and malware research. (Java, 74.8k★)
★ 74,816
refined-github/refined-github
Browser extension that declutters GitHub UI and adds features like code search, PR insights, and status shortcuts. (TypeScript, 32.1k★)
★ 32,126
freestylefly/awesome-gpt-image-2
530+ GPT-4o image prompts, 20+ industrial templates, skill sets, and prompt comparison for GPT-4o 2.5. (JavaScript, 31.3k★ ⚡529★/day)
★ 31,316
gitleaks/gitleaks
CLI to find leaked credentials and secrets in git history, CI/CD, and filesystem scans. (Go, 29.2k★)
★ 29,240
bobeff/open-source-games
Curated list of open-source and commercial game remakes organized by genre. (Python, 13.9k★ ⚡126★/day)
★ 13,870
Own Your Iron
xyproto/algernon
Tiny self-contained Go web server with Lua, Teal, Markdown, React 19, SQLite, PostgreSQL, and live reload. (JavaScript, 3k★)
★ 3,028
thu-pacman/chitu
High-performance LLM inference engine for DeepSeek, Qwen, GLM, Kimi; supports Nvidia, Ascend, Huawei chips. (Python, 3k★)
★ 3,000
Dicklesworthstone/llm_aided_ocr
Boost Tesseract OCR with local or API LLMs for error correction, smart chunking, and markdown formatting. (Python, 3k★)
★ 2,996
vercel-labs/opensrc
CLI to fetch and cache npm, PyPI, Crates, and GitHub source for context injection into coding agents. (Rust, 3k★)
★ 2,979
stochasticai/xTuring
Fine-tune open-source LLMs (Llama, Qwen, GPT-2) locally with LoRA, INT8, and multi-GPU scaling. (Python, 2.7k★)
★ 2,674
AI Cost & Token Economics
ojuschugh1/sqz
CLI and Python SDK to compress LLM prompts, cut input tokens 24–92% without accuracy loss. (Rust, 621★)
★ 621
jia-gao/leanctx
Drop-in prompt compressor for OpenAI, Gemini, Anthropic; cuts input tokens 40–60% with MIT license, runs locally. (Python, 324★)
★ 324
project-koku/koku
Open source cloud cost management for AWS, Azure, GCP; audit spending, detect waste, forecast bills. (Python, 313★)
★ 313
kosty-cloud/kosty
Scan 30+ AWS services for cost waste, security gaps, IAM escalations, and GenAI workload audit in one command. (Python, 273★)
★ 273
siara-cc/Unishox2
Compact compression for short Unicode strings, optimized for Arduino and IoT (not for large text). (C, 249★)
★ 249
trufflesecurity/trufflehog
Find, verify, and analyze leaked credentials in git history, Jira, Slack, Confluence, Teams, SharePoint. (Go, 27.8k★)
★ 27,795
ruby/ruby
The Ruby programming language: interpreted, object-oriented, with mixins, iterators, closures, and garbage collection. (Ruby, 23.7k★ ⚡7★/day)
★ 23,724
Replicate Models
prunaai/p-video
Fast video generation with built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-to-video in a single endpoint. (3.6M runs)
prunaai/z-image-turbo-lora
Lora version of Z-Image Turbo, which is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI. (694K runs)
openai/gpt-image-2.5-sunburst
OpenAI's most capable image model, built for workflows where editing precision matters most. Generate and edit images from text and image inputs with strong instruction following, sharp text rendering, and detailed control. (43K runs)
openai/gpt-image-2.5-flare
OpenAI's fastest model for high-quality, everyday image generation. Generate and edit images from text and image inputs with strong instruction following and sharp text rendering. (35K runs)
prunaai/p-video-animate
p-video-animate animates a reference image with the motion and audio of a source video. Optimized for speed and cost — 5.24s per 1s of video. (25K runs)
Ollama Models
nomic-embed-text-v2-moe
nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval. (878.8K pulls)
meditron
Open-source medical large language model adapted from Llama 2 to the medical domain. (870.5K pulls)
command-r-plus
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases. (801K pulls)
mistral-small3.1
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. (787.4K pulls)
deepseek-v4-flash
DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview). (447.6K pulls)
npm Packages
pac-proxy-agent
A PAC file proxy `http.Agent` implementation for HTTP (20.3M/wk)
puppeteer-core
A high-level API to control headless Chrome over the DevTools Protocol (15.7M/wk)
puppeteer
A high-level API to control headless Chrome over the DevTools Protocol (8.5M/wk)
cypress
Cypress is a next generation front end testing tool built for the modern web (5.1M/wk)
PyPI Packages
HuggingFace Spaces
HuggingFace Models
jonatasgrosman/wav2vec2-large-xlsr-53-japanese
wav2vec2-large-xlsr-53-japanese (automatic-speech-recognition, 14.8M downloads)
timm/efficientnet_b3.ra2_in1k
efficientnet_b3.ra2_in1k (image-classification, 12.4M downloads)
argmaxinc/whisperkit-coreml
whisperkit-coreml (automatic-speech-recognition, 11.6M downloads)
Qwen/Qwen2.5-7B-Instruct
Qwen2.5-7B-Instruct (text-generation, 10.1M downloads)
pyannote/speaker-diarization-3.1
speaker-diarization-3.1 (automatic-speech-recognition, 9.0M downloads)
HuggingFace Datasets
New Launches
Anysite.io
Build and enrich B2B lists by chatting to your agent (346 upvotes) [producthunt]
Loqua
Speak naturally and move from thoughts to being done (306 upvotes) [producthunt]
Raycast 2.0
The next generation of Raycast is here (249 upvotes) [producthunt]
Wisry
Clone the ads already winning in your market, at scale (230 upvotes) [producthunt]
Cline Desktop App
An open-source app for open-weight models (181 upvotes) [producthunt]
easyspecs.ai
The spec review platform (135 upvotes) [producthunt]
Modeinspect
99 Days Free AI Credits - Design product UI in your codebase (128 upvotes) [producthunt]
Devin Voice
You say it, Devin ships it (110 upvotes) [producthunt]